WO2019069875A1 - 移動体用画像生成記録表示装置及びプログラム - Google Patents
移動体用画像生成記録表示装置及びプログラム Download PDFInfo
- Publication number
- WO2019069875A1 WO2019069875A1 PCT/JP2018/036758 JP2018036758W WO2019069875A1 WO 2019069875 A1 WO2019069875 A1 WO 2019069875A1 JP 2018036758 W JP2018036758 W JP 2018036758W WO 2019069875 A1 WO2019069875 A1 WO 2019069875A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- virtual
- mobile
- moving body
- virtual space
- objects
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—Three-dimensional [3D] image rendering
- G06T15/50—Lighting effects
- G06T15/503—Blending, e.g. for anti-aliasing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—Three-dimensional [3D] image rendering
- G06T15/10—Geometric effects
- G06T15/20—Perspective computation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics
- G06T19/003—Navigation within 3D models or images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—Three-dimensional [3D] animation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—Three-dimensional [3D] image rendering
- G06T15/08—Volume rendering
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/24—Indexing scheme for image data processing or generation, in general involving graphical user interfaces [GUIs]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/61—Scene description
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/62—Semi-transparency
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2215/00—Indexing scheme for image rendering
- G06T2215/16—Using real world measurements to influence rendering
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Definitions
- the present invention relates to an apparatus for generating, recording or displaying an image of an object around a moving object, and a program thereof.
- An image conversion technology that processes an image captured using a camera installed on a mobile object such as a car and converts the mobile object into an image similar to that seen from various directions.
- a so-called “around view monitor” (registered trademark) that synthesizes images taken using a plurality of cameras mounted on a mobile body, and generates an image of a region around the mobile body like a bird's-eye view.
- Such image synthesis technology displays other moving objects, objects, etc. in positions that are difficult to see from the driver's seat of moving objects on a monitor and shows them to the driver, for example, when driving in back or driving in parallel parking. It is used at the time of the day.
- the image synthesis technology as described above converts an actual captured image and displays it on a display device in a car. For this reason, when an object being photographed is temporarily blocked by another moving object or enters a blind spot of a camera, the object may not be displayed.
- An apparatus comprising an input device, a virtual model database, a virtual model conversion device, a virtual model reconfiguration device, a virtual model processing device, and a control device or a display device
- the virtual model conversion device comprising It recognizes information on a plurality of objects acquired from the device, identifies a corresponding virtual model from a virtual model database, and replaces it.
- the virtual model reconstruction device reconstructs objects and their relationships into corresponding virtual models and their relationships in virtual space.
- the virtual model processing apparatus understands and determines the virtual model and the relationship between them based on the reconstructed virtual model and the relationship between them, and there is a technology for instructing the control device or the display device (for example, Patent Document 1) reference).
- the viewpoint can be moved and the state from the freely moved viewpoint can be displayed.
- the operation lever is displayed on a part of the display screen, and the operation lever is operated in the desired direction of up, down, left, and right You can move the viewpoint.
- the viewpoint conversion image generation means synthesizes a vehicle model image drawn to imitate a vehicle in a portion corresponding to the vehicle in the viewpoint conversion image (see, for example, Patent Document 4).
- An object of the present invention is to enable recording with less storage capacity even when recording the running condition of the body.
- the disclosed technology includes a traveling state acquisition unit for acquiring information on traveling state of the mobile unit including the position and velocity of the mobile unit, and other mobile units and traveling paths existing around the mobile unit of the mobile unit.
- An object information acquisition unit for acquiring information on a plurality of objects including a shape, and information obtained from the traveling state acquisition unit and the object information acquisition unit, at least for each of the mobile object and the plurality of objects
- a virtual space is associated with the virtual model and arranged in a three-dimensional space, so that a virtual space constructing unit for constructing the virtual space and a two-dimensional image obtained by imaging the virtual space from a virtual camera arranged in the virtual space
- a two-dimensional image generation unit for generating an image and outputting the image on a display screen, wherein the two-dimensional image generation unit is configured to perform two-dimensional projection according to a relative velocity with the mobile object.
- FIG. 1 is a diagram showing an example of sensors installed in a virtual space and a real moving object in one embodiment.
- the virtual space 150 shown in FIG. 1 (A) is the image information of the peripheral object from the camera (101a to 101d) installed on the real moving object 100R shown in FIG. 1 (B), the periphery by the radar 103 Information such as relative velocity and position of objects, GPS information received by wireless antenna 105 and various information from other systems connected to wireless network, speedometer installed in real mobile 100R, accelerometer , And is constructed based on the information etc. of the mobile unit 100R obtained from sensors (not shown) such as a gyro.
- the above-described cameras (101a to 101d), the radar 103, the wireless antenna 105, and sensors (not shown) such as a speedometer are merely examples, and any other appropriate information collection device may be used. Further, the device for collecting information may be installed either inside or outside the vehicle 100R.
- the virtual camera 130 is positioned such that the virtual moving body 100 corresponding to the actual moving body 100R shown in FIG. 1B is positioned approximately at the center of the imaging direction of the virtual camera 130. It is desirable that it is set.
- the virtual camera 130 can set various parameters used when converting the virtual space 150 into a two-dimensional image by the virtual imaging system of the virtual camera 130.
- the parameters of the virtual camera 130 are, for example, the position of the virtual camera 130 in the virtual space, the imaging direction, the focal length, the angle of view, and the like.
- the depth of field is a parameter indicating the depth at which the virtual lens system is in focus, but in the case of this embodiment, the depth of field is pan-focused (ie, any distance from the virtual camera 130). It is desirable that the settings be made to focus on existing virtual objects.
- FIG. 1A other moving objects and stationary objects in the real space traveling around the actual moving object 100R are recognized from the above-mentioned information.
- the 3D model database is referred to according to the embodiment of the present invention, and they are respectively arranged in the virtual space 150 in association with the virtual model.
- a truck 110, an automobile 112, a bus 114, and a pole 120 on the roadside are arranged around the virtual mobile 100 in the virtual space corresponding to the real mobile 100R.
- These virtual models existing in the virtual space 150 correspond to each of the objects existing in the real space with respect to the virtual moving body 100, and relative motions between them and the real moving body 100R. And always move relatively within the virtual space 150.
- the virtual imaging system of the virtual camera 130 moves in the same direction as the virtual moving body 100 so that the virtual moving body 100 is always placed at the center of the screen, and the virtual imaging system performs virtual movement It is desirable that the virtual mobile unit 100 be followed so that the body 100 is placed at the center of the screen.
- the relative distance between the virtual camera 130 and the virtual mobile unit 100 and the parameters of the imaging system of the virtual camera can be freely set by the instruction of the operator (driver) on board the real mobile unit 100R. Is desirable.
- a display device be installed in the vicinity of the driver's seat so that the operator (driver) or the like of the actual mobile unit 100R can view the image captured by the virtual camera 130.
- a recognized two-wheeled vehicle, a person, etc. can also be put on virtual space. Therefore, in the present embodiment, for real objects that need to be recognized in the driving of the driver, it is desirable to secure the comprehensiveness of the recognizable objects so that they can be arranged in the virtual space.
- an oncoming vehicle with respect to the actual moving body 100R in the virtual space is not illustrated in FIG. 1A, it is desirable to recognize an oncoming vehicle as well.
- FIG. 2 is a functional block diagram of one embodiment.
- the moving body measuring unit 210 receives information from sensors (not shown) such as a speedometer, an accelerometer, and a gyro installed in the actual moving body 100R.
- the information on the actual mobile unit 100R obtained by the mobile unit measurement unit 210 is sent to the virtual space construction unit 250.
- the peripheral object measurement unit 220 is an image information of other moving objects and objects in the periphery from cameras (101a to 101d) installed on the real moving object 100R, and relative velocities of other moving objects and objects in the vicinity by the radar 103. And information such as position, GPS information received by the wireless antenna 105, and various information from other systems connected to the wireless network (road information, video from a camera installed on the road, etc.). The information received by the peripheral object measurement unit 220 is sent to the virtual space construction unit 250 and the object recognition unit 230.
- the object recognition unit 230 recognizes other moving objects existing on the periphery and an object such as a pole on the road based on the information received by the peripheral object measurement unit 220, and recognizes the recognition result as a virtual space construction unit 250. Send to
- the virtual space construction unit 250 acquires the shape of the road from the car navigation database 270 and forms a model of the road in the virtual space 150. Also, based on the information from the moving body measuring unit 210, the virtual space constructing unit 250 positions the virtual moving body 100 corresponding to the actual moving body 100R on the above virtual road formed in the virtual space 150. The virtual road travels at a speed corresponding to the real mobile unit 100R.
- the three-dimensional shape of the virtual mobile object 100 may be stored in the virtual space construction unit 250 or may be acquired from the 3D model database 240.
- the virtual space construction unit 250 acquires virtual models corresponding to other moving objects and objects in the vicinity from the 3D model database.
- the virtual space construction unit 250 places virtual models corresponding to other obtained moving objects and objects in the vicinity in the virtual space.
- the virtual space construction unit 250 causes each of the virtual models to travel on a virtual road based on the information of the peripheral object measurement unit 220 on virtual models corresponding to other moving objects and objects in the vicinity.
- the virtual space construction unit 250 sends information of the virtual space to the rendering unit 260 and the recorder unit 280.
- the rendering unit 260 sets parameters of the virtual camera 130 based on virtual camera instruction information instructed by the operator (driver), and sends information obtained by imaging the virtual space 150 to the rendering unit 260.
- the rendering unit 260 generates a two-dimensional image obtained by imaging the virtual space 150 from the virtual camera 130.
- the generated two-dimensional video is sent to the display device.
- the rendering unit displays or captures residual images of surrounding mobiles so that the relative velocity can be easily identified with respect to other mobiles moving relative to the virtual mobile 100.
- the image of the past may be displayed superimposed on a two-dimensional image by increasing the degree of transparency as the image of the past is increased by a predetermined time of the moving object.
- a trajectory may be added to the surrounding moving objects so that the moving conditions of the surrounding moving objects can be known.
- past residual images or images of other moving objects in the past may be determined in advance, or may be appropriately changed based on an instruction of the operator (driver).
- the velocity of the mobile object, the mobile object traveling oppositely, the absolute value of the relative velocity to the mobile object or the absolute value of the relative velocity change is smaller than a predetermined value, and the velocity is higher than that of the mobile object.
- slow moving objects, or stationary objects, etc. do not display afterimage, past images, etc., or after images, past images, etc. of some moving objects or objects of these moving objects.
- the display effect can be made different depending on the type or nature of the moving object or object, or not.
- the recorder unit 280 stores information of the virtual space, which changes from moment to moment, in the memory 704 or the storage medium 760. Since the information stored in the recorder unit is information of the virtual space 150, more compressed information can be recorded than a drive recorder which records a real traveling image. Therefore, the storage capacity to be consumed can be reduced. Also, by moving the virtual camera, it is possible to change the viewpoint and display the virtual space as a two-dimensional image on the display by moving the virtual camera. .
- FIG. 3 is a diagram showing an example of a first display image in one embodiment.
- the image in FIG. 3 is an image obtained by imaging the virtual space 150 by the virtual camera 130.
- a virtual mobile unit 100 at the current time, a peripheral mobile unit 310 at the current time, and a pole 330 present on the road shoulder at the current time are displayed.
- an afterimage 312, an afterimage 314 and an afterimage 316 are images of afterimages of the peripheral moving body 310.
- the afterimage 312 may be an afterimage of the peripheral moving object 310 past the current time by a time d. Then, the afterimage 312 may be an image in which the transparency is increased by ⁇ % compared to the peripheral moving body 310. Therefore, the afterimage 312 is an image in which the transparency is increased by ⁇ % compared to the peripheral moving body 310, and may be an image that is always a time d past the peripheral moving body 310. In this case, if the relative image velocity of the afterimage 312 is faster than that of the virtual mobile object 100, it will appear as following the peripheral mobile object 310.
- “transparency” means 100% transparency means complete transparency, and 0% transparency means completely opaque.
- the afterimage 312 may be an instantaneous image of the peripheral moving object 310 past the given time by a predetermined time, and an image in which the transparency is increased by ⁇ %. That is, the peripheral moving body 310 may leave an afterimage at a predetermined interval time d.
- the peripheral mobile object 310 is a still image of the peripheral mobile object 100 at a predetermined interval d, and is still with the transparency increased by ⁇ %. It looks like you are moving while leaving the picture.
- the afterimage 314 is a past image by a time d more than the afterimage 312 and is an image in which the transparency is further increased by ⁇ %
- the afterimage 316 is a past image by a time d more than the afterimage 314, Furthermore, it may be an image in which the transparency is increased by ⁇ %.
- the value for increasing the transparency may be different for each residual image.
- the interval d of the afterimage may be different for each afterimage. Note that how many afterimages are left may be determined in advance. Alternatively, when the transparency becomes 100% or more when the transparency is increased, the afterimage may be erased and excluded from the drawing target.
- the virtual camera 130 is moved as being stationary in the image as an example, but the virtual mobile object 100 is moved May generate an image.
- the virtual mobile body 310 is not limited to a four-wheeled vehicle, and may be a two-wheeled vehicle, a bicycle or the like.
- FIG. 4 is a view showing a modification of the first display image in the embodiment.
- the blur image 360 in FIG. 4 represents the behavior of the peripheral moving body 310 by adding the blurring effect to the afterimage 312, the afterimage 314, the afterimage 316, and the like. It goes without saying that the blur image can be expressed by various processes other than the above-described process. By displaying such an effect, it is possible to provide an operator (driver) with a more easily understandable image.
- FIG. 5 is a diagram showing an example of a second display image in one embodiment.
- FIG. 5 shows an example in the case where the speed of the peripheral moving body 410 is slower than that of the virtual moving body 100.
- the peripheral moving object 410 at the current time is displayed, and the residual image 412, the residual image 414, and the residual image 416 are displayed in front of the peripheral moving object 410 as going back to the past. If the speed of the peripheral moving body 410 is slower than that of the virtual moving body 100 as in this track, the afterimage 412, the afterimage 414 and the afterimage 416 may not be displayed.
- the shape of the track may be difficult to recognize for humans. . Therefore, in such a situation, it may be possible for a human to clearly recognize the shape of the track rather than the situation of movement of the track (peripheral moving body 410) by not displaying the afterimage.
- the absolute value of the relative velocity between the peripheral moving body 410 and the virtual moving body 100 is smaller than a predetermined value, the overlap of the afterimage becomes strong, and it may be difficult for a human to recognize the shape of the track.
- FIG. 6 is a first flowchart of the display of the afterimage of the surrounding moving object in one embodiment. Each step will be described below.
- Step S500 The processing flow of this embodiment is started by interruption at a predetermined interval. Note that the trigger for starting the process is not limited to the interrupt.
- the processing proceeds to step S510.
- Step 510 repeats the processing of each step existing between step S526 and all surrounding objects.
- Step S512 For example, it is determined whether an object recognized by pattern recognition is new based on an image from a camera mounted on a real mobile unit 100R. If it is new ("Yes"), the process proceeds to step S514. If already recognized and not new (“No"), the process proceeds to step S516.
- Step S514 Determine a new object and specify a corresponding virtual model. If the object to be recognized is a new one, pattern recognition, machine learning techniques, etc. are used to determine what kind of vehicle it is or what kind of object it is, and the corresponding model Is identified.
- pattern recognition for example, in the case of a moving object, a vehicle type that most matches the feature is identified based on features such as the position of the headlights and various designs of the vehicle body.
- the 3D model of the identified vehicle type is searched and acquired from the 3D model database 240. Features are also extracted for the pole 330 on the stationary road, object recognition is performed, and 3D model search and acquisition are performed. The acquired 3D model is used in constructing a virtual space and in rendering.
- the process proceeds to step S516.
- Step S516 Determine an object and specify a virtual model.
- the virtual model is placed at an appropriate position in the virtual space 150 based on the positions of the recognized one or more objects.
- step S518 The virtual space is recorded in the recorder.
- the operator driver or the like instructs to record the virtual space
- the virtual space at that time is stored in the memory 704 or the storage medium 760.
- step S520 the process proceeds to step S520.
- Step S520 The position of the mobile object model in the vicinity by time d before the current time is specified. In this case, it is desirable that the position relative to the virtual mobile unit 100 be maintained, and the positional relationship with the pole 330 on the stationary road or the roadside may be shifted. By doing this, the operator (driver) can grasp the past positional relationship between his virtual mobile unit 100 and other mobile units in the vicinity. Next, the process proceeds to step S522.
- Step S522 The position of the mobile object model in the vicinity by time 2d before the current time is specified.
- the other processes are the same as step S520.
- the process proceeds to step S524.
- Step S524 The position of the model of the mobile object in the vicinity, which is 3 d before the current time, is specified.
- the other processes are the same as step S520.
- the process of the embodiment is not limited to FIG. Next, the process proceeds to step S526.
- Step S526 If there is another unprocessed object, the process returns to step S510. If there is no other unprocessed object, the process proceeds to step S528.
- Step S528 In the virtual space 150, the two-dimensional image captured by the virtual camera 130 is rendered. Note that for a model past by time d, the transparency is increased by ⁇ % over the peripheral moving object at the current time, and for a model past by time 2d, the transparency is increased by 2 ⁇ %, and the model past by 3d For example, rendering may be performed with the transparency increased by 3 ⁇ % to obtain the image shown in FIG. Although an example in which a past model is generated at a constant interval d has been shown, the interval may not be constant. Further, with regard to the transparency, the transparency of each past model may be individually changed in consideration of the characteristics of the display device and the like, instead of increasing the transparency at a predetermined rate.
- the peripheral mobile object 312 at a time past the present by the time d is made transparent by ⁇ % so as to follow the current image of the peripheral mobile object 310. It will be displayed increased.
- the past peripheral moving object 314 and the past peripheral moving object 316 are also as described above, and thus the description thereof is omitted.
- an image is generated so that the peripheral moving objects (312, 314, 316) at a plurality of past times move smoothly following the peripheral moving object 310.
- peripheral moving objects (312, 314, 316) at a plurality of past times may be displayed in a blurred state.
- the past afterimage shown in FIG. 7 may be displayed in a blurred manner. Note that the expression of blur is not limited to these methods.
- FIG. 7 is a second flowchart of the display of the afterimage of the surrounding mobile unit in one embodiment. Each step will be described below.
- Step S600 The processing flow of the present embodiment is started by interruption at a predetermined interval. Note that the trigger for starting the process is not limited to the interrupt.
- the processing proceeds to step S610.
- Step S610 Step 610 repeats the processing of each step existing between step S626 and all surrounding objects.
- Step S612 For example, it is determined whether an object recognized by pattern recognition is new based on an image from a camera mounted on a real mobile unit 100R. If it is new ("Yes"), the process proceeds to step S614. If already recognized and not new, the process proceeds to step S616.
- Step S614 A new object is determined, and a corresponding virtual model is identified. If the object to be recognized is new, pattern recognition technology is used to determine what kind of vehicle or what kind of object it is and to identify the corresponding model . In pattern recognition, for example, in the case of a moving object, a vehicle type that most matches the feature is identified based on features such as the position of the headlights and various designs of the vehicle body. Based on the identified vehicle type, the 3D model of the identified vehicle type is retrieved and acquired from the 3D model database. Features are also extracted for the pole 330 on the stationary road, object recognition is performed, and 3D model search and acquisition are performed. The acquired 3D model is used in constructing a virtual space and in rendering. Next, the process proceeds to step S616.
- Step S616 Determine an object and specify a virtual model.
- the model is placed at an appropriate position in the virtual space 150 based on the positions of the recognized one or more objects.
- the process proceeds to step S618.
- Step S618 The recorder records a virtual space. When it is instructed by the operator to record a virtual space, the virtual space at that time is stored in the memory 704 or the storage medium 760. Next, the process proceeds to step S620.
- Step S620 It is checked whether the time d1 of the interval has elapsed. If the interval time d1 has elapsed ("Yes"), the interval measurement is reset to zero, and the process proceeds to step S622. If the interval time d1 has not elapsed ("No"), the process proceeds to step S624.
- Step S 622 For the mobile objects in the vicinity, the drawing of the model at the current time is left as an afterimage. The process proceeds to step S622. By this step, a plurality of residual images are sequentially generated for each interval time d1.
- Step S624 The transparency of each of the plurality of afterimages is increased by ⁇ %. You may exclude the afterimage which transparency became 100% or more from drawing object. It is desirable that the afterimage maintain the positional relationship with the virtual mobile body 100. Incidentally, even if the transparency does not reach 100% or more, the residual image in the past for a predetermined time may be excluded from the objects to be drawn. Note that rendering can be performed collectively in step S 628. The process proceeds to step S626.
- Step S626 If there is another unprocessed object, the process returns to step S610. If there is no other unprocessed object, the process proceeds to step S 628.
- Step S628 In the virtual space 150, the two-dimensional image captured by the virtual camera 130 is rendered.
- the transparency is increased by ⁇ % for the residual image in the past by time d1
- the transparency is increased by 2 ⁇ % for the residual image in time 2d
- the transparency is increased by 3 ⁇ % for the residual image in time 3d
- the rendering can be done to obtain the image shown in FIG.
- generates a residual image for every fixed interval d1 was shown, an interval does not need to be fixed.
- the transparency of each past model may be individually changed in consideration of the characteristics of the display device and the like, instead of increasing the transparency at a predetermined rate.
- the transparency of the peripheral moving object 310 is further increased by ⁇ % in order by a time d1 so as to leave a plurality of residual images, as shown in FIG. It will be displayed.
- residual images (312, 314, 316) of the peripheral mobile object 312 are generated at every interval time d1.
- FIG. 8 is a diagram illustrating a hardware configuration 700 of an embodiment.
- the hardware configuration 700 includes a CPU 702, a memory 704, a communication control device 706, an input interface 708, a display control unit 710, an external memory control unit 712, and an output interface 714.
- the communication control device 706 is connected to a network such as the Internet or CAN 731 (controller area network).
- a touch sensor 740, a GPS 742, a camera 744 and the like are connected to the input interface 708.
- a display 750 is connected to the display control unit 710.
- the external memory control unit 712 can read and write the storage medium 760.
- a speaker 770 or the like is connected to the output interface.
- the storage medium 760 may be a RAM, a ROM, a CD-ROM, a DVD-ROM, a hard disk, a memory card, or the like.
- the program of the embodiment described above can be executed by a computer provided with the hardware configuration 700. Also, the program of the embodiment may be implemented as a method to be executed by a computer. A part or all of the program of this embodiment may be executed by the operating system. Also, part of the program may be realized by hardware.
- the program may be stored on storage medium 760 or memory 704. In the above-described embodiment, the steps of the program may be performed simultaneously or in different order as long as no contradiction arises.
- the above embodiments can be implemented as hardware devices. It goes without saying that the above embodiments do not limit the invention described in the claims, and are treated as examples.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Signal Processing (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computing Systems (AREA)
- Geometry (AREA)
- Processing Or Creating Images (AREA)
- Traffic Control Systems (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
- Image Generation (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
Description
以下に、従来の技術について説明する。
なお、仮想空間に現実の移動体100Rに対する対向車については、図1(A)に描かれていないが、対向車についても認識対象とすることが望ましい。
また、仮想空間構築部250は、仮想空間の情報をレンダリング部260及びレコーダ部280に送る。
なお、自己の移動体、対向して走行する移動体、自己の移動体との相対速度の絶対値あるいは相対速度変化の絶対値が所定の値より小さい移動体、自己の移動体よりも速度が遅い移動体、又は静止しているオブジェクト等については、残像、過去の映像等を表示させないようにしたり、或いはこれらの移動体のうちの一部の移動体又はオブジェクトについて残像、過去の映像等を表示させないようにしたり、移動体又はオブジェクトの種類或いは性質に応じて、表示の効果を異ならせるようにしたりすることができる。
図2において、残像312、残像314及び残像316は、周辺移動体310の残像の画像である。
なお、静止している路肩のポール330は、残像を残さないように表示させることが望ましい。
図4は、一実施形態における第1の表示画像の変形例を示す図である。
このように、仮想移動体100に対する周辺移動体410の相対速度が特定の条件を満たす場合に、周辺移動体100の表示に与える効果を変化させるようにしてもよい。
インターバル時間d及び透明度Δ%については、図3と同様であるので、説明を省略する。
図6は、一実施形態における周囲の移動体の残像の表示の第1のフローチャートである。以下に各ステップについて、説明する。
[ステップS510]ステップ510は、ステップS526との間に存在する各ステップの処理を、周辺のオブジェクト全てについて繰り返す。
[ステップS518]レコーダにおいて仮想空間を記録する。オペレータ(ドライバ)等により、仮想空間を記録することが指示されている場合には、その時刻における仮想空間をメモリ704又は記憶媒体760に記憶する。次にステップS520に進む。
なお、図4のように、ブレを表示させるためには、過去の複数の時点における周辺移動体(312、314、316)をぼかして表示させるようにしてもよい。あるいは、図7に示す過去の残像をぼかして表示するようにしてもよい。なお、ブレの表現については、これらの手法に限定されるものではない。
[ステップS600] 本実施形態の処理フローは、所定のインターバルで割り込みにより開始される。なお、処理の開始の契機は、割り込みに限定されるものではない。処理はステップS610に進む。
[ステップS610]ステップ610は、ステップS626との間に存在する各ステップの処理を、周辺のオブジェクト全てについて繰り返す。
図7の処理を用いることにより、周辺移動体312の残像(312、314、316)が、インターバル時間d1毎に生成される。
図8は、一実施形態のハードウエア構成700を示す図である。
記憶媒体760は、RAM、ROM、CD-ROM、DVD-ROM、ハードディスク、メモリーカード等であってもよい。
なお,上述の実施形態において,プログラムのステップは、矛盾のない限り,同時に,又は順序を入れ替えて実行されてもよい。
以上の実施形態は,ハードウエアの装置としてインプリメントされ得る。 以上の実施形態は,請求項に記載された発明を限定するものではなく,例示として取り扱われることは言うまでもない。
220 周辺オブジェクト計測部
230 オブジェクト認識部
240 3Dモデルデータベース
250 仮想空間構築部
260 レンダリング部
270 カーナビゲーションデータベース
280 レコーダ部
Claims (7)
- 自己の移動体の位置及び速度を含む自己の移動体の走行状態に関する情報を取得する走行状態取得部と、
自己の移動体の周辺に存在する他の移動体及び走行路の形状を含む複数のオブジェクトに関する情報を取得するオブジェクト情報取得部と、
前記走行状態取得部及び前記オブジェクト情報取得部から得られた情報から、少なくとも、前記自己の移動体及び前記複数のオブジェクトの各々に対して仮想モデルを対応付けて三次元空間の中に配置することで、仮想空間を構築する仮想空間構築部と、
前記仮想空間に配置された仮想的なカメラから前記仮想空間を撮像した二次元映像を生成し表示画面に出力する二次元映像生成部と、
を有し、
前記二次元映像生成部は、前記自己の移動体との相対的な速度に応じて、二次元映像における前記複数のオブジェクトの各々に対応する仮想モデルの表示に所定の効果を加えて前記二次元映像を生成する、
移動体位置情報認識表示装置。 - 前記効果は、離散的に表示される残像であって、時間の経過と共に透明度が増加する残像である、請求項1に記載の移動体位置情報認識表示装置。
- 前記残像は、現在の時刻よりも所定時間だけ前の時刻のモデルの映像であって、前記所定の時間が大きいほど、モデルの映像の透明度が増加している、請求項2に記載の移動体位置情報認識表示装置。
- 前記効果は、軌跡である、請求項1に記載の移動体位置情報認識表示装置。
- 前記自己の移動体に対向して走行するオブジェクト、前記自己の移動体との相対速度の絶対値あるいは相対速度変化の絶対値が所定の値より小さいオブジェクト、前記自己の移動体よりも速度が遅いオブジェクト、又は静止しているオブジェクトに対応するモデルには、前記効果を加えない、請求項1ないし4のうちいずれか1項記載の移動体位置情報認識表示装置。
- 前記仮想空間又は前記二次元映像を記録する記録部、
を更に有する請求項1ないし5のうちいずれか1項記載の移動体位置情報認識表示装置。 - 自己の移動体の位置及び速度を含む自己の移動体の走行状態に関する情報を取得する走行状態取得ステップと、
自己の移動体の周辺に存在する他の移動体及び走行路の形状を含む複数のオブジェクトに関する情報を取得するオブジェクト情報取得ステップと、
前記走行状態取得ステップ及び前記オブジェクト情報取得ステップから得られた情報から、少なくとも、前記自己の移動体及び前記複数のオブジェクトの各々に対して仮想モデルを対応付けて三次元空間の中に配置することで、仮想空間を構築する仮想空間構築ステップと、
前記仮想空間に配置された仮想的なカメラから前記仮想空間を撮像した二次元映像を生成し表示画面に出力する二次元映像生成ステップと、
をコンピュータに実行させるプログラムであって、
前記二次元映像生成ステップは、前記自己の移動体との相対的な速度に応じて、二次元映像における前記複数のオブジェクトの各々に対応する仮想モデルの表示に所定の効果を加えて前記二次元映像を生成する、
移動体位置情報認識表示プログラム。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP18864949.5A EP3693930A4 (en) | 2017-10-02 | 2018-10-01 | IMAGE GENERATION / RECORDING / DISPLAY DEVICE FOR MOVING BODIES AND PROGRAM |
| KR1020207012744A KR102349915B1 (ko) | 2017-10-02 | 2018-10-01 | 이동체용 이미지 생성 기록 표시 장치 및 프로그램 |
| CN201880064353.4A CN111164652B (zh) | 2017-10-02 | 2018-10-01 | 移动体图像生成记录显示装置和程序产品 |
| US16/837,981 US10896542B2 (en) | 2017-10-02 | 2020-04-01 | Moving body image generation recording display device and program product |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2017-192431 | 2017-10-02 | ||
| JP2017192431A JP6543313B2 (ja) | 2017-10-02 | 2017-10-02 | 移動体用画像生成記録表示装置及びプログラム |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US16/837,981 Continuation US10896542B2 (en) | 2017-10-02 | 2020-04-01 | Moving body image generation recording display device and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019069875A1 true WO2019069875A1 (ja) | 2019-04-11 |
Family
ID=65995397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2018/036758 Ceased WO2019069875A1 (ja) | 2017-10-02 | 2018-10-01 | 移動体用画像生成記録表示装置及びプログラム |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US10896542B2 (ja) |
| EP (1) | EP3693930A4 (ja) |
| JP (1) | JP6543313B2 (ja) |
| KR (1) | KR102349915B1 (ja) |
| CN (1) | CN111164652B (ja) |
| WO (1) | WO2019069875A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110708594A (zh) * | 2019-09-26 | 2020-01-17 | 三星电子(中国)研发中心 | 一种内容影像的生成方法及系统 |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020095465A (ja) * | 2018-12-12 | 2020-06-18 | ソニー株式会社 | 画像処理装置、画像処理方法、及び、プログラム |
| PT3912089T (pt) * | 2019-02-28 | 2025-07-21 | Stats Llc | Sistema e método para a reidentificação de jogadores em transmissões de vídeo |
| CN113989101B (zh) * | 2021-09-30 | 2025-05-02 | 北京新氧科技有限公司 | 一种3d图片到2d图片的转化方法、装置、电子设备及存储介质 |
| CN114520875B (zh) * | 2022-01-28 | 2024-04-02 | 西安维沃软件技术有限公司 | 视频处理方法、装置及电子设备 |
| JP7364269B2 (ja) * | 2022-03-15 | 2023-10-18 | Necプラットフォームズ株式会社 | 物体検知装置、画像処理表示方法及びプログラム |
| EP4495725A4 (en) * | 2022-03-15 | 2026-04-08 | Omron Tateisi Electronics Co | AERIAL VIEW DATA GENERATION DEVICE, LEARNING DEVICE, AERIAL VIEW DATA GENERATION PROGRAM, AERIAL VIEW DATA GENERATION METHOD AND ROBOT |
| JP7438515B2 (ja) * | 2022-03-15 | 2024-02-27 | オムロン株式会社 | 俯瞰データ生成装置、学習装置、俯瞰データ生成プログラム、俯瞰データ生成方法、及びロボット |
| US20250285381A1 (en) * | 2024-03-07 | 2025-09-11 | GM Global Technology Operations LLC | Human-centric vehicular metaverse platform for road-side ar/vr content delivery |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11250396A (ja) | 1998-02-27 | 1999-09-17 | Hitachi Ltd | 車両位置情報表示装置および方法 |
| JPH11339192A (ja) * | 1998-05-25 | 1999-12-10 | Hitachi Ltd | 車両用表示装置 |
| JP2002278662A (ja) * | 2001-03-22 | 2002-09-27 | Namco Ltd | ゲーム装置、ゲーム処理用プログラム、およびそのプログラムを記録した記録媒体 |
| JP2003216981A (ja) | 2002-01-25 | 2003-07-31 | Iwane Kenkyusho:Kk | 自動作業システム |
| JP2006107521A (ja) | 2005-10-17 | 2006-04-20 | Denso Corp | 移動体用通信装置 |
| JP2011182059A (ja) | 2010-02-26 | 2011-09-15 | Mitsubishi Motors Corp | 車両周辺監視装置 |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1183494C (zh) * | 1997-11-25 | 2005-01-05 | 世嘉股份有限公司 | 图象生成装置 |
| JP3059956B2 (ja) * | 1998-03-19 | 2000-07-04 | コナミ株式会社 | 画像作成装置、画像作成方法及び画像作成プログラムが記録された可読記録媒体 |
| CN1170284C (zh) * | 1998-03-20 | 2004-10-06 | 西铁城时计株式会社 | 磁记录装置 |
| JP3442736B2 (ja) * | 2000-11-30 | 2003-09-02 | コナミ株式会社 | 画像処理装置、画像処理方法及び情報記憶媒体 |
| WO2005088970A1 (ja) | 2004-03-11 | 2005-09-22 | Olympus Corporation | 画像生成装置、画像生成方法、および画像生成プログラム |
| JP3769287B2 (ja) * | 2004-09-09 | 2006-04-19 | コナミ株式会社 | 画像生成装置、荷重表示方法、ならびに、プログラム |
| JP2006092156A (ja) * | 2004-09-22 | 2006-04-06 | Namco Ltd | プログラム、情報記憶媒体及び画像生成装置 |
| JP4534922B2 (ja) * | 2005-09-16 | 2010-09-01 | 株式会社デンソー | 仮想先行車画像表示システム |
| GB0807953D0 (en) * | 2008-05-01 | 2008-06-11 | Ying Ind Ltd | Improvements in motion pictures |
| JP5681569B2 (ja) | 2011-05-31 | 2015-03-11 | 富士通テン株式会社 | 情報処理システム、サーバ装置、および、車載装置 |
| DE112013002354T5 (de) * | 2012-05-07 | 2015-04-16 | Honda Motor Co., Ltd. | Verfahren zum Erzeugen virtueller Anzeigeflächen aus Videobildern einer straßenbasierten Landschaft |
| US8892358B2 (en) * | 2013-03-14 | 2014-11-18 | Robert Bosch Gmbh | System and method for distortion correction in three-dimensional environment visualization |
| DE102014219575A1 (de) * | 2013-09-30 | 2015-07-23 | Honda Motor Co., Ltd. | Verbesserte 3-Dimensionale (3-D) Navigation |
| US20150104757A1 (en) * | 2013-10-15 | 2015-04-16 | Mbfarr, Llc | Driving assessment and training method and apparatus |
| US10321117B2 (en) * | 2014-04-11 | 2019-06-11 | Lucasfilm Entertainment Company Ltd. | Motion-controlled body capture and reconstruction |
| WO2016092591A1 (ja) * | 2014-12-09 | 2016-06-16 | 三菱電機株式会社 | 衝突リスク算出装置、衝突リスク表示装置、車体制御装置 |
| JP6372402B2 (ja) * | 2015-03-16 | 2018-08-15 | 株式会社デンソー | 画像生成装置 |
| KR101750159B1 (ko) * | 2015-07-01 | 2017-06-22 | 엘지전자 주식회사 | 차량 주행 보조 장치, 이의 동작 방법, 및 이를 포함하는 차량 |
-
2017
- 2017-10-02 JP JP2017192431A patent/JP6543313B2/ja active Active
-
2018
- 2018-10-01 EP EP18864949.5A patent/EP3693930A4/en not_active Withdrawn
- 2018-10-01 KR KR1020207012744A patent/KR102349915B1/ko not_active Expired - Fee Related
- 2018-10-01 CN CN201880064353.4A patent/CN111164652B/zh active Active
- 2018-10-01 WO PCT/JP2018/036758 patent/WO2019069875A1/ja not_active Ceased
-
2020
- 2020-04-01 US US16/837,981 patent/US10896542B2/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11250396A (ja) | 1998-02-27 | 1999-09-17 | Hitachi Ltd | 車両位置情報表示装置および方法 |
| JPH11339192A (ja) * | 1998-05-25 | 1999-12-10 | Hitachi Ltd | 車両用表示装置 |
| JP2002278662A (ja) * | 2001-03-22 | 2002-09-27 | Namco Ltd | ゲーム装置、ゲーム処理用プログラム、およびそのプログラムを記録した記録媒体 |
| JP2003216981A (ja) | 2002-01-25 | 2003-07-31 | Iwane Kenkyusho:Kk | 自動作業システム |
| JP2006107521A (ja) | 2005-10-17 | 2006-04-20 | Denso Corp | 移動体用通信装置 |
| JP2011182059A (ja) | 2010-02-26 | 2011-09-15 | Mitsubishi Motors Corp | 車両周辺監視装置 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110708594A (zh) * | 2019-09-26 | 2020-01-17 | 三星电子(中国)研发中心 | 一种内容影像的生成方法及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20200234497A1 (en) | 2020-07-23 |
| CN111164652B (zh) | 2023-12-08 |
| EP3693930A4 (en) | 2021-06-30 |
| CN111164652A (zh) | 2020-05-15 |
| JP6543313B2 (ja) | 2019-07-10 |
| EP3693930A1 (en) | 2020-08-12 |
| KR20200054322A (ko) | 2020-05-19 |
| US10896542B2 (en) | 2021-01-19 |
| JP2019067174A (ja) | 2019-04-25 |
| KR102349915B1 (ko) | 2022-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6543313B2 (ja) | 移動体用画像生成記録表示装置及びプログラム | |
| CN109215433B (zh) | 用于自动驾驶仿真的基于视觉的驾驶场景生成器 | |
| US12017663B2 (en) | Sensor aggregation framework for autonomous driving vehicles | |
| JP7052174B2 (ja) | 将来経路を推定するシステム及び方法 | |
| EP3942794B1 (en) | Depth-guided video inpainting for autonomous driving | |
| JP5182042B2 (ja) | 画像処理装置、画像処理方法及びコンピュータプログラム | |
| US11328219B2 (en) | System and method for training a machine learning model deployed on a simulation platform | |
| US11016500B2 (en) | Simulation-based method to evaluate perception requirement for autonomous driving vehicles | |
| EP3583380B1 (en) | Shape estimating apparatus | |
| JP6095985B2 (ja) | 再生装置、再生システム、再生方法及びプログラム | |
| US20190325597A1 (en) | Simultaneous Localization And Mapping Constraints In Generative Adversarial Networks For Monocular Depth Estimation | |
| US10860868B2 (en) | Lane post-processing in an autonomous driving vehicle | |
| KR20180049040A (ko) | 자율 주행 차량의 주행 결정을 위한 주변 환경 구성 방법 및 시스템 | |
| JP6697115B2 (ja) | 移動体用画像生成記録表示装置及びプログラム | |
| JP7077726B2 (ja) | 車両システム、空間領域推測方法及び空間領域推測装置 | |
| KR102511539B1 (ko) | 영상 기반 차량 주행 시뮬레이션 시스템 및 방법 | |
| JP6080735B2 (ja) | 運転支援装置 | |
| CN119904841A (zh) | 图像处理方法、装置、电子设备及车辆 | |
| CN112669335B (zh) | 车辆感知方法、装置、电子设备以及机器可读存储介质 | |
| CN121009663A (zh) | 一种仿真数据生成方法、装置和设备 | |
| CN117036403A (zh) | 图像处理方法、装置、电子设备和存储介质 | |
| CN112805200B (zh) | 交通场景的快照图像 | |
| CN121686409A (zh) | 障碍物轨迹预测方法、存储介质、程序产品及车载设备 | |
| CN120702461A (zh) | 一种路径推荐方法、装置以及车辆 |
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: 18864949 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: 20207012744 Country of ref document: KR Kind code of ref document: A |
|
| ENP | Entry into the national phase |
Ref document number: 2018864949 Country of ref document: EP Effective date: 20200504 |
|
| WWW | Wipo information: withdrawn in national office |
Ref document number: 2018864949 Country of ref document: EP |