WO2019176273A1 - 情報処理装置、情報処理方法、及びプログラム - Google Patents
情報処理装置、情報処理方法、及びプログラム Download PDFInfo
- Publication number
- WO2019176273A1 WO2019176273A1 PCT/JP2019/001191 JP2019001191W WO2019176273A1 WO 2019176273 A1 WO2019176273 A1 WO 2019176273A1 JP 2019001191 W JP2019001191 W JP 2019001191W WO 2019176273 A1 WO2019176273 A1 WO 2019176273A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- information processing
- processing apparatus
- information
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/014—Hand-worn input/output arrangements, e.g. data gloves
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/0304—Detection arrangements using opto-electronic means
- G06F3/0325—Detection arrangements using opto-electronic means using a plurality of light emitters or reflectors or a plurality of detectors forming a reference frame from which to derive the orientation of the object, e.g. by triangulation or on the basis of reference deformation in the picked up image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/1613—Constructional details or arrangements for portable computers
- G06F1/163—Wearable computers, e.g. on a belt
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/0304—Detection arrangements using opto-electronic means
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Definitions
- the present technology relates to an information processing device, an information processing method, and a program that can be applied to a wearable device or the like.
- Patent Document 1 discloses a projection system including a wristband type terminal and a smartphone.
- this projection system an image is transmitted from a smartphone to a wristband type terminal.
- the transmitted image is projected on the palm of the user by a projector mounted on the wristband type terminal.
- various GUIs projected on the palm can be operated like operating a smartphone.
- the usability of the mobile terminal is improved (paragraphs [0013] to [0025] in FIG. 1 of Patent Document 1).
- an object of the present technology is to provide an information processing apparatus, an information processing method, and a program capable of realizing high usability.
- an information processing apparatus includes a light source unit, a detection unit, and a determination unit.
- the light source unit irradiates light on a body part of a user.
- the detection unit includes a plurality of light detection units, and outputs a plurality of detection signals based on the reflected light reflected by the body part.
- the determination unit determines the movement of the user based on information about speckles generated by irradiation of the light to the body part, which is included in the plurality of detection signals.
- this information processing apparatus light is irradiated to a part of the user's body, and a plurality of detection signals are output based on the reflected light. And a user's motion is determined based on the information regarding the speckle contained in a some detection signal. Thereby, high usability can be realized.
- the light source unit may irradiate the body part with laser light.
- the plurality of light detection units may be a plurality of photodiodes.
- the determination unit may determine the movement of the user based on a speckle pattern included in information on the speckle.
- the determination unit may determine the movement of the user based on a time series change of the speckle pattern.
- the determination unit may determine the movement of the user based on the periodicity of the time series change of the speckle pattern.
- the body part may be a wrist.
- the determination unit may determine the movement of the user's hand.
- the determination unit may determine at least one of a bent finger type, a bent finger bending amount, an interaction between fingers, and an interaction between the finger and another object.
- the information processing apparatus may further include an execution unit that executes processing according to the determined movement.
- the execution unit may identify an operation input by the user based on the determined movement, and execute a process according to the identified operation.
- the information processing apparatus may further include a history information storage unit that stores history information related to operations input by the user in the past.
- the execution unit may identify an operation input by the user based on the stored history information.
- the information processing apparatus may further include a display unit capable of displaying a predetermined GUI (Graphical User Interface).
- the execution unit may identify an operation input to the displayed predetermined GUI based on the determined movement.
- the execution unit may select a plurality of selection candidates that can be selected by the user based on the determined movement.
- the display unit may display a selected image including the plurality of selected selection candidates.
- the determination unit may determine the movement of the user according to a predetermined learning algorithm.
- the information processing apparatus may further include an instruction unit and a determination information storage unit.
- the instruction unit instructs the user to perform a predetermined movement.
- the determination information storage unit stores determination information including information on the speckles included in the plurality of detection signals when the user performs the instructed predetermined movement. In this case, the determination unit may determine the movement of the user based on the stored determination information.
- the information processing apparatus may further include a reception unit that receives correct / incorrect information regarding whether the determination result by the determination unit is correct.
- the determination unit may determine the movement of the user based on the received correct / incorrect information.
- the detection unit may include an image sensor.
- the plurality of light detection units may be a plurality of pixels of the image sensor.
- An information processing apparatus includes a reception unit and a determination unit.
- the receiving unit receives a plurality of detection signals output based on reflected light reflected by the body part of the user in response to light irradiation on the body part of the user.
- the determination unit determines the movement of the user based on information on speckles generated by irradiation of the light to the body part, which is included in the received plurality of detection signals.
- An information processing method is an information processing method executed by a computer system, and is reflected by a part of the user's body in response to light irradiation on the part of the user's body Receiving a plurality of detection signals output based on the light. The movement of the user is determined based on information on speckles generated by irradiation of the light to the body part, which is included in the received plurality of detection signals.
- a program causes a computer system to execute the following steps. Receiving a plurality of detection signals output based on the reflected light reflected by the body part of the user in response to light irradiation on the body part of the user; Determining the movement of the user based on information about speckles generated by irradiation of the light on the body part, which is included in the plurality of received detection signals.
- FIG. 1 is a schematic diagram illustrating an appearance of a wearable device according to an embodiment of the present technology.
- the wearable device 100 is a wristband type wearable device, and is used by being worn on the wrist 2 of the user.
- the wearable device 100 corresponds to an embodiment of a recognition device and an information processing device according to the present technology.
- the wearable device 100 includes a main body 10 and a mounting belt 11.
- the body 10 is fixed by winding the attachment belt 11 around the wrist 2 and fastening it.
- the wearable device 100 is mounted so that the main body 10 is positioned on the inner side of the user's wrist 2 (the palm side portion).
- FIG. 2 is a schematic view of the wearable device 100 that is not worn by the user as viewed from the side.
- FIG. 3 is a block diagram illustrating a functional configuration example of the wearable device 100.
- the wearable device 100 includes a controller 12, a speaker 13, a projector 14, a touch panel 15, operation buttons 16, a communication unit 17, a sensor unit 18, and a storage unit 19. These blocks are mounted on the main body 10 of the wearable device 100.
- the speaker 13 can output sound.
- a voice guidance or an alarm sound is output from the speaker 13.
- the projector 14 can project various images and GUI (Graphical User Interface).
- GUI Graphic User Interface
- an image or a GUI is projected on a surface such as a desk or a wall on which the user's hand is placed.
- the touch panel 15 Various images and GUIs are displayed on the touch panel 15.
- the user can input a predetermined instruction or the like by touching the touch panel 15.
- the operation button 16 is provided to perform an operation different from the operation via the touch panel 15, for example, an operation of turning on / off the power.
- the projector 14 and the touch panel 15 function as a display unit.
- a gesture operation it is possible to easily input an instruction by a gesture using a hand (including a finger, a joint of a hand, a back of a hand, etc.). That is, it is possible to perform an input operation (gesture operation) using a gesture.
- the gesture is a concept included in “movement”. The input of the gesture operation will be described in detail later.
- the communication unit 17 is a module for executing network communication, short-range wireless communication, infrared communication, and the like with other devices.
- a wireless LAN module such as WiFi or a communication module such as Bluetooth (registered trademark) is provided.
- An arbitrary infrared communication module may be used.
- the sensor unit 18 includes a light source unit 21, a PD (Photodiode) array sensor 22, a camera 23, and a 9-axis sensor 24.
- the camera 23 can photograph the periphery of the wearable device 100. For example, the user's hand or face can be photographed by the camera 23.
- the 9-axis sensor 24 includes a 3-axis acceleration sensor, a 3-axis gyro sensor, and a 3-axis compass sensor.
- the nine-axis sensor 24 can detect, for example, the acceleration, angular velocity, and direction of the wearable device 100 in three axes.
- the light source unit 21 and the PD array sensor 22 are arranged side by side on the back surface 10a of the main body unit 10 (the surface facing the surface of the user's wrist 2).
- the light source unit 21 includes a laser light source, and irradiates the user's wrist 2 with the laser light L (see FIG. 4).
- the type of the laser light source is not limited, and various laser light sources such as a semiconductor laser, a gas laser, a solid laser, and a liquid laser may be used.
- the light source unit 21 may be provided with a lens system or the like that can adjust the luminous flux of the laser light emitted from the laser light source.
- the PD array sensor 22 is composed of a plurality of photodiodes (PD) 26 (see FIG. 5) arranged two-dimensionally.
- the PD 26 functions as a photodetector and can output a detection signal corresponding to the amount of incident light.
- the PD 26 can detect light with a time resolution of several tens of kHz, and can detect a change in the amount of light for a minute time. In the present embodiment, 100 PDs 26 are used, but the number of PDs 26 is not limited and may be set arbitrarily. The specific configuration of the PD 26 is not limited and may be arbitrarily designed.
- the light source unit 21 corresponds to a light source unit that irradiates light on a body part of a user.
- the wrist 2 is selected as the body part.
- the PD array sensor 22 includes a plurality of light detection units, and corresponds to a detection unit that outputs a plurality of detection signals based on the reflected light L1 (see FIG. 4) reflected by the body part (wrist 2).
- the plurality of light detection units are the plurality of PDs 26, and the detection signals output from the plurality of PDs 26 correspond to the plurality of detection signals.
- the storage unit 19 is a non-volatile storage device, and for example, an HDD (Hard Disk Drive) or the like is used.
- the storage unit 19 stores a control program for controlling the overall operation of the wearable device 100.
- the storage unit 19 stores learning data, history information, and the like, which will be described later.
- a method for installing the control program or the like in the wearable device 100 is not limited.
- the controller 12 controls the operation of each block that the wearable device 100 has.
- the controller 12 has a hardware configuration necessary for a computer such as a CPU and a memory (RAM, ROM). Various processes are executed when the CPU loads a control program or the like stored in the storage unit 19 to the RAM and executes it.
- a PLD Programmable Logic Device
- FPGA Field Programmable Gate Array
- ASIC Application Specific Integrated Circuit
- FIG. 4 is a schematic diagram for explaining operations of the light source unit 21 and the PD array sensor 22 arranged on the back surface 10 a of the main body unit 10.
- FIG. 5 is a diagram schematically showing the PD array sensor 22.
- FIG. 5A illustrates an arrangement example of a plurality of PDs 26, and
- FIG. 5B schematically illustrates intensity distributions of detection signals output from the plurality of PDs 26.
- the wearable device 100 is mounted on the bare skin. Therefore, the light source unit 21 and the PD array sensor 22 disposed on the back surface 10 a of the main body unit 10 are disposed to face the skin 4 covering the blood vessel 3. A minute gap is provided between the light source unit 21 and the PD array sensor 22 and the surface 4 a of the skin 4.
- the light source unit 21 irradiates the laser beam L toward the surface 4 a of the skin 4.
- coherent light such as the laser beam L
- the laser beam L is diffused (scattered) by the fine unevenness on the surface 4a of the skin 4.
- speckles spots
- a detection signal corresponding to the speckle pattern is output from each PD 26 of the PD array sensor 22.
- the intensity of the detection signal of the white PD 26 shown in FIG. 5B is the maximum, and the intensity of the detection signal of the black PD 26 is the minimum.
- the intensity of the detection signal is an intermediate value.
- FIG. 5B only two kinds of gray colors are schematically displayed, but of course, the present invention is not limited to this, and intensities included in the range from the minimum value to the maximum value depending on the amount of incident light.
- a detection signal is output.
- the intensity distribution of the plurality of detection signals output from the plurality of PDs 26 is an intensity distribution according to the speckle pattern generated. That is, the intensity distribution of the plurality of detection signals corresponds to the planar intensity pattern of the generated speckle.
- the speckle pattern is a pattern according to the shape of the surface 4a of the skin 4, and when the shape of the surface 4a changes, the speckle pattern also changes. For example, when a finger is moved, muscles and tendons connected from the hand to the arm move, and the shape of the surface 4a of the skin 4 changes. That is, when the finger is moved, the speckle pattern generated by irradiating the laser beam L changes.
- the inventor has focused on this point and newly found out that the movement of the hand around the finger is determined by capturing the movement of the muscle / tendon based on the speckle pattern. That is, the present inventors have newly found that the movement of the hand is determined based on the current speckle pattern, the time series change of the speckle pattern, and the like.
- the intensity distribution of the plurality of detection signals output from the PD array sensor 22 corresponds to the speckle pattern. Therefore, by analyzing the intensity distribution of the plurality of detection signals output from the PD array sensor 22, it is possible to capture the movement of the muscle / tendon and determine the movement of the hand.
- FIG. 6 is a schematic diagram showing an example of changes in hand motion and intensity distribution of detection signals.
- the left index finger is bent inward.
- 6B the muscle / tendon that moves the finger is deformed, and the surface 4a of the skin 4 covering the muscle / tendon is deformed near the wrist 2.
- the speckle pattern at the time of laser irradiation changes. Therefore, as shown in FIG. 6C, the intensity distribution of the plurality of detection signals output from the PD array sensor 22 changes.
- the intensity distribution of the detection signal is further schematically illustrated.
- the deformation position and deformation method of the muscle / tendon differ, so the speckle pattern changes in different ways. come. Therefore, by analyzing the intensity distribution of the plurality of detection signals output from the PD array sensor 22, it is possible to determine the type of the bent finger and the way the finger is bent (the amount of bending of the finger, the bending speed, etc.). It is.
- FIG. 7 is a schematic diagram for explaining the determination of the interaction between fingers and the interaction between the finger and another object.
- the interaction between fingers includes arbitrary interactions such as hitting fingers (making two fingers collide with each other) and rubbing fingers (rubbing fingers together).
- the interaction between the finger and another object includes any interaction such as hitting the object with the finger or rubbing the finger against the object.
- the muscles and tendons inside the hand vibrate.
- the shape of the surface 4a of the skin 4 changes and the speckle pattern also changes according to the frequency of vibration (vibration period).
- vibration period For example, when a finger hitting sound is generated, it is considered that muscles / tendons vibrate at a frequency equivalent to the frequency of the sound and the speckle pattern changes.
- the periodicity of the time series change of the speckle pattern by analyzing the periodicity of the time series change of the speckle pattern, it becomes possible to determine the interaction between the finger and the finger or the finger and the object. That is, it is possible to determine the interaction between the finger and the finger or the finger and the object by analyzing the time series change of the signal intensity schematically illustrated in FIG.
- the analysis of the periodicity of the time series change includes analysis of arbitrary parameters related to the periodicity of the time series change such as the shape of the frequency distribution of the time series change and the peak frequency of the period.
- frequency analysis is performed for a time-series change in signal intensity when the finger is stationary and a time-series change in signal intensity when the finger or the like is hit.
- a peak occurs at a specific frequency when a desk or the like is hit with a finger. This is because the muscles and tendons vibrate when the finger is struck, thereby causing the surface 4a of the skin 4 to vibrate, and the influence appears as vibration of vibration intensity.
- the positional relationship and structure of muscles and tendons differ. Therefore, the vibration frequency of muscles and tendons is different, and the frequency of time-series change of the speckle pattern (signal intensity), the peak frequency, the shape of the frequency distribution, and the like are also different.
- the intensity distribution of the detection signal output from the PD array sensor 22, the time series change, the periodicity of the time series change (the frequency of the time series change, the peak frequency of the time series change period, etc.) Included in the information relating to speckles generated by irradiating the body part with light included in the detection signal.
- the information regarding speckle includes arbitrary information regarding generated speckle, and includes, for example, a spatial speckle pattern feature and a time series feature that can be detected from a detection signal. Since the intensity of the detection signal itself is determined corresponding to the speckle, it is included in the information on the speckle.
- the determination of the user's movement based on the intensity distribution of the plurality of detection signals is included in the determination of the user's movement based on the speckle pattern.
- the determination of the user's movement based on the time series change of the plurality of detection signals is included in the determination of the user's movement based on the time series change of the speckle pattern.
- the determination of the user's movement based on the periodicity of the time series change of the plurality of detection signals is included in the determination of the user's movement based on the periodicity of the time series change of the speckle pattern.
- the determination may be executed based on the time series change of some of the detection signals. That is, the determination based on the time-series change of the speckle pattern (the peak frequency of the time-series change) is determined based on the time-series change (the peak frequency of the time-series change) of some of the detection signals. including. There may be a case where determination of the user's movement is executed by paying attention to the detection signal of one PD 26.
- FIG. 8 is a block diagram illustrating a software configuration example of the wearable device 100.
- FIG. 9 is a flowchart illustrating an operation example of the wearable device 100.
- the detection signal output from the PD array sensor 22 may be referred to as a speckle signal.
- the CPU of the controller 12 executes a program according to the present technology, so that the speckle signal receiving unit 30, the speckle signal analyzing unit 31, the motion determining unit 32, the operation identifying unit 33, and the process executing unit 34 are performed. Is realized. And the information processing method which concerns on this technique is performed by these blocks. Note that dedicated hardware may be appropriately used to implement each block.
- the storage unit 19 is schematically illustrated in the controller 12 in order to easily understand that the learning data and the history information are appropriately read from the storage unit 19.
- the speckle signal receiving unit 30 receives a plurality of detection signals (speckle signals) output from the PD array sensor 22 (step 101).
- the speckle signal receiving unit 30 functions as a receiving unit.
- the speckle signal analysis unit 31 analyzes the speckle signal (step 102).
- the speckle pattern analysis unit 35 analyzes the speckle pattern.
- the time-series speckle signal analysis unit 36 analyzes the time-series change of the speckle pattern over a plurality of times. As described above, these analysis results are included in the information on speckle.
- the movement determination unit 32 determines the movement of the user's hand based on the analysis result of the speckle signal analysis unit 31. That is, the gesture made by the user is determined (step 103).
- the motion determination unit 32 corresponds to a determination unit that determines a user's motion based on information about speckles included in a plurality of detection signals.
- a user's movement is determined according to a predetermined machine learning algorithm.
- a machine learning algorithm using a neural network such as RNN (Recurrent Neural Network), CNN (ConvolutionalMNeural Network), MLP (Multilayer Perceptron) or the like is used.
- RNN Recurrent Neural Network
- CNN ConvolutionalMNeural Network
- MLP Multilayer Perceptron
- any machine learning algorithm that executes a supervised learning method, an unsupervised learning method, a semi-supervised learning method, a reinforcement learning method, or the like may be used.
- the storage unit 19 stores learning data including a correct answer label (user's gesture) and a speckle signal analysis result corresponding to the correct answer label.
- the motion determination unit 32 performs learning according to a predetermined machine learning algorithm using the stored learning data. Thereby, it is possible to improve the accuracy of the user's gesture determination.
- FIG. 10 and 11 are tables showing examples of gesture patterns that can be determined. As shown in FIG. 10, a gesture of shaking a finger in the air can be determined as a single finger operation. It is possible to determine both the shaking motion with one finger and the shaking motion with a plurality of fingers.
- spatial direction information that is, a two-dimensional speckle pattern
- the analysis target PD 26 and its detection signal may be appropriately selected.
- the sensor area corresponding to the movement of each finger can be set based on, for example, the movement of the finger and the change in the speckle pattern in advance.
- a sensor area corresponding to the movement of each finger may be set by machine learning.
- the time direction information that is, the time-series change of the detection signal output from each PD 26, an intensity change occurs in a cycle corresponding to the shaking operation.
- the time change of the detection signal of the PD 26 in the sensor area corresponding to the movement of the index finger is analyzed.
- the shaking motion is determined based on the periodicity.
- the features of the spatial direction information and the time direction information for the shaking motion shown in FIG. 10 are examples found by the inventor, and are not limited to cases where such features are seen. For example, even when other characteristics are seen, it is possible to determine the motion to shake based on the characteristics. As a matter of course, the motion of shaking may be determined by inputting the signal strength and the time series change of the strength as they are by machine learning.
- the sensor area with the largest change is calculated based on the change in the intensity distribution of the detection signal.
- the finger moved based on the calculated sensor area is determined, and the movement of the finger is determined based on the detection signal of the PD 26 included in the sensor area. Such a determination method is also possible.
- the gesture of bending the finger can be determined as a single finger operation. It is possible to determine both the bending operation with one finger and the bending operation with a plurality of fingers.
- the time change of the detection signal of the PD 26 in the sensor area corresponding to the movement of the index finger is analyzed. Since the amount of deformation of the surface 4a of the skin 4 increases due to finger bending, the intensity fluctuation of the detection signal (intensity fluctuation of the scattered light) increases. Based on such characteristics, the bending operation can be determined.
- the present invention is not limited to such a case.
- a gesture of rubbing fingers and a gesture of hitting fingers as movements between fingers.
- a sensor area related to rubbing between the index finger and the thumb and a sensor area related to hitting the index finger and the thumb are set as analysis targets.
- the sensor area related to each operation can be set based on, for example, each movement and a change in speckle pattern in advance. Of course, it may be set by machine learning.
- gesture determination is executed by paying attention to the fact that the peak frequency due to finger rubbing and the peak frequency due to finger hitting each have a unique value. That is, based on the peak frequency of the time series change of the detection signal of each PD 26, a gesture for rubbing fingers and a gesture for tapping fingers are determined.
- the present invention is not limited to such a case.
- the moving average (average for each predetermined section) of the intensity of the detection signal of the PD 26 is acquired as “time direction information” of “single finger movement”. By calculating the average for each predetermined section, it is possible to smooth the fine time fluctuation and see the signal trend macroscopically.
- the intensity change of the detection signal of the PD 26 is acquired as it is as “time direction information”. As described above, various methods may be adopted as a method of acquiring “time direction information” from the detection signal.
- a gesture of rubbing a finger against an object can be determined as an operation between the finger and the object. Either a rubbing operation with one finger or a rubbing operation with a plurality of fingers can be determined. It is also possible to determine each of the rubbing operations with different rubbing directions.
- one PD 26 in the sensor area corresponding to the movement of the index finger is selected as an analysis target. Based on the peak frequency of the time series change of the detection signal of the PD 26, a gesture of rubbing a finger against the object is determined.
- the present invention is not limited to such a case.
- a gesture of hitting an object with a finger can be determined as an operation between the finger and the object. It is possible to determine both a tapping action with one finger and a tapping action with a plurality of fingers.
- one PD 26 in the sensor area corresponding to the movement of the index finger is selected as an analysis target. Based on the peak frequency of the time-series change of the detection signal of the PD 26, a gesture of hitting an object with a finger is determined.
- the present invention is not limited to such a case.
- the frequency of the time-series change of the detection signal and the peak frequency vary depending on how the finger is bent (such as the amount of bending of the finger and the bending speed). . Therefore, by analyzing the time-series change of the detection signal, it is possible to determine how to bend the finger (such as the amount of bending of the finger and the bending speed) when the object is hit with a finger.
- the operation identifying unit 33 identifies the operation input by the user based on the determined gesture (step 104). That is, the content of the input operation (gesture operation) using the gesture is identified.
- the process execution unit 34 executes a process according to the gesture determined by the movement determination unit 32. Specifically, the process according to the operation input by the user identified by the operation identifying unit 33 is executed (step 105). In the present embodiment, an execution unit is realized by the operation identification unit 33 and the process execution unit.
- FIG. 12 is a schematic diagram for explaining an example of a virtual remote controller using the present technology. For example, as illustrated in FIG. 12A, it is assumed that a user is sitting in a room and the wearable device 100 according to the present technology is mounted on the left hand of the user.
- remote controller remote control
- a gesture is associated with a device operation. Selection of gesture ⁇ control target device to shake one finger up and down as shown in FIG. 12B Selection of tap ⁇ operation item between fingers as shown in FIG. 12C Control over gesture ⁇ operation item as shown in FIG. 12D
- the gesture that shakes one finger up and down is determined by the movement determination unit 32.
- the operation identifying unit 33 identifies that an operation for selecting a device to be controlled is input by the gesture. Here, it is assumed that the television is selected as the device to be controlled.
- the tap between fingers is determined by the motion determination unit 32.
- the operation identifying unit 33 identifies that an operation for selecting an operation item is input by the gesture. Here, it is assumed that volume adjustment is selected.
- the movement determination unit 32 determines a gesture for rubbing fingers.
- the operation identifying unit 33 identifies that control for the operation item is input by the gesture. For example, it is assumed that a fast rubbing ⁇ volume up, a slow rubbing ⁇ volume down, etc. are assigned.
- the operation identifying unit 33 identifies whether the input operation is volume up or volume down.
- the process execution unit 34 executes a process according to the identified input operation. That is, when the volume is increased, a control signal for increasing the volume is transmitted to the television. When the volume is down, a control signal for decreasing the volume is transmitted to the television.
- a virtual remote controller can be realized, and high usability can be realized. Assignment of a remote control operation or the like to a gesture, a device to be controlled, a control method, and the like can be arbitrarily set.
- FIG. 13 is a diagram for explaining an example of a virtual dialog box using the present technology.
- the wearable device 100 according to the present technology is worn on the right hand.
- the projector 14 of the wearable device 100 displays a spinning wheel UI 37 as a dialog box on the surface of a desk or wall.
- the displayed spinning wheel UI 37 can be operated by a gesture using the finger of the right hand.
- a wheel to be rotated is selected according to the kind of finger, and the selected wheel is rotated by a gesture of rubbing the finger.
- a gesture of rubbing the thumb against the surface an operation to rotate the left end wheel is recognized, and the left end wheel is rotated.
- an operation to rotate the center wheel is recognized, and the center wheel is rotated.
- an operation to rotate the rightmost wheel is recognized, and the rightmost wheel is rotated.
- the input operation of the selected numerical value is identified by rotating the wheel, and the input of the selected numerical value is executed. For example, such processing is executed.
- a display 38 that functions as a display unit is provided at a position outside the wrist (on the back of the hand).
- the spinning wheel UI 37 ′ displayed on the display 38 can be operated by a gesture using the finger of the right hand.
- the present technology is applicable not only to the spinning wheel UI 37 but also to various input UIs as shown in FIGS. 14A and 14B.
- a column is selected according to the type of finger, and a row is selected according to how the finger is moved, and the character or numerical value to be input is determined.
- Other gestures may be used as appropriate.
- this technology is applied to any GUI such as a UI for selecting a desired selection tab from a plurality of selection tabs or a UI for displaying a menu including a plurality of options when a pull-down button is selected. It is possible to apply.
- FIG. 15 is a diagram for explaining an example of a virtual keyboard using the present technology.
- wearable device 100 is attached to the left hand of the user.
- keyboard input becomes possible. For example, a tap with a predetermined finger is determined, and the key input operation is recognized based on the type of the finger, how to spread the hand, how the finger is bent, and the like. Then, the corresponding key is input.
- the wearable device 100 by wearing the wearable device 100 according to the present technology on the wrists of both hands, it is possible to determine a gesture using ten fingers and to realize a virtual keyboard. This makes it possible to achieve high usability.
- the camera 23 provided in the wearable device 100 captures a hand that is not attached to the wearable device 100. It is also possible to determine the movement of the hand based on the captured image and identify the key input. Such a method may be used to implement a virtual keyboard.
- the wearable device 100 is mounted so that the main body 10 is located outside the wrist (on the back side of the hand).
- the position at which the main body portion 10 is fixed is not limited, and may be arbitrarily set as long as it is disposed to face the skin.
- FIG. 17 is a diagram for explaining an example of virtual flick input using the present technology.
- Flick input can be performed by a gesture using a finger. For example, when it is determined that the finger touches for a predetermined time or longer, a process of displaying the UI 39 for flick input around is executed. After that, when a gesture for rubbing a finger and a gesture for separating a finger are determined, it is identified which character has been selected based on how the finger is rubbed (rubbing direction, etc.), and input of the selected character is executed. Is done.
- the user selects a character by tapping on the UI for flick input. Also in this case, it is possible to identify which character has been selected by detecting vibration or the like corresponding to the tap. This makes it possible to achieve high usability.
- the identification processing by the operation identification unit 33 may be executed using history information stored in the storage unit 19.
- the history information is information related to operations input by the user in the past, and is not limited to operations input using gestures, but may include information related to operations input by other methods.
- the storage unit 19 that stores history information corresponds to a history information storage unit.
- the input data history input in the past is referred to as history information.
- the input data is accumulated, and the next input is predicted from the pattern of the input data. It is possible to improve the identification accuracy by comprehensively identifying the input operation after combining the identification based on the gesture and the prediction result.
- N-gram As a prediction from the input data pattern, there is a method using N-gram.
- the frequency of N consecutive input data strings is stored, the frequency distribution is used to obtain the probability of the input next to the N ⁇ 1 input strings, and the higher one is used as the estimation result. For example, assume that “son” is input. In this case, it is assumed that the frequency distribution of the next input is (sony: 7, song: 10, sona: 2, son: 1). Therefore, the estimation result is “g” (probability 1/2).
- the reliability of the gesture determination, the reliability of the operation identified based on the gesture determination, and the like may be calculated, and the parameters may be used when performing comprehensive determination.
- history information Even when an application other than a virtual keyboard is being executed, operation identification using history information can be performed.
- the specific type of the history information is not limited, and arbitrary information may be used as the history information. Moreover, it is not limited to the system using N-gram, and an arbitrary system may be used.
- FIG. 18 is a schematic diagram showing an example of the selected image.
- the selected image is an image including a plurality of selection candidates that can be selected by the user, and corresponds to a candidate selection GUI.
- the operation identifying unit 33 may identify a plurality of operations as a plurality of candidates based on the gesture determination. For example, when key input using a virtual keyboard is being executed, it is assumed that two operations of “H” input operation and “J” input operation are identified as candidates based on gesture determination. In such a case, a selection image 40 having “H” and “I” as selection candidates as shown in FIG. 18 is displayed. The selection image 40 can also be said to be an image that informs the user that two of “H” and “I” have been identified as operation candidates.
- the selected image 40 includes “other” in which it can be input that it is not a selection candidate.
- the user operates the selection image 40 to select any one of “H”, “I”, and “other”.
- the operation can also be input using a gesture.
- By displaying the selection image 40 it is possible to easily input an operation even when there are a plurality of candidates. Even if the operation is identified incorrectly, only one step of selecting “other” is required without causing the user to go through the two steps of “erase” ⁇ “reselect”. This makes it possible to achieve high usability.
- an input indicating that it is not a selection candidate can be assigned to a special operation. For example, when two taps are input at the same time, it is input that they are not selection candidates in the selection image 40.
- the selected image 40 can be displayed even when an application other than the virtual keyboard is being executed.
- a selection image including a plurality of selection candidates corresponding to each application may be displayed as appropriate.
- a selection image is displayed when the reliability is below a predetermined threshold value. Such processing is also possible.
- an instruction processing execution unit 45 and a learning data generation unit 46 are configured in the controller 12.
- the instruction process execution unit 45 instructs the user to execute a predetermined movement (predetermined gesture).
- the learning data generation unit 46 generates learning data including an analysis result (information on speckle) of a speckle signal output from the PD array sensor 22 when a predetermined gesture instructed by the user is executed. That is, the gesture instructed to the user is set as a correct answer label, and the analysis result when the user executes the gesture is associated with each other and generated as learning data.
- the learning data corresponds to determination information
- the storage unit 19 that stores the learning data corresponds to a determination information storage unit.
- the projector 14 of the wearable device 100 displays the input UI shown in FIG. 14B on a display surface such as a desk.
- the following instruction is executed by displaying a text image or outputting sound from the speaker 13.
- (1) Tap the index finger on the display surface with the sensation of hitting “4”
- (2) Move the index finger to the upper side and tap it with the sensation of hitting “7” above
- (2) Down one Move the index finger downward and tap it with the sensation of hitting “1”
- the instruction processing execution unit 45 outputs gesture information corresponding to the instructions (1) to (4), that is, information serving as a correct answer label, to the learning data generation unit 46.
- the learning data generation unit 46 generates learning data by associating the received correct answer label with the analysis result when the gesture is executed.
- the projector 14, the speaker 13, and the instruction processing execution unit 45 realize an instruction unit.
- gestures are executed by the user is not limited and may be arbitrarily set.
- the method of executing the gesture is not limited, and any method may be adopted.
- correct / incorrect information regarding whether or not the determination result of the gesture determination is correct is input via the user input unit 47.
- any configuration capable of inputting correct / incorrect information may be employed.
- correct / incorrect information may be input by an operation on the UI displayed by the projector 14 shown in FIG. 3, an operation on the touch panel 15, or an operation on the operation button 16.
- selection of the delete key “Del” displayed by the projector 14 or the touch panel 15, selection of a predetermined delete button included in the operation button 16, or the like may be performed.
- a microphone etc. may be mounted and correct / error information may be input by a user's voice input.
- correct / incorrect information may be input by a special gesture operation.
- the correct / incorrect information regarding whether or not the determination result of the gesture determination is correct is typically information indicating whether or not the process executed by the process execution unit is correct.
- information indicating that is input as correct / incorrect information For example, when “J” is input even though “H” is input using the virtual keyboard, correct / incorrect information indicating that the determination result of the gesture determination is incorrect is input. Other information may be used as correct / incorrect information.
- the present invention is not limited to inputting information indicating that the determination result is incorrect, and information indicating that the determination result is correct may be input.
- information indicating that the determination result is correct may be input.
- the process is re-executed, and correct correct / incorrect information is input in order to input that the process is correct.
- it is not limited to such a case.
- the correct / incorrect information input by the user is received by the feedback receiving unit 48 configured in the controller 12.
- the feedback receiving unit 48 outputs the correct / incorrect information to the learning data generating unit 46.
- the feedback receiving unit 46 functions as a receiving unit.
- the learning data generation unit 46 generates learning data based on the determination result by the motion determination unit 32 and the analysis result output from the speckle signal analysis unit 31 and stores the learning data in the storage unit 19.
- the correct / incorrect information output from the feedback receiver 48 is referred to. For example, when correct / incorrect information indicating an incorrect answer is received, the learning data generated when the process of accepting the incorrect answer feedback is updated.
- the process is then redone and the correct feedback is received.
- the learning data can be updated by updating the correct answer label to a gesture related to the redo process. If the learning data cannot be updated, the learning data may be discarded.
- the wearable 100 As described above, in the wearable 100 according to the present embodiment, light is irradiated onto the body part of the user, and a plurality of detection signals are output based on the reflected light.
- the user's gesture is determined based on information on speckles included in the plurality of detection signals, that is, the analysis result of the speckle signals.
- the wearable device 100 increases the gesture based on information on speckles generated by irradiating the body part with light, that is, speckle patterns, time-series changes / peak frequencies of speckle patterns, and the like. It is possible to determine the accuracy and identify the input operation with high accuracy.
- the PD array sensor 22 is used as the detection unit. Therefore, it is possible to detect a change in the amount of light for a minute time compared to an image sensor such as a CCD (Charge-Coupled Device) sensor or a CMOS (Complementary Metal-Oxide-Semiconductor) sensor. As a result, it is possible to determine the user's gesture with high accuracy.
- an image sensor such as a CCD (Charge-Coupled Device) sensor or a CMOS (Complementary Metal-Oxide-Semiconductor) sensor.
- the PD array sensor 22 can be operated with lower power consumption than an image sensor, and can be driven for a long time.
- the sensitivity is high, the power of the laser beam emitted to the body part can be reduced, which is advantageous in reducing power consumption. Further, it is possible to reduce the size of the condenser lens and the like, and it is possible to reduce the cost.
- the wearable device 100 it is possible to sufficiently suppress the influence of the brightness of the environment where the wearable device 100 is used. For example, when an image sensor is used and a hand movement is photographed, the identification accuracy decreases if the surroundings are dark.
- the light source unit 21 and the PD array sensor 22 are arranged at a position very close to the body part, and the intensity of the reflected light is detected. Therefore, it is possible to analyze a speckle pattern or the like with high accuracy without being affected by surrounding brightness.
- the image sensor functions as a detection unit, and a plurality of pixels of the image sensor function as a plurality of light detection units.
- a plurality of pixel signals output from a plurality of pixels correspond to a plurality of detection signals.
- a determination information storage unit and a history information storage unit are realized by the storage unit 19, and a motion determination process using learning data and an operation identification process using history information are executed.
- the present invention is not limited to this, and a configuration that does not include one or both of the determination information storage unit and the history information storage unit is also included in an embodiment of the information processing apparatus according to the present technology. That is, the motion determination process may be executed without using determination information such as learning data, or the operation identification process may be executed without using history information.
- a configuration that does not include the history information storage unit may be employed as an embodiment of the information processing device according to the present technology.
- the determination information storage unit and the history information storage unit are realized by the storage unit 19, but the determination information storage unit and the history information storage unit may be configured separately by different storages or the like.
- the user's movement was determined by machine learning based on the analysis result of the speckle signal. Based on the determination result, the operation input by the user is identified.
- the present invention is not limited to this, and the operation input by the user may be identified by machine learning based on the analysis result of the speckle signal. In other words, it may be estimated what the input operation is without determining how the user has moved.
- the motion determination unit 32 and the operation identification unit 33 shown in FIG. 8 and the like are integrated to form an input estimation unit.
- the input operation may be identified by machine learning based on the analysis result of the speckle signal.
- Such a configuration also corresponds to an embodiment of a recognition device and an information processing device according to the present technology. Also with such a configuration, it is possible to similarly execute processing using history information and learning data.
- gesture determination and operation identification were performed based on the analysis result of the speckle signal. Instead, gesture determination and operation identification may be executed by machine learning or the like from the detection signal output from the PD array sensor. That is, the analysis step may be omitted.
- gesture determination and operation identification may be executed on a rule basis using table information or the like. Even when machine learning is not used, data corresponding to the learning data shown in FIG. 8 and the like can be appropriately used as determination information. Of course, any learning algorithm other than machine learning can be employed.
- the case where a laser light source is used for the light source unit is taken as an example. Note that the present technology can be applied even when another coherent light source capable of emitting coherent light is used.
- a PD array sensor in which a plurality of PDs are arranged two-dimensionally was used.
- the present invention is not limited to this, and a PD array sensor in which a plurality of PDs are arranged one-dimensionally may be used.
- FIG. 21 is a schematic diagram showing another example of a position where the main body is fixed.
- the wearable device 100 may be mounted so that the main body 10 is located outside the wrist (on the back of the hand).
- the main-body parts 10a and 10b may be fixed to the inner side and the outer side of a wrist, respectively. That is, analysis of speckle patterns or the like may be executed at two locations, the inner portion and the outer portion of the wrist.
- the position and number of the light source unit and the detection unit are not limited and may be set arbitrarily.
- the wearing state of the wearable device may be determined based on the analysis result of the speckle signal. For example, it is possible to detect the position shift of the main body (light source and detection unit) and to prompt the user to confirm the wearing state. It is also possible to execute gesture determination and operation identification with reference to the position information of the main body (light source and detection unit).
- a wristband type wearable device is taken as an example, but the present invention is not limited to this.
- a bracelet for the upper arm, a headband for the head (head mount), a neckband for the neck, a torso for the chest, a belt for the waist, an anklet for the ankle The present technology can be applied to various wearable devices such as a watch type, a ring type, a necklace type, an earring type, and a pierced type.
- the part irradiated with light is not limited, and may be arbitrarily selected.
- the user movement that can be determined by using the present technology is not limited to the movement of the user's hand.
- the part where the wearable device is worn that is, the part irradiated with light, the foot (thigh, knee, calf, ankle, toe), neck, waist, buttocks, arms, head, face, chest It is possible to determine the movement of any part such as.
- Sign language translation Captures the movement of fingers and arms, and verbalizes the sign language expression (for example, displayed on a smartphone)
- Action recognition Captures the movement of holding and grasping objects and recognizes user actions (spoon and chopstick movement, PC operation, car driving, hanging leather gripping, etc.)
- Pen input recording When a notebook is filled with a pen, the pen movement is simultaneously recorded on an electronic medium.
- the movement of the user may be determined by combining a PD array sensor and an acceleration sensor.
- the movements determined based on the results of the sensors may be integrated, or the user's movements may be determined by machine learning or the like using the results of the sensors as inputs.
- the information processing method and program according to the present technology can be executed not only in a computer system configured by a single computer but also in a computer system in which a plurality of computers operate in conjunction with each other.
- the system means a set of a plurality of components (devices, modules (parts), etc.), and it does not matter whether all the components are in the same housing. Accordingly, a plurality of devices housed in separate housings and connected via a network and a single device housing a plurality of modules in one housing are all systems.
- all or some of the functions of the blocks included in the controller 12 may be executed by the cloud server.
- the information processing method according to the present technology may be executed by interlocking a plurality of computers that can communicate with each other.
- the execution of each process by a predetermined computer includes causing another computer to execute a part or all of the process and acquiring the result.
- the information processing method and program according to the present technology can also be applied to a configuration of cloud computing in which one function is shared by a plurality of devices via a network and is jointly processed.
- this technique can also take the following structures.
- a light source unit that irradiates light on a body part of a user;
- a detection unit having a plurality of light detection units and outputting a plurality of detection signals based on the reflected light reflected by the body part;
- An information processing apparatus comprising: a determination unit that determines the movement of the user based on information about speckles generated by irradiation of the light to the body part included in the plurality of detection signals.
- the information processing apparatus according to (1) The light source unit irradiates a laser beam to a part of the body.
- the plurality of light detection units are a plurality of photodiodes.
- the information processing apparatus determines the user's movement based on a speckle pattern included in information on the speckle.
- the information processing apparatus according to (4) determines the user's movement based on a time-series change of the speckle pattern.
- the information processing apparatus according to (5) determines the user's movement based on the periodicity of the time-series change of the speckle pattern.
- the information processing apparatus determines the movement of the user's hand.
- the information processing apparatus determines at least one of a bent finger type, a bent finger bending amount, an interaction between fingers, and an interaction between a finger and another object.
- An information processing apparatus comprising: an execution unit that executes processing according to the determined movement.
- the information processing apparatus identifies an operation input by the user based on the determined movement, and executes a process according to the identified operation.
- (11) The information processing apparatus according to (10), wherein A history information storage unit for storing history information related to operations input by the user in the past, The execution unit identifies an operation input by the user based on the stored history information.
- the information processing apparatus according to (10) or (11), A display unit capable of displaying a predetermined GUI (Graphical User Interface); The execution unit identifies an operation input to the displayed predetermined GUI based on the determined movement. (13) The information processing apparatus according to (12), The execution unit selects a plurality of selection candidates that the user can select based on the determined movement, The information processing apparatus, wherein the display unit displays a selected image including the plurality of selected selection candidates. (14) The information processing apparatus according to any one of (1) to (13), The information processing apparatus determines the user's movement according to a predetermined learning algorithm.
- the information processing apparatus according to any one of (1) to (14), An instruction unit for instructing the user to perform a predetermined movement; A determination information storage unit that stores determination information including information about the speckles included in the plurality of detection signals when the user performs the instructed predetermined movement; and The determination unit determines the user's movement based on the stored determination information.
- the information processing apparatus according to any one of (1) to (15), Comprising a receiving unit for receiving correct / incorrect information regarding whether or not the determination result by the determination unit is correct; The determination unit determines the user's movement based on the received correct / incorrect information.
- the detection unit includes an image sensor, The plurality of light detection units are a plurality of pixels of the image sensor.
- a receiving unit that receives a plurality of detection signals output based on reflected light reflected by the body part of the user in response to light irradiation on the body part of the user;
- An information processing apparatus comprising: a determination unit configured to determine the user's movement based on information on speckles generated by irradiation of the light to the body part included in the plurality of received detection signals.
- a program for causing a computer system to execute a step of determining the movement of the user based on information on speckles generated by irradiation of the light to the body part, which is included in the plurality of received detection signals.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Multimedia (AREA)
- Psychiatry (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Description
前記光源部は、ユーザの体の部位に光を照射する。
前記検出部は、複数の光検出部を有し、前記体の部位により反射された反射光に基づいて、複数の検出信号を出力する。
前記判定部は、前記複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する。
前記指示部は、前記ユーザに所定の動きの実行を指示する。
前記判定用情報記憶部は、前記ユーザが前記指示された所定の動きを実行した際の、前記複数の検出信号に含まれる前記スペックルに関する情報を含む判定用情報を記憶する。
この場合、前記判定部は、前記記憶された判定用情報に基づいて、前記ユーザの動きを判定してもよい。
前記受信部は、ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信する。
前記判定部は、前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する。
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きが判定される。
ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信するステップ。
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定するステップ。
図5Aでは、複数のPD26の配置例が図示されており、図5Bでは、複数のPD26から出力される検出信号の強度分布が模式的に表現されている。
図12Bに示す1本の指を上下に振るジェスチャー⇔制御対象となる機器の選択
図12Cに示す指間のタップ⇔操作項目の選択
図12Dに示す指同士擦るジェスチャー⇔操作項目に対する制御
(1)「4」を打つ感覚で、人差指を表示面にタップさせる
(2)1つ上の「7」を打つ感覚で、人差指を上方側へ移動させてタップさせる
(3)1つ下の「1」を打つ感覚で、人差指を下方側へ移動させてタップさせる
(4)さらに1つ下の「0」を打つ感覚で、人差指をさらに下方側へ移動させてタップさせる
本技術は、以上説明した実施形態に限定されず、他の種々の実施形態を実現することができる。
手話翻訳:手腕指の動きを捉え、手話表現を言語化(例えばスマートフォンに表示)
行動認識:物を持つ、掴むという動きを捉え、ユーザの行動を認識(スプーンや箸の動き、PC操作、車運転、吊革掴む等)
ペン入力記録:ノート等にペンで記入時に、同時にペンの動きを電子媒体に記録
(1)ユーザの体の部位に光を照射する光源部と、
複数の光検出部を有し、前記体の部位により反射された反射光に基づいて、複数の検出信号を出力する検出部と、
前記複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する判定部と
を具備する情報処理装置。
(2)(1)に記載の情報処理装置であって、
前記光源部は、前記体の部位に、レーザ光を照射する
情報処理装置。
(3)(1)又は(2)に記載の情報処理装置であって、
前記複数の光検出部は、複数のフォトダイオードである
情報処理装置。
(4)(1)から(3)のうちいずれか1つに記載の情報処理装置であって、
前記判定部は、前記スペックルに関する情報に含まれるスペックルパターンに基づいて、前記ユーザの動きを判定する
情報処理装置。
(5)(4)に記載の情報処理装置であって、
前記判定部は、前記スペックルパターンの時系列変化に基づいて、前記ユーザの動きを判定する
情報処理装置。
(6)(5)に記載の情報処理装置であって、
前記判定部は、前記スペックルパターンの時系列変化の周期性に基づいて、前記ユーザの動きを判定する
情報処理装置。
(7)(1)から(6)のうちいずれか1つに記載の情報処理装置であって、
前記体の部位は、手首であり、
前記判定部は、前記ユーザの手の動きを判定する
情報処理装置。
(8)(7)に記載の情報処理装置であって、
前記判定部は、曲げられた指の種類、曲げられた指の曲がり量、指同士の相互作用、及び指と他の物体との相互作用の少なくとも1つを判定する
情報処理装置。
(9)(1)から(8)のうちいずれか1つに記載の情報処理装置であって、さらに、
前記判定された動きに応じた処理を実行する実行部を具備する
情報処理装置。
(10)(9)に記載の情報処理装置であって、
前記実行部は、前記判定された動きに基づいて、前記ユーザにより入力された操作を識別し、前記識別された操作に応じた処理を実行する
情報処理装置。
(11)(10)に記載の情報処理装置であって、さらに、
過去にユーザが入力した操作に関する履歴情報を記憶する履歴情報記憶部を具備し、
前記実行部は、前記記憶された履歴情報に基づいて、前記ユーザにより入力された操作を識別する
情報処理装置。
(12)(10)又は(11)に記載の情報処理装置であって、さらに、
所定のGUI(Graphical User Interface)を表示可能な表示部を具備し、
前記実行部は、前記判定された動きに基づいて、前記表示された所定のGUIに対して入力された操作を識別する
情報処理装置。
(13)(12)に記載の情報処理装置であって、
前記実行部は、前記判定された動きに基づいて、前記ユーザが選択可能な複数の選択候補を選択し、
前記表示部は、前記選択された複数の選択候補を含む選択画像を表示する
情報処理装置。
(14)(1)から(13)のうちいずれか1つに記載の情報処理装置であって、
前記判定部は、所定の学習アルゴリズムに従って、前記ユーザの動きを判定する
情報処理装置。
(15)(1)から(14)のうちいずれか1つに記載の情報処理装置であって、さらに、
前記ユーザに所定の動きの実行を指示する指示部と、
前記ユーザが前記指示された所定の動きを実行した際の、前記複数の検出信号に含まれる前記スペックルに関する情報を含む判定用情報を記憶する判定用情報記憶部と
を具備し、
前記判定部は、前記記憶された判定用情報に基づいて、前記ユーザの動きを判定する
情報処理装置。
(16)(1)から(15)のうちいずれか1つに記載の情報処理装置であって、さらに、
前記判定部による判定結果が正しいか否かに関する正誤情報を受付ける受付部を具備し、
前記判定部は、前記受付けた前記正誤情報に基づいて、前記ユーザの動きを判定する
情報処理装置。
(17)(1)に記載の情報処理装置であって、
前記検出部は、イメージセンサを含み、
前記複数の光検出部は、前記イメージセンサの複数の画素である
情報処理装置。
(18)ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信する受信部と、
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する判定部と
を具備する情報処理装置。
(19)ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信し、
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する
ことをコンピュータシステムが実行する情報処理方法。
(20)ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信するステップと、
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定するステップと
をコンピュータシステムに実行させるプログラム。
L1…反射光
2…手首
10…本体部
11…装着ベルト
12…コントローラ
19…記憶部
21…光源部
22…PDアレイセンサ
26…PD
30…スペックル信号受信部
31…スペックル信号解析部
32…動き判定部
33…操作識別部
34…処理実行部
35…スペックル信号パターン解析部
36…時系列スペックル信号解析部
40…選択画像
45…指示処理実行部
46…学習データ生成部
100、100'…ウェアラブル装置
Claims (20)
- ユーザの体の部位に光を照射する光源部と、
複数の光検出部を有し、前記体の部位により反射された反射光に基づいて、複数の検出信号を出力する検出部と、
前記複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する判定部と
を具備する情報処理装置。 - 請求項1に記載の情報処理装置であって、
前記光源部は、前記体の部位に、レーザ光を照射する
情報処理装置。 - 請求項1に記載の情報処理装置であって、
前記複数の光検出部は、複数のフォトダイオードである
情報処理装置。 - 請求項1に記載の情報処理装置であって、
前記判定部は、前記スペックルに関する情報に含まれるスペックルパターンに基づいて、前記ユーザの動きを判定する
情報処理装置。 - 請求項4に記載の情報処理装置であって、
前記判定部は、前記スペックルパターンの時系列変化に基づいて、前記ユーザの動きを判定する
情報処理装置。 - 請求項5に記載の情報処理装置であって、
前記判定部は、前記スペックルパターンの時系列変化の周期性に基づいて、前記ユーザの動きを判定する
情報処理装置。 - 請求項1に記載の情報処理装置であって、
前記体の部位は、手首であり、
前記判定部は、前記ユーザの手の動きを判定する
情報処理装置。 - 請求項7に記載の情報処理装置であって、
前記判定部は、曲げられた指の種類、曲げられた指の曲がり量、指同士の相互作用、及び指と他の物体との相互作用の少なくとも1つを判定する
情報処理装置。 - 請求項1に記載の情報処理装置であって、さらに、
前記判定された動きに応じた処理を実行する実行部を具備する
情報処理装置。 - 請求項9に記載の情報処理装置であって、
前記実行部は、前記判定された動きに基づいて、前記ユーザにより入力された操作を識別し、前記識別された操作に応じた処理を実行する
情報処理装置。 - 請求項10に記載の情報処理装置であって、さらに、
過去にユーザが入力した操作に関する履歴情報を記憶する履歴情報記憶部を具備し、
前記実行部は、前記記憶された履歴情報に基づいて、前記ユーザにより入力された操作を識別する
情報処理装置。 - 請求項10に記載の情報処理装置であって、さらに、
所定のGUI(Graphical User Interface)を表示可能な表示部を具備し、
前記実行部は、前記判定された動きに基づいて、前記表示された所定のGUIに対して入力された操作を識別する
情報処理装置。 - 請求項12に記載の情報処理装置であって、
前記実行部は、前記判定された動きに基づいて、前記ユーザが選択可能な複数の選択候補を選択し、
前記表示部は、前記選択された複数の選択候補を含む選択画像を表示する
情報処理装置。 - 請求項1に記載の情報処理装置であって、
前記判定部は、所定の学習アルゴリズムに従って、前記ユーザの動きを判定する
情報処理装置。 - 請求項1に記載の情報処理装置であって、さらに、
前記ユーザに所定の動きの実行を指示する指示部と、
前記ユーザが前記指示された所定の動きを実行した際の、前記複数の検出信号に含まれる前記スペックルに関する情報を含む判定用情報を記憶する判定用情報記憶部と
を具備し、
前記判定部は、前記記憶された判定用情報に基づいて、前記ユーザの動きを判定する
情報処理装置。 - 請求項1に記載の情報処理装置であって、さらに、
前記判定部による判定結果が正しいか否かに関する正誤情報を受付ける受付部を具備し、
前記判定部は、前記受付けた前記正誤情報に基づいて、前記ユーザの動きを判定する
情報処理装置。 - 請求項1に記載の情報処理装置であって、
前記検出部は、イメージセンサを含み、
前記複数の光検出部は、前記イメージセンサの複数の画素である
情報処理装置。 - ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信する受信部と、
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する判定部と
を具備する情報処理装置。 - ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信し、
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定する
ことをコンピュータシステムが実行する情報処理方法。 - ユーザの体の部位への光の照射に応じて、前記ユーザの体の部位により反射された反射光に基づいて出力される複数の検出信号を受信するステップと、
前記受信された複数の検出信号に含まれる、前記体の部位への前記光の照射により発生するスペックルに関する情報に基づいて、前記ユーザの動きを判定するステップと
をコンピュータシステムに実行させるプログラム。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP19768565.4A EP3767433A4 (en) | 2018-03-12 | 2019-01-17 | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROCESS, AND PROGRAM |
| US16/977,873 US11573648B2 (en) | 2018-03-12 | 2019-01-17 | Information processing apparatus and information processing method to identify gesture operation of a user |
| CN201980017235.2A CN111837094B (zh) | 2018-03-12 | 2019-01-17 | 信息处理装置、信息处理方法和程序 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2018-043790 | 2018-03-12 | ||
| JP2018043790 | 2018-03-12 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019176273A1 true WO2019176273A1 (ja) | 2019-09-19 |
Family
ID=67908354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2019/001191 Ceased WO2019176273A1 (ja) | 2018-03-12 | 2019-01-17 | 情報処理装置、情報処理方法、及びプログラム |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US11573648B2 (ja) |
| EP (1) | EP3767433A4 (ja) |
| CN (1) | CN111837094B (ja) |
| WO (1) | WO2019176273A1 (ja) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942040A (zh) * | 2019-11-29 | 2020-03-31 | 四川大学 | 一种基于环境光的手势识别系统和方法 |
| JP2022186188A (ja) * | 2021-06-04 | 2022-12-15 | 日産自動車株式会社 | 監視装置及び監視方法 |
| WO2025187220A1 (ja) * | 2024-03-07 | 2025-09-12 | Cyberdyne株式会社 | 触力覚伝達装置および触力覚伝達方法 |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12229338B2 (en) | 2022-03-15 | 2025-02-18 | Doublepoint Technologies Oy | Detecting user input from multi-modal hand bio-metrics |
| US11635823B1 (en) * | 2022-03-15 | 2023-04-25 | Port 6 Oy | Detecting user input from multi-modal hand bio-metrics |
| CN114722968A (zh) * | 2022-04-29 | 2022-07-08 | 中国科学院深圳先进技术研究院 | 一种识别肢体运动意图的方法及电子设备 |
| WO2023206450A1 (zh) * | 2022-04-29 | 2023-11-02 | 中国科学院深圳先进技术研究院 | 一种识别肢体运动意图的方法和电子设备 |
| DE102023200505A1 (de) * | 2023-01-24 | 2024-07-25 | Robert Bosch Gesellschaft mit beschränkter Haftung | Sensoranordnung |
| CN116665298A (zh) * | 2023-05-18 | 2023-08-29 | 中兴通讯股份有限公司 | 手势识别方法、装置、设备及存储介质 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011186693A (ja) * | 2010-03-08 | 2011-09-22 | Brother Industries Ltd | 情報入力装置 |
| JP2015041052A (ja) | 2013-08-23 | 2015-03-02 | ソニー株式会社 | リストバンド型情報処理装置および記憶媒体 |
| JP2016150081A (ja) * | 2015-02-17 | 2016-08-22 | ソニー株式会社 | 光学ユニット、測定システムおよび測定方法 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4988016B2 (ja) * | 2009-08-27 | 2012-08-01 | 韓國電子通信研究院 | 指の動き検出装置およびその方法 |
| WO2013135299A1 (en) * | 2012-03-15 | 2013-09-19 | Cherradi El Fadili Ibrahim Farid | Extending the free fingers typing technology and introducing the finger taps language technology |
| EP2879568A1 (en) * | 2012-08-01 | 2015-06-10 | Bar Ilan University | Method and system for non-invasively monitoring biological or biochemical parameters of individual |
| CN105027030B (zh) | 2012-11-01 | 2018-10-23 | 艾卡姆有限公司 | 用于三维成像、映射、建网和界面连接的无线腕式计算和控制设备和方法 |
| JP6075122B2 (ja) * | 2013-03-05 | 2017-02-08 | 株式会社リコー | システム、画像投影装置、情報処理装置、情報処理方法およびプログラム |
| US9208566B2 (en) | 2013-08-09 | 2015-12-08 | Microsoft Technology Licensing, Llc | Speckle sensing for motion tracking |
| US9743860B2 (en) * | 2013-11-08 | 2017-08-29 | Applied Invention, Llc | Use of light transmission through tissue to sense joint flexure |
| WO2015128226A1 (en) * | 2014-02-26 | 2015-09-03 | Koninklijke Philips N.V. | Device for measuring a cycling cadence |
| US20160209929A1 (en) * | 2015-01-20 | 2016-07-21 | Jahja I. Trisnadi | Method and system for three-dimensional motion-tracking |
| CN106020448B (zh) * | 2016-05-06 | 2019-03-29 | 深圳市国华识别科技开发有限公司 | 基于智能终端的人机交互方法和系统 |
| US10152798B2 (en) * | 2017-04-10 | 2018-12-11 | Wisconsin Alumni Research Foundation | Systems, methods and, media for determining object motion in three dimensions using speckle images |
-
2019
- 2019-01-17 EP EP19768565.4A patent/EP3767433A4/en not_active Withdrawn
- 2019-01-17 US US16/977,873 patent/US11573648B2/en active Active
- 2019-01-17 WO PCT/JP2019/001191 patent/WO2019176273A1/ja not_active Ceased
- 2019-01-17 CN CN201980017235.2A patent/CN111837094B/zh active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011186693A (ja) * | 2010-03-08 | 2011-09-22 | Brother Industries Ltd | 情報入力装置 |
| JP2015041052A (ja) | 2013-08-23 | 2015-03-02 | ソニー株式会社 | リストバンド型情報処理装置および記憶媒体 |
| JP2016150081A (ja) * | 2015-02-17 | 2016-08-22 | ソニー株式会社 | 光学ユニット、測定システムおよび測定方法 |
Non-Patent Citations (2)
| Title |
|---|
| FUKUI, RUI ET AL.: "Hand shape classification with a wrist contour sensor: :Development of a Prototype Device", PROCEEDINGS OF THE 29TH ANNUAL CONF. OF THE ROBOTICS SOCIETY OF JAPAN, 7 September 2011 (2011-09-07), pages 311 - 314, XP055428887 * |
| See also references of EP3767433A4 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942040A (zh) * | 2019-11-29 | 2020-03-31 | 四川大学 | 一种基于环境光的手势识别系统和方法 |
| JP2022186188A (ja) * | 2021-06-04 | 2022-12-15 | 日産自動車株式会社 | 監視装置及び監視方法 |
| JP7753682B2 (ja) | 2021-06-04 | 2025-10-15 | 日産自動車株式会社 | 監視装置及び監視方法 |
| WO2025187220A1 (ja) * | 2024-03-07 | 2025-09-12 | Cyberdyne株式会社 | 触力覚伝達装置および触力覚伝達方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| US11573648B2 (en) | 2023-02-07 |
| CN111837094A (zh) | 2020-10-27 |
| US20210311564A1 (en) | 2021-10-07 |
| CN111837094B (zh) | 2025-01-14 |
| EP3767433A4 (en) | 2021-07-28 |
| EP3767433A1 (en) | 2021-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111837094B (zh) | 信息处理装置、信息处理方法和程序 | |
| US11294475B1 (en) | Artificial reality multi-modal input switching model | |
| US20250130700A1 (en) | Virtual interactions for machine control | |
| KR101904889B1 (ko) | 표시 장치와 이를 이용한 입력 처리 방법 및 시스템 | |
| US9395821B2 (en) | Systems and techniques for user interface control | |
| US7843425B2 (en) | Motion recognition system and method for controlling electronic devices | |
| US10015402B2 (en) | Electronic apparatus | |
| US20160378193A1 (en) | Wearable Device with Gesture Recognition Mechanism | |
| US20150177836A1 (en) | Wearable information input device, information input system, and information input method | |
| WO2016038953A1 (ja) | 検出装置、検出方法、制御装置、および制御方法 | |
| CN106062666A (zh) | 使用光学传感器检测到的运动手势输入 | |
| US20250341893A1 (en) | Human interface system | |
| US20170277428A1 (en) | Information processing device, information processing method, and non-transitory computer readable memory medium | |
| US20170357336A1 (en) | Remote computer mouse by camera and laser pointer | |
| JP6519074B2 (ja) | 電子機器 | |
| WO2024085997A1 (en) | Triggering actions based on detected motions on an artificial reality device | |
| TW201243333A (en) | Operation controlling system | |
| US11054941B2 (en) | Information processing system, information processing method, and program for correcting operation direction and operation amount | |
| Ruser et al. | Evaluating the accuracy and user experience of a gesture-based infrared remote control in smart homes | |
| JPH11345073A (ja) | 携帯情報端末操作システム | |
| US12105926B2 (en) | XR manipulation feature with smart watch | |
| US20240220097A1 (en) | Virtual mouse with tactile feedback provided via keyboard keys | |
| Arun et al. | Gesture Control for Enhanced Accessibility | |
| Ravindran | Techniques for subtle mid-air gestural interaction using mmWave radar | |
| JP2025087611A (ja) | ピンチ状態検出システム及び方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19768565 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2019768565 Country of ref document: EP Effective date: 20201012 |
|
| NENP | Non-entry into the national phase |
Ref country code: JP |
|
| WWG | Wipo information: grant in national office |
Ref document number: 201980017235.2 Country of ref document: CN |
|
| WWW | Wipo information: withdrawn in national office |
Ref document number: 2019768565 Country of ref document: EP |