WO2017092679A1 - 一种眼球跟踪的方法及装置、设备 - Google Patents
一种眼球跟踪的方法及装置、设备 Download PDFInfo
- Publication number
- WO2017092679A1 WO2017092679A1 PCT/CN2016/108060 CN2016108060W WO2017092679A1 WO 2017092679 A1 WO2017092679 A1 WO 2017092679A1 CN 2016108060 W CN2016108060 W CN 2016108060W WO 2017092679 A1 WO2017092679 A1 WO 2017092679A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- eyeball
- grayscale image
- nth frame
- facial
- grayscale
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Definitions
- the present invention relates to the field of visual tracking technology, and in particular, to a method, device and device for eyeball tracking.
- Eye tracking is an algorithm for tracking eye movements.
- the algorithm can perform eye iris contour detection and localization for each frame of video recording, then use the optimal frame to fit and mark, and can calculate pupils. The location of the center.
- Embodiments of the present invention provide a method, device, and device for eyeball tracking, which are used to automatically detect a starting point of an eyeball, and automatically adjust when an eyeball contour is recognized incorrectly.
- a method for eyeball tracking provided by an embodiment of the present invention includes:
- the facial grayscale map set includes a multi-frame facial grayscale map
- N is a positive integer
- the contour of the iris of the eye according to the Nth frame facial grayscale image is determined.
- a center position of the eyeball pupil as a center position of the eyeball pupil in the grayscale image of the (N+1)th frame;
- the performing an eyeball pupil detection on the Nth frame facial grayscale image to determine a center position of the eyeball pupil in the Nth frame facial grayscale image comprises:
- the center position of the eyeball pupil is determined according to the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image and the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image.
- the horizontal projection projection of the Nth frame facial grayscale image is performed to obtain a horizontal projection curve of the Nth frame facial grayscale image, including:
- the determining, according to the horizontal projection curve of the Nth frame facial grayscale image, the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image comprising:
- Pre-processing the horizontal projection curve of the Nth frame facial grayscale image, and correspondingly the second trough and the third trough in the horizontal projection curve of the preprocessed Nth frame facial grayscale image The coordinates in the Nth frame facial grayscale image are determined as the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image;
- the horizontal projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the horizontal projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the determining, according to the vertical projection curve of the Nth frame facial grayscale image, the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image including:
- the central axis is a coordinate in the Nth frame facial grayscale image corresponding to two mutually symmetric troughs of the symmetry axis, and is determined as a coordinate of the eyeball in a horizontal direction of the Nth frame facial grayscale image ;
- the vertical projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the vertical projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the center of the eyeball pupil is determined according to the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image and the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image.
- Location including:
- centroid of the collection of the positions of the eyeball pupils is determined as the center position of the pupil of the eyeball.
- the center of the eyeball pupil is centered to determine an eyeball window corresponding to Grayscale area, including:
- a grayscale image region extending on the Nth frame or the N+1th frame facial grayscale image centering on a center position of the eyeball pupil is determined as a grayscale image region corresponding to the eyeball window.
- the determining, according to the grayscale region corresponding to the eyeball window, the contour of the iris of the eyeball in the grayscale image of the Nth frame or the N+1th frame comprising:
- the preset condition is a1+(x-1) ⁇ , and each movement distance is d, wherein a1 is a first angle threshold, x is a number of movements, and ⁇ is a second angle threshold;
- a2 is a third angle threshold, a2 is greater than a1, and a2 is greater than ⁇ .
- an apparatus for eyeball tracking including:
- An acquiring unit configured to acquire a set of facial grayscale images to be detected, where the facial grayscale map set includes a multi-frame facial grayscale map;
- a determining unit configured to determine whether the Nth frame facial grayscale image in the facial grayscale set to be detected determines an outline of the iris of the eyeball; N is a positive integer;
- a central position determining unit configured to perform an eyeball on the Nth frame facial grayscale image if the Nth frame facial grayscale image in the facial grayscale set to be detected does not determine an outline of the eyeball iris Hole detection, determining a center position of the pupil of the eyeball in the grayscale image of the Nth frame;
- An eyeball window determining unit configured to determine, in the Nth frame grayscale image, a grayscale image region corresponding to the eyeball window centering on a center position of the eyeball pupil;
- the eyeball contour determining unit is configured to determine an outline of the iris of the eyeball in the grayscale image of the Nth frame according to the grayscale image region corresponding to the eyeball window.
- the central position determining unit is further configured to: according to the Nth frame facial grayscale map The contour of the eyeball iris determines the center position of the eyeball pupil as the center position of the eyeball pupil in the grayscale image of the (N+1)th frame;
- the eyeball window determining unit is further configured to determine, in the N+1th frame facial grayscale image, a grayscale image region corresponding to the eyeball window centering on a center position of the eyeball pupil;
- the eyeball contour determining unit is further configured to determine an outline of the iris of the eyeball in the grayscale image of the (N+1)th frame according to the grayscale region and the preset condition corresponding to the eyeball window.
- the central location determining unit is specifically configured to:
- the center position of the eyeball pupil is determined according to the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image and the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image.
- the central location determining unit is specifically configured to:
- the N-th frame facial grayscale image with the grayscale value greater than the first threshold is horizontally integrated and projected, and the horizontal projection curve of the Nth frame facial grayscale image is acquired.
- the central location determining unit is specifically configured to:
- Pre-processing the horizontal projection curve of the Nth frame facial grayscale image, and correspondingly the second trough and the third trough in the horizontal projection curve of the preprocessed Nth frame facial grayscale image The coordinates in the Nth frame facial grayscale image are determined as the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image;
- the horizontal projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the horizontal projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the central location determining unit is specifically configured to:
- the central axis is a coordinate in the Nth frame facial grayscale image corresponding to two mutually symmetric troughs of the symmetry axis, and is determined as a coordinate of the eyeball in a horizontal direction of the Nth frame facial grayscale image ;
- the vertical projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the vertical projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the central location determining unit is specifically configured to:
- centroid of the collection of the positions of the eyeball pupils is determined as the center position of the pupil of the eyeball.
- the eyeball window determining unit is specifically configured to:
- a grayscale image region extending on the Nth frame or the N+1th frame facial grayscale image centering on a center position of the eyeball pupil is determined as a grayscale image region corresponding to the eyeball window.
- the eyeball contour determining unit is specifically configured to:
- the preset condition is a1+(x-1) ⁇ , and each movement distance is d, wherein a1 is a first angle threshold, x is a number of movements, and ⁇ is a second angle threshold;
- the eyeball contour determining unit is further configured to stop moving in a grayscale region of the eyeball window when the moving angle is greater than or equal to a2;
- a2 is a third angle threshold, a2 is greater than a1, and a2 is greater than ⁇ .
- an embodiment of the present invention provides an eye tracking device, including:
- At least one processor and,
- the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of eye tracking in the first aspect above.
- an embodiment of the present invention provides a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium stores computer instructions for causing the computer to perform the first aspect described above The method of eye tracking in the middle.
- an embodiment of the present invention provides a computer program product, including a computing program stored on a non-transitory computer readable storage medium, the computer program A program instruction is included that, when executed by a computer, causes the computer to perform the method of eye tracking in the first aspect above.
- the embodiment of the present invention indicates that, by acquiring the set of facial grayscale images to be detected, determining whether the grayscale image of the Nth frame in the facial grayscale set to be detected determines the contour of the iris of the eyeball, and if not, the Nth
- the frame grayscale image is used to detect the pupil of the eyeball, and the center position of the pupil of the eyeball in the grayscale image of the Nth frame is determined.
- the grayscale image of the face of the Nth frame the gray position corresponding to the eyeball window is determined centering on the center position of the eyeball pupil.
- the contour of the iris of the eyeball in the grayscale image of the Nth frame is determined according to the grayscale region corresponding to the eyeball window.
- the contour of the iris of the eyeball can be automatically adjusted, and the pupil of the eyeball can be repositioned, thereby avoiding the situation that the tracking error of the contour of the iris of the eyeball cannot be automatically adjusted. Improves the accuracy of eye tracking, and can automatically identify the center of the eyeball to detect the pupil of the eye.
- FIG. 1 is a schematic flowchart of a method for eyeball tracking according to an embodiment of the present invention
- FIG. 2 is a schematic diagram of a horizontal projection curve before preprocessing according to an embodiment of the present invention
- FIG. 3 is a schematic diagram of a horizontal projection curve after preprocessing according to an embodiment of the present invention.
- FIG. 4 is a schematic structural diagram of an apparatus for eyeball tracking according to an embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of an apparatus for eyeball tracking according to an embodiment of the present invention.
- FIG. 1 shows a flow of an eyeball tracking provided by an embodiment of the present invention, which may be performed by a device for eyeball tracking.
- Step 101 Acquire a set of facial grayscale images to be detected.
- Step 102 Determine whether an Nth frame facial grayscale image in the facial grayscale set to be detected determines an outline of an eye iris.
- Step 103 Perform eyeball pupil detection on the Nth frame facial grayscale image, and determine a center position of the eyeball pupil in the Nth frame facial grayscale image.
- Step 104 Determine, in the Nth frame facial grayscale image, a grayscale region corresponding to the eyeball window centering on a center position of the eyeball pupil.
- Step 105 Determine an outline of an iris of the eyeball in the grayscale image of the Nth frame according to the grayscale region corresponding to the eyeball window.
- Step 106 The center position of the eyeball pupil determined according to the contour of the eye iris of the Nth frame facial grayscale image is taken as the center position of the eyeball pupil in the (N+1)th frame facial grayscale image.
- Step 107 Determine, in the N+1 frame facial grayscale image, a grayscale region corresponding to the eyeball window centering on a center position of the eyeball pupil.
- Step 108 Determine an outline of an iris of the eyeball in the grayscale image of the (N+1)th frame according to the grayscale region and the preset condition corresponding to the eyeball window.
- the set of facial grayscales to be detected includes a multi-frame facial grayscale image. Dividing the video into pictures of one frame, and grouping the pictures of the one frame, if the pictures of the frame are all colored, it is necessary to convert the color picture of the other frame into a gray image, that is, The face grayscale image to be detected can be obtained.
- step 102 it is determined whether the Nth frame facial grayscale image in the facial grayscale image set to be detected acquired in step 101 can determine the contour of the eyeball iris, and if the contour of the eyeball iris can be determined, the description There is no error in the eye tracking of the N frame facial grayscale image, and the eye tracking of the N+1 frame facial grayscale image can be performed. If the outline of the iris of the eyeball cannot be determined, it may be the Nth There is an error in the eyeball tracking of the frame face grayscale image, and it is necessary to re-determine the center position of the eyeball pupil of the Nth frame facial grayscale image, or the Nth frame facial grayscale image is the first frame facial grayscale image. The first frame facial grayscale image needs to determine the center position of the eyeball pupil of the first frame facial grayscale image. Where N is a positive integer.
- step 103 if it is determined in step 102 that the Nth frame facial grayscale image in the facial grayscale image set to be detected does not determine the contour of the eyeball iris, the Nth frame facial grayscale image needs to be eyeballed.
- the pupil detection determines the center position of the pupil of the eyeball in the grayscale image of the Nth frame.
- the Nth frame facial grayscale image is horizontally integrated and projected, and a horizontal projection curve of the Nth frame facial grayscale image is obtained.
- the pixels in the grayscale image of the Nth frame are larger than the first threshold, and then the grayscale image of the Nth frame whose grayscale value is greater than the first threshold is horizontally integrated and projected. , that is, the horizontal projection curve of the face gray image of the Nth frame can be obtained.
- the first threshold can be set empirically, such as a gray value that can be set to 100. Removing the Nth frame facial grayscale image whose grayscale value is greater than the first threshold value indicates denoising the Nth frame facial grayscale image. You can get a smooth curve.
- the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image may be determined.
- Preprocessing the horizontal projection curve of the Nth frame facial grayscale image, and corresponding to the second trough and the third trough in the horizontal projection curve of the preprocessed Nth frame facial grayscale image The coordinates in the Nth frame facial grayscale image are determined as the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image.
- the horizontal projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the horizontal projection curve of the Nth frame facial grayscale image is greater than the second threshold.
- the second threshold can be set empirically, and only the peak that determines the trough to peak distance greater than the second threshold can be retained.
- Fig. 2 is the horizontal projection curve before pretreatment
- Fig. 3 is the horizontal projection curve after pretreatment.
- the “+” in the figure indicates the position of the peak.
- Fig. 3 The "+" in the middle removed a part.
- Figure 3 shows a horizontal projection curve, with gray values representing the ordinate and abscissa representing the vertical direction of the face grayscale image, with the peak on the left side being the trough and the peak on the right side being the crest.
- the first trough indicates where the hair is located
- the second trough indicates where the eyebrows are located
- the position between the second trough and the third trough indicates the eyeball to determine that the eye is at the The coordinates in the vertical direction of the N-frame facial grayscale image.
- the vertical map of the grayscale image in the vertical direction of the grayscale image of the Nth frame is vertically integrated, and the vertical projection curve of the grayscale image of the Nth frame is obtained.
- the abscissa of the vertical projection curve represents the coordinate in the horizontal direction of the face grayscale image, and the ordinate represents the grayscale value.
- the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image are determined.
- Preprocessing the vertical projection curve of the Nth frame facial grayscale image, and taking the central axis of the vertical projection curve of the Nth facial grayscale image as the symmetry axis in the vertical projection curve of the preprocessed Nth facial grayscale image The coordinates in the N-th face grayscale image corresponding to the two mutually symmetric valleys are determined as the coordinates of the eyeball in the horizontal direction of the N-th face facial grayscale image.
- the central axis is the central axis of the vertical projection curve of the facial grayscale image of the Nth frame, and the coordinates of the two troughs on the two sides of the central axis are the horizontal coordinates of the left and right eyes, that is, It is possible to determine the coordinates of the eyeball in the horizontal direction of the face grayscale image of the Nth frame.
- the vertical projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the vertical projection curve of the Nth frame facial grayscale image is greater than the second threshold.
- the center position of the eyeball pupil is determined according to the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image and the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image. Selecting a pixel whose gray value is smaller than a third threshold from a region in which the eyeball is located in the vertical direction of the N-th face grayscale image and a coordinate in which the eyeball is located in the horizontal direction of the N-th face facial grayscale image, The coordinates of the pixels whose degree is less than the third threshold constitute a set of positions of the eye pupil. The center of mass of the position of the pupil of the eyeball is determined as the center position of the pupil of the eyeball. This third threshold can be set empirically.
- the pixel whose gray value is smaller than the third threshold indicates the position where the black iris is located, and the longest strip of the pixel whose gray value is smaller than the third threshold in each row can be selected, and then the set is formed, and the center of mass of the set is the center position of the eye pupil. .
- the first preset distance may be extended to the left and right in the horizontal direction of the Nth frame facial grayscale image centering on the center position of the eyeball pupil.
- the second preset distance is extended up and down in the vertical direction of the Nth frame facial grayscale image.
- the grayscale image region extended on the Nth frame facial grayscale image centering on the center position of the eyeball pupil is determined as the grayscale image region corresponding to the eyeball window.
- the first preset distance and the second preset distance may be set according to experience.
- a grayscale region determined after expansion can be determined as a grayscale image corresponding to the eyeball window.
- step 105 after determining the grayscale image corresponding to the eyeball window in step 104, the center position of the eyeball pupil may be used as a starting point, and moving in the grayscale region corresponding to the eyeball window according to a preset condition, The corresponding gray value after the second movement is used as the comparison gray value. If the difference between the gray value of the comparison gray value of the Mth movement and the comparison gray value of the M-1th movement is greater than the fourth threshold, determining the point of the Mth movement as the edge of the iris of the eyeball point.
- M is a positive integer
- the fourth threshold can be set empirically.
- the contour of the iris of the eye in the grayscale image of the Nth frame is determined according to the point at the edge of the iris of the eyeball.
- the above preset condition is a1+(x-1) ⁇ , and each movement distance is d, wherein a1 is a first angle threshold, x is a number of movements, and ⁇ is a second angle threshold.
- a1 is a first angle threshold
- x is a number of movements
- ⁇ is a second angle threshold.
- the moving angle is greater than or equal to a2
- the movement in the grayscale area of the eyeball window is stopped.
- a2 is the third angle threshold
- a2 is greater than a1
- a2 is greater than ⁇ .
- the first angle threshold, the second angle threshold, the third angle threshold, and each movement distance may be set according to experience.
- step 106 the Nth in the set of facial grayscales to be detected is determined in step 102.
- the frame facial grayscale image determines the outline of the eye iris, and the eye tracking of the N+1th frame facial grayscale image can be performed. Then, the center position of the eyeball pupil determined according to the contour of the eye iris of the Nth frame facial grayscale image is taken as the center position of the eyeball pupil in the N+1 frame facial grayscale image.
- step 107 after determining the center position of the pupil of the eyeball in the grayscale image of the N+1th frame in step 106, centering on the center position of the pupil of the eyeball, in the horizontal direction of the grayscale image of the face of the N+1th frame
- the first preset distance is extended upward and leftward
- the second preset distance is extended upward and downward in the vertical direction of the N+1th frame grayscale image.
- the grayscale image region extended on the N+1th frame facial grayscale image centering on the center position of the eyeball pupil is determined as the grayscale image region corresponding to the eyeball window.
- the first preset distance is extended to the left and right in the horizontal direction of the N+1th frame, and the second preset distance is extended downward and upward respectively in the vertical direction.
- a grayscale region determined after two expansions can be determined as a grayscale image corresponding to the eyeball window.
- step 108 after determining the grayscale image corresponding to the eyeball window in step 107, the center position of the eyeball pupil may be used as a starting point, and moving in the grayscale region corresponding to the eyeball window according to a preset condition, The corresponding gray value after the second movement is used as the comparison gray value. If the difference between the gray value of the comparison gray value of the Mth movement and the comparison gray value of the M-1th movement is greater than the fourth threshold, determining the point of the Mth movement as the edge of the iris of the eyeball point.
- M is a positive integer
- the fourth threshold can be set empirically.
- the difference in the gray value of the points of the two adjacent movements is relatively large, indicating that it is at the edge of the iris of the eye.
- the contour of the iris of the eye in the grayscale image of the face of the N+1th frame is determined according to the point at the edge of the iris of the eyeball.
- the above preset condition is a1+(x-1) ⁇ , and each movement distance is d, wherein a1 is a first angle threshold, x is a number of movements, and ⁇ is a second angle threshold.
- a1 is a first angle threshold
- x is a number of movements
- ⁇ is a second angle threshold.
- the moving angle is greater than or equal to a2
- the movement in the grayscale area of the eyeball window is stopped.
- a2 is the third angle threshold
- a2 is greater than a1
- a2 is greater than ⁇ .
- the first angle threshold, the second angle threshold, the third angle threshold, and each movement distance may be set according to experience.
- the above embodiment shows that the face to be detected is determined by acquiring the set of face grayscale images to be detected. Whether the Nth frame facial grayscale image in the grayscale image set determines the outline of the iris of the eyeball, and if not, performs eyeball pupil detection on the Nth frame facial grayscale image to determine the eyeball pupil in the Nth frame facial grayscale image The central position, in the N-th face grayscale image, centering on the center position of the eyeball pupil, determining the grayscale region corresponding to the eyeball window, and determining the Nth frame facial grayscale according to the grayscale region corresponding to the eyeball window The outline of the iris of the eyeball in the figure.
- the contour of the iris of the eyeball can be automatically adjusted, and the pupil of the eyeball can be repositioned, thereby avoiding the situation that the tracking error of the contour of the iris of the eyeball cannot be automatically adjusted. Improves the accuracy of eye tracking, and can automatically identify the center of the eyeball to detect the pupil of the eye.
- FIG. 4 shows a structure of an apparatus for eye tracking provided by an embodiment of the present invention, which can perform a flow of eye tracking.
- the device specifically includes:
- the obtaining unit 401 is configured to acquire a set of facial grayscale images to be detected, where the facial grayscale map set includes a multi-frame facial grayscale map;
- the determining unit 402 is configured to determine whether the Nth frame facial grayscale image in the facial grayscale set to be detected determines an outline of the iris of the eyeball; N is a positive integer;
- the central position determining unit 403 is configured to perform eyeball boring on the Nth frame facial grayscale image if the Nth frame facial grayscale image in the facial grayscale set to be detected does not determine the contour of the eyeball iris Detecting, determining a center position of the pupil of the eyeball in the grayscale image of the Nth frame;
- An eyeball window determining unit 404 configured to determine, in the Nth frame grayscale image, a grayscale image region corresponding to the eyeball window centering on a center position of the eyeball pupil;
- the eyeball contour determining unit 405 is configured to determine an outline of the iris of the eyeball in the grayscale image of the Nth frame according to the grayscale image region corresponding to the eyeball window.
- the central position determining unit 403 is further configured to: according to the Nth frame facial grayscale image The contour of the eyeball iris determines the center position of the eyeball pupil as the center position of the eyeball pupil in the grayscale image of the (N+1)th frame;
- the eyeball window determining unit 404 is further configured to use the eye in the (N+1)th frame grayscale image Centering the center of the ball pupil to determine the grayscale area corresponding to the eyeball window;
- the eyeball contour determining unit 405 is further configured to determine an outline of the iris of the eyeball in the grayscale image of the (N+1)th frame according to the grayscale region and the preset condition corresponding to the eyeball window.
- the central location determining unit 403 is specifically configured to:
- the center position of the eyeball pupil is determined according to the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image and the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image.
- the central location determining unit 403 is specifically configured to:
- the central location determining unit 403 is specifically configured to:
- Pre-processing the horizontal projection curve of the Nth frame facial grayscale image, and correspondingly the second trough and the third trough in the horizontal projection curve of the preprocessed Nth frame facial grayscale image The coordinates in the Nth frame facial grayscale image are determined as the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image;
- the horizontal projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the horizontal projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the central location determining unit 403 is specifically configured to:
- the central axis is a coordinate in the Nth frame facial grayscale image corresponding to two mutually symmetric troughs of the symmetry axis, and is determined as a coordinate of the eyeball in a horizontal direction of the Nth frame facial grayscale image ;
- the vertical projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the vertical projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the central location determining unit 403 is specifically configured to:
- centroid of the collection of the positions of the eyeball pupils is determined as the center position of the pupil of the eyeball.
- the eyeball window determining unit 404 is specifically configured to:
- a grayscale image region extending on the Nth frame or the N+1th frame facial grayscale image centering on a center position of the eyeball pupil is determined as a grayscale image region corresponding to the eyeball window.
- the eyeball contour determining unit 405 is specifically configured to:
- the preset condition is a1+(x-1) ⁇ , and each movement distance is d, wherein a1 is a first angle threshold, x is a number of movements, and ⁇ is a second angle threshold;
- the eyeball contour determining unit 405 is further configured to stop moving in a grayscale region of the eyeball window when the moving angle is greater than or equal to a2;
- a2 is a third angle threshold, a2 is greater than a1, and a2 is greater than ⁇ .
- an embodiment of the present invention provides an eyeball tracking device. At least one processor; and a memory communicatively coupled to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor such that The at least one processor is capable of performing the method of eye tracking in the above embodiments.
- FIG. 5 is a structure of an eyeball tracking device according to an embodiment of the present invention.
- the eyeball tracking device 500 includes a transceiver 501, a processor 502, a memory 503, and a bus system 504.
- the memory 503 is used to store a program.
- the program can include program code, the program code including computer operating instructions.
- the memory 503 may be a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. Only one memory is shown in the figure, of course, the memory can also be set to a plurality as needed. Memory 503 can also be a memory in processor 502.
- the memory 503 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof:
- Operation instructions include various operation instructions for implementing various operations.
- Operating system Includes a variety of system programs for implementing various basic services and handling hardware-based tasks.
- Processor 502 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method of eye tracking can be completed by an integrated logic circuit of hardware in the processor 502 or an instruction in the form of software.
- the above processor 502 can be a pass A processor, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component.
- DSP digital signal processor
- ASIC application specific integrated circuit
- FPGA field programmable gate array
- the methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed.
- the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
- the steps of the method disclosed in the embodiments of the present invention may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
- the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
- the storage medium is located in the memory 503, and the processor 502 reads the information in the memory 503 and performs the following steps in conjunction with its hardware:
- the transceiver 501 is configured to acquire a facial grayscale set to be detected, where the facial grayscale set includes a multi-frame facial grayscale image;
- the processor 502 is configured to determine whether the Nth frame facial grayscale image in the facial grayscale set to be detected determines an outline of the iris of the eyeball; N is a positive integer; if the facial grayscale to be detected If the Nth frame grayscale image in the set of images does not determine the contour of the iris of the eyeball, the pupil of the Nth frame is subjected to eye pupil detection, and the center of the pupil of the eyeball in the grayscale image of the Nth frame is determined.
- the processor 502 is further configured to: according to the Nth frame facial grayscale map The contour of the eyeball iris determines the center position of the eyeball pupil as the center position of the eyeball pupil in the (N+1)th frame facial grayscale image; in the (N+1)th frame facial grayscale image, the pupil of the eyeball is pupild Centering on the center of the eye, determining a grayscale region corresponding to the eyeball window; determining a contour of the iris of the eyeball in the grayscale image of the (N+1)th frame according to the grayscale region and the preset condition corresponding to the eyeball window .
- the processor 502 is specifically configured to:
- the center position of the eyeball pupil is determined according to the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image and the coordinates of the eyeball in the horizontal direction of the Nth frame facial grayscale image.
- the processor 502 is specifically configured to:
- the processor 502 is specifically configured to:
- Pre-processing the horizontal projection curve of the Nth frame facial grayscale image, and correspondingly the second trough and the third trough in the horizontal projection curve of the preprocessed Nth frame facial grayscale image The coordinates in the Nth frame facial grayscale image are determined as the coordinates of the eyeball in the vertical direction of the Nth frame facial grayscale image;
- the horizontal projection curve of the Nth frame facial grayscale image is preprocessed to select a peak in which the distance from the trough to the peak in the horizontal projection curve of the Nth frame facial grayscale image is greater than a second threshold.
- the processor 502 is specifically configured to:
- the central axis is a coordinate in the Nth frame facial grayscale image corresponding to two mutually symmetric troughs of the symmetry axis, and is determined as a coordinate of the eyeball in a horizontal direction of the Nth frame facial grayscale image ;
- the vertical projection curve of the Nth frame facial grayscale image is preprocessed to select the The distance from the trough to the peak in the vertical projection curve of the Nth frame facial grayscale image is greater than the peak value of the second threshold.
- the processor 502 is specifically configured to:
- centroid of the collection of the positions of the eyeball pupils is determined as the center position of the pupil of the eyeball.
- the processor 502 is specifically configured to:
- a grayscale image region extending on the Nth frame or the N+1th frame facial grayscale image centering on a center position of the eyeball pupil is determined as a grayscale image region corresponding to the eyeball window.
- the processor 502 is specifically configured to:
- the preset condition is a1+(x-1) ⁇ , and each movement distance is d, wherein a1 is a first angle threshold, x is a number of movements, and ⁇ is a second angle threshold;
- the processor 502 is further configured to stop moving in a grayscale region of the eyeball window when the moving angle is greater than or equal to a2;
- a2 is a third angle threshold, a2 is greater than a1, and a2 is greater than ⁇ .
- the eye tracking device of the embodiment of the present invention exists in various forms, including but not limited to:
- Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication. Such devices include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
- Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
- Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.
- Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
- the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .
- the present invention provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the eyeball of any of the above The method of tracking.
- the present invention also provides a computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer A method of causing the computer to perform the eye tracking as described in any of the above.
- the present application is made with reference to a method, a device (system), and a computer program according to an embodiment of the present application.
- the flow chart and/or block diagram of the product is described. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG.
- These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (23)
- 一种眼球跟踪的方法,其特征在于,包括:获取待检测的面部灰度图集合,所述面部灰度图集合中包括多帧面部灰度图;判断所述待检测的面部灰度图集合中的第N帧面部灰度图是否确定出眼球虹膜的轮廓;N为正整数;若否,则对所述第N帧面部灰度图进行眼球瞳孔检测,确定所述第N帧面部灰度图中眼球瞳孔的中心位置;在所述第N帧面部灰度图中,以所述眼球瞳孔的中心位置为中心,确定眼球窗口对应的灰度图区域;根据所述眼球窗口对应的灰度图区域,确定所述第N帧面部灰度图中的眼球虹膜的轮廓。
- 如权利要求1所述的方法,其特征在于,若所述待检测的面部灰度图集合中的第N帧面部灰度图确定出眼球虹膜的轮廓,则将根据所述第N帧面部灰度图的眼球虹膜的轮廓确定的眼球瞳孔的中心位置作为所述第N+1帧面部灰度图中眼球瞳孔的中心位置;在所述第N+1帧面部灰度图中,以所述眼球瞳孔的中心位置为中心,确定眼球窗口对应的灰度图区域;根据所述眼球窗口对应的灰度图区域和预设条件,确定所述第N+1帧面部灰度图中的眼球虹膜的轮廓。
- 如权利要求1所述的方法,其特征在于,所述对所述第N帧面部灰度图进行眼球瞳孔检测,确定所述第N帧面部灰度图中眼球瞳孔的中心位置,包括:将所述第N帧面部灰度图进行水平积分投影,获取所述第N帧面部灰度图的水平投影曲线;根据所述第N帧面部灰度图的水平投影曲线,确定眼球位于所述第N帧 面部灰度图的垂直方向上的坐标;将所述眼球位于所述第N帧面部灰度图的垂直方向上的灰度图区域进行垂直积分投影,获取所述第N帧面部灰度图的垂直投影曲线;根据所述第N帧面部灰度图的垂直投影曲线,确定所述眼球位于所述第N帧面部灰度图的水平方向上的坐标;根据所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标和所述眼球位于所述第N帧面部灰度图的水平方向上的坐标,确定眼球瞳孔的中心位置。
- 如权利要求3所述的方法,其特征在于,所述将所述第N帧面部灰度图进行水平积分投影,获取所述第N帧面部灰度图的水平投影曲线,包括:去除所述第N帧面部灰度图中灰度值大于第一阈值的像素,将所述去除灰度值大于第一阈值的第N帧面部灰度图进行水平积分投影,获取所述第N帧面部灰度图的水平投影曲线。
- 如权利要求3所述的方法,其特征在于,所述根据所述第N帧面部灰度图的水平投影曲线,确定眼球位于所述第N帧面部灰度图的垂直方向上的坐标,包括:对所述第N帧面部灰度图的水平投影曲线进行预处理,将所述预处理后的第N帧面部灰度图的水平投影曲线中第二个波谷与第三个波谷之间相对应的所述第N帧面部灰度图中的坐标,确定为所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标;其中,对所述第N帧面部灰度图的水平投影曲线进行预处理为选取所述第N帧面部灰度图的水平投影曲线中波谷到波峰的距离大于第二阈值的峰值。
- 如权利要求3所述的方法,其特征在于,所述根据所述第N帧面部灰度图的垂直投影曲线,确定所述眼球位于所述第N帧面部灰度图的水平方向上的坐标,包括:对所述第N帧面部灰度图的垂直投影曲线进行预处理,将所述预处理后 的第N帧面部灰度图的垂直投影曲线中以所述第N面部灰度图的垂直投影曲线的中轴线为对称轴的两个相互对称的波谷相对应的所述第N帧面部灰度图中的坐标,确定为所述眼球位于所述第N帧面部灰度图的水平方向上的坐标;其中,对所述第N帧面部灰度图的垂直投影曲线进行预处理为选取所述第N帧面部灰度图的垂直投影曲线中波谷到波峰的距离大于第二阈值的峰值。
- 如权利要求3所述的方法,其特征在于,根据所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标和所述眼球位于所述第N帧面部灰度图的水平方向上的坐标,确定眼球瞳孔的中心位置,包括:从所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标和所述眼球位于所述第N帧面部灰度图的水平方向上的坐标围成的区域中选取灰度值小于第三阈值的像素,将所述灰度值小于第三阈值的像素的坐标组成所述眼球瞳孔的位置集合;将所述眼球瞳孔的位置集合的质心,确定为眼球瞳孔的中心位置。
- 如权利要求1或2所述的方法,其特征在于,所述以所述眼球瞳孔的中心位置为中心,确定眼球窗口对应的灰度图区域,包括:以所述眼球瞳孔的中心位置为中心,在第N帧或第N+1帧面部灰度图的水平方向上向左右扩展第一预设距离,在第N帧或第N+1帧面部灰度图的垂直方向上向上下扩展第二预设距离;将以所述眼球瞳孔的中心位置为中心,在所述第N帧或第N+1帧面部灰度图上扩展的灰度图区域,确定为所述眼球窗口对应的灰度图区域。
- 如权利要求1或2所述的方法,其特征在于,所述根据所述眼球窗口对应的灰度图区域,确定所述第N帧或第N+1帧面部灰度图中的眼球虹膜的轮廓,包括:以所述眼球瞳孔的中心位置为出发点,根据预设条件,在所述眼球窗口对应的灰度图区域内移动,将每次移动后对应位置的灰度值作为比较灰度值;若第M次移动的比较灰度值与第M-1次移动的比较灰度值的灰度值差值 大于第四阈值,则将所述第M次移动的点确定为眼球虹膜边缘处的点;M为正整数;根据所述眼球虹膜边缘处的点,确定所述第N帧或第N+1帧面部灰度图中的眼球虹膜的轮廓。
- 如权利要求9所述的方法,其特征在于,所述预设条件为a1+(x-1)λ,每次移动距离为d,其中,a1为第一角度阈值,x为移动的次数,λ为第二角度阈值;当所述移动角度大于等于a2时,停止在所述眼球窗口的灰度图区域内移动;其中,所述a2为第三角度阈值,a2大于a1,a2大于λ。
- 一种眼球跟踪的装置,其特征在于,包括:获取单元,用于获取待检测的面部灰度图集合,所述面部灰度图集合中包括多帧面部灰度图;判断单元,用于判断所述待检测的面部灰度图集合中的第N帧面部灰度图是否确定出眼球虹膜的轮廓;N为正整数;中心位置确定单元,用于若所述待检测的面部灰度图集合中的第N帧面部灰度图未确定出眼球虹膜的轮廓,则对所述第N帧面部灰度图进行眼球瞳孔检测,确定所述第N帧面部灰度图中眼球瞳孔的中心位置;眼球窗口确定单元,用于在所述第N帧面部灰度图中,以所述眼球瞳孔的中心位置为中心,确定眼球窗口对应的灰度图区域;眼球轮廓确定单元,用于根据所述眼球窗口对应的灰度图区域,确定所述第N帧面部灰度图中的眼球虹膜的轮廓。
- 如权利要求11所述的装置,其特征在于,若所述待检测的面部灰度图集合中的第N帧面部灰度图确定出眼球虹膜的轮廓,则中心位置确定单元还用于将根据所述第N帧面部灰度图的眼球虹膜的轮廓确定的眼球瞳孔的中心位置作为所述第N+1帧面部灰度图中眼球瞳孔的中心位置;眼球窗口确定单元还用于在所述第N+1帧面部灰度图中,以所述眼球瞳 孔的中心位置为中心,确定眼球窗口对应的灰度图区域;眼球轮廓确定单元还用于根据所述眼球窗口对应的灰度图区域和预设条件,确定所述第N+1帧面部灰度图中的眼球虹膜的轮廓。
- 如权利要求11所述的装置,其特征在于,所述中心位置确定单元具体用于:将所述第N帧面部灰度图进行水平积分投影,获取所述第N帧面部灰度图的水平投影曲线;根据所述第N帧面部灰度图的水平投影曲线,确定眼球位于所述第N帧面部灰度图的垂直方向上的坐标;将所述眼球位于所述第N帧面部灰度图的垂直方向上的灰度图区域进行垂直积分投影,获取所述第N帧面部灰度图的垂直投影曲线;根据所述第N帧面部灰度图的垂直投影曲线,确定所述眼球位于所述第N帧面部灰度图的水平方向上的坐标;根据所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标和所述眼球位于所述第N帧面部灰度图的水平方向上的坐标,确定眼球瞳孔的中心位置。
- 如权利要求13所述的装置,其特征在于,所述中心位置确定单元具体用于:去除所述第N帧面部灰度图中灰度值大于第一阈值的像素,将所述去除灰度值大于第一阈值的第N帧面部灰度图进行水平积分投影,获取所述第N帧面部灰度图的水平投影曲线。
- 如权利要求13所述的装置,其特征在于,所述中心位置确定单元具体用于:对所述第N帧面部灰度图的水平投影曲线进行预处理,将所述预处理后的第N帧面部灰度图的水平投影曲线中第二个波谷与第三个波谷之间相对应的所述第N帧面部灰度图中的坐标,确定为所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标;其中,对所述第N帧面部灰度图的水平投影曲线进行预处理为选取所述所述第N帧面部灰度图的水平投影曲线中波谷到波峰的距离大于第二阈值的峰值。
- 如权利要求13所述的装置,其特征在于,所述中心位置确定单元具体用于:对所述第N帧面部灰度图的垂直投影曲线进行预处理,将所述预处理后的第N帧面部灰度图的垂直投影曲线中以所述第N面部灰度图的垂直投影曲线的中轴线为对称轴的两个相互对称的波谷相对应的所述第N帧面部灰度图中的坐标,确定为所述眼球位于所述第N帧面部灰度图的水平方向上的坐标;其中,对所述第N帧面部灰度图的垂直投影曲线进行预处理为选取所述所述第N帧面部灰度图的垂直投影曲线中波谷到波峰的距离大于第二阈值的峰值。
- 如权利要求13所述的装置,其特征在于,所述中心位置确定单元具体用于:从所述眼球位于所述第N帧面部灰度图的垂直方向上的坐标和所述眼球位于所述第N帧面部灰度图的水平方向上的坐标围成的区域中选取灰度值小于第三阈值的像素,将所述灰度值小于第三阈值的像素的坐标组成所述眼球瞳孔的位置集合;将所述眼球瞳孔的位置集合的质心,确定为眼球瞳孔的中心位置。
- 如权利要求11或12所述的装置,其特征在于,所述眼球窗口确定单元具体用于:以所述眼球瞳孔的中心位置为中心,在第N帧或第N+1帧面部灰度图的水平方向上向左右扩展第一预设距离,在第N帧或第N+1帧面部灰度图的垂直方向上向上下扩展第二预设距离;将以所述眼球瞳孔的中心位置为中心,在所述第N帧或第N+1帧面部灰度图上扩展的灰度图区域,确定为所述眼球窗口对应的灰度图区域。
- 如权利要求11或12所述的装置,其特征在于,所述眼球轮廓确定 单元具体用于:以所述眼球瞳孔的中心位置为出发点,根据预设条件,在所述眼球窗口对应的灰度图区域内移动,将每次移动后对应位置的灰度值作为比较灰度值;若第M次移动的比较灰度值与第M-1次移动的比较灰度值的灰度值差值大于第四阈值,则将所述第M次移动的点确定为眼球虹膜边缘处的点;M为正整数;根据所述眼球虹膜边缘处的点,确定所述第N帧或第N+1帧面部灰度图中的眼球虹膜的轮廓。
- 如权利要求19所述的装置,其特征在于,所述预设条件为a1+(x-1)λ,每次移动距离为d,其中,a1为第一角度阈值,x为移动的次数,λ为第二角度阈值;所述眼球轮廓确定单元还用于当所述移动角度大于等于a2时,停止在所述眼球窗口的灰度图区域内移动;其中,所述a2为第三角度阈值,a2大于a1,a2大于λ。
- 一种眼球跟踪的设备,其特征在于,包括:至少一个处理器;以及,与所述至少一个处理器通信连接的存储器;其中,所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行权利要求1-10任一所述眼球跟踪的方法。
- 一种非暂态计算机可读存储介质,其特征在于,所述非暂态计算机可读存储介质存储计算机指令,所述计算机指令用于使所述计算机执行权利要求1-10任一所述眼球跟踪的方法。
- 一种计算机程序产品,其特征在于,所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算程序,所述计算机程序包括程序指令,当所述程序指令被计算机执行时,使所述计算机执行权利要求1-10任一所述眼球跟踪的方法。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US15/780,641 US10699420B2 (en) | 2015-12-02 | 2016-11-30 | Eyeball tracking method and apparatus, and device |
| CA3025964A CA3025964C (en) | 2015-12-02 | 2016-11-30 | Eyeball tracking method and apparatus, and device |
| EP16869989.0A EP3385885A4 (en) | 2015-12-02 | 2016-11-30 | Eyeball tracking method and apparatus, and device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510875607.9 | 2015-12-02 | ||
| CN201510875607.9A CN105930762A (zh) | 2015-12-02 | 2015-12-02 | 一种眼球跟踪的方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017092679A1 true WO2017092679A1 (zh) | 2017-06-08 |
Family
ID=56839969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/108060 Ceased WO2017092679A1 (zh) | 2015-12-02 | 2016-11-30 | 一种眼球跟踪的方法及装置、设备 |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US10699420B2 (zh) |
| EP (1) | EP3385885A4 (zh) |
| CN (1) | CN105930762A (zh) |
| CA (1) | CA3025964C (zh) |
| TW (1) | TWI611353B (zh) |
| WO (1) | WO2017092679A1 (zh) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930762A (zh) * | 2015-12-02 | 2016-09-07 | 中国银联股份有限公司 | 一种眼球跟踪的方法及装置 |
| CN106778713B (zh) * | 2017-03-01 | 2023-09-22 | 武汉虹识技术有限公司 | 一种动态人眼跟踪的虹膜识别装置及方法 |
| CN107145224B (zh) * | 2017-04-07 | 2019-10-29 | 清华大学 | 基于三维球面泰勒展开的人眼视线跟踪方法和装置 |
| JP6930223B2 (ja) * | 2017-05-31 | 2021-09-01 | 富士通株式会社 | 瞳孔検出用コンピュータプログラム、瞳孔検出装置及び瞳孔検出方法 |
| EP3430973B1 (en) * | 2017-07-19 | 2024-11-27 | Sony Group Corporation | Mobile system and method |
| CN108053444B (zh) * | 2018-01-02 | 2021-03-12 | 京东方科技集团股份有限公司 | 瞳孔定位方法及装置、设备和存储介质 |
| CN108498064B (zh) * | 2018-03-19 | 2021-06-18 | 中国人民解放军空军特色医学中心 | 数字化亮点闪烁检测系统 |
| CN108513074B (zh) * | 2018-04-13 | 2020-08-04 | 京东方科技集团股份有限公司 | 自拍控制方法及装置、电子设备 |
| TWI676821B (zh) * | 2018-12-11 | 2019-11-11 | 國立臺灣大學 | 適應性視線追蹤的校正方法 |
| CN110119457B (zh) * | 2019-05-17 | 2021-08-10 | 北京字节跳动网络技术有限公司 | 用于生成信息的方法和装置 |
| CN110929672B (zh) * | 2019-11-28 | 2024-03-01 | 联想(北京)有限公司 | 瞳孔定位方法和电子设备 |
| CN111209881A (zh) * | 2020-01-13 | 2020-05-29 | 深圳市雄帝科技股份有限公司 | 一种在图像中检测眼睛状态的方法及其系统 |
| CN112464829B (zh) * | 2020-12-01 | 2024-04-09 | 中航航空电子有限公司 | 一种瞳孔定位方法、设备、存储介质及视线追踪系统 |
| CN113011393B (zh) * | 2021-04-25 | 2022-06-03 | 中国民用航空飞行学院 | 基于改进混合投影函数的人眼定位方法 |
| CN114845005A (zh) * | 2022-03-31 | 2022-08-02 | 北京航天控制仪器研究所 | 一种智能图像跟踪压缩存储器 |
| CN115565224A (zh) * | 2022-09-29 | 2023-01-03 | 珠海视熙科技有限公司 | 一种实时连续定位瞳孔中心的方法、装置、介质及设备 |
| CN118799359A (zh) * | 2024-07-01 | 2024-10-18 | 成都集思鸣智科技有限公司 | 眼动追踪方法、装置、系统及存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1686051A (zh) * | 2005-05-08 | 2005-10-26 | 上海交通大学 | 基于vpf和改进的susan的眼角和瞳孔的定位方法 |
| CN101201893A (zh) * | 2006-09-30 | 2008-06-18 | 电子科技大学中山学院 | 一种基于灰度信息的虹膜识别预处理方法 |
| CN103885589A (zh) * | 2014-03-06 | 2014-06-25 | 华为技术有限公司 | 眼动追踪方法及装置 |
| CN105930762A (zh) * | 2015-12-02 | 2016-09-07 | 中国银联股份有限公司 | 一种眼球跟踪的方法及装置 |
Family Cites Families (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1357831A2 (en) * | 2001-02-09 | 2003-11-05 | Sensomotoric Instruments GmbH | Multidimensional eye tracking and position measurement system |
| US7593550B2 (en) * | 2005-01-26 | 2009-09-22 | Honeywell International Inc. | Distance iris recognition |
| KR20050025927A (ko) * | 2003-09-08 | 2005-03-14 | 유웅덕 | 홍채인식을 위한 동공 검출 방법 및 형상기술자 추출방법과 그를 이용한 홍채 특징 추출 장치 및 그 방법과홍채인식 시스템 및 그 방법 |
| GB0603411D0 (en) * | 2006-02-21 | 2006-03-29 | Xvista Ltd | Method of processing an image of an eye |
| US7682026B2 (en) | 2006-08-22 | 2010-03-23 | Southwest Research Institute | Eye location and gaze detection system and method |
| WO2008091401A2 (en) * | 2006-09-15 | 2008-07-31 | Retica Systems, Inc | Multimodal ocular biometric system and methods |
| US7970179B2 (en) * | 2006-09-25 | 2011-06-28 | Identix Incorporated | Iris data extraction |
| US8023699B2 (en) * | 2007-03-09 | 2011-09-20 | Jiris Co., Ltd. | Iris recognition system, a method thereof, and an encryption system using the same |
| CN100452081C (zh) * | 2007-06-01 | 2009-01-14 | 华南理工大学 | 一种人眼定位及人眼状态识别方法 |
| TWI335544B (en) | 2007-07-31 | 2011-01-01 | Univ Nat Taiwan Science Tech | Iris recognition system |
| WO2010011785A1 (en) * | 2008-07-23 | 2010-01-28 | Indiana University Research & Technology Corporation | System and method for a non-cooperative iris image acquisition system |
| JP2010033305A (ja) * | 2008-07-29 | 2010-02-12 | Hitachi Ltd | 画像情報処理方法、及び装置 |
| US8317325B2 (en) * | 2008-10-31 | 2012-11-27 | Cross Match Technologies, Inc. | Apparatus and method for two eye imaging for iris identification |
| CN101615292B (zh) * | 2009-07-24 | 2011-11-16 | 云南大学 | 基于灰度信息的人眼精确定位方法 |
| CN101964111B (zh) * | 2010-09-27 | 2011-11-30 | 山东大学 | 基于超分辨率的视线跟踪精度提升方法 |
| CN102456137B (zh) * | 2010-10-20 | 2013-11-13 | 上海青研信息技术有限公司 | 基于近红外反射点特性的视线跟踪预处理方法 |
| TWI471808B (zh) * | 2012-07-20 | 2015-02-01 | Pixart Imaging Inc | 瞳孔偵測裝置 |
| CN104050448B (zh) | 2014-06-11 | 2017-10-17 | 青岛海信电器股份有限公司 | 一种人眼定位、人眼区域定位方法及装置 |
| CN104793741A (zh) * | 2015-04-03 | 2015-07-22 | 深圳市虚拟现实科技有限公司 | 带眼球跟踪虚拟现实成像系统和方法 |
| WO2018016837A1 (en) * | 2016-07-18 | 2018-01-25 | Samsung Electronics Co., Ltd. | Method and apparatus for iris recognition |
| KR102707594B1 (ko) * | 2016-11-11 | 2024-09-19 | 삼성전자주식회사 | 홍채 영역 추출 방법 및 장치 |
| US10521661B2 (en) * | 2017-09-01 | 2019-12-31 | Magic Leap, Inc. | Detailed eye shape model for robust biometric applications |
-
2015
- 2015-12-02 CN CN201510875607.9A patent/CN105930762A/zh active Pending
-
2016
- 2016-11-30 WO PCT/CN2016/108060 patent/WO2017092679A1/zh not_active Ceased
- 2016-11-30 EP EP16869989.0A patent/EP3385885A4/en not_active Withdrawn
- 2016-11-30 CA CA3025964A patent/CA3025964C/en active Active
- 2016-11-30 US US15/780,641 patent/US10699420B2/en active Active
- 2016-12-02 TW TW105140169A patent/TWI611353B/zh active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1686051A (zh) * | 2005-05-08 | 2005-10-26 | 上海交通大学 | 基于vpf和改进的susan的眼角和瞳孔的定位方法 |
| CN101201893A (zh) * | 2006-09-30 | 2008-06-18 | 电子科技大学中山学院 | 一种基于灰度信息的虹膜识别预处理方法 |
| CN103885589A (zh) * | 2014-03-06 | 2014-06-25 | 华为技术有限公司 | 眼动追踪方法及装置 |
| CN105930762A (zh) * | 2015-12-02 | 2016-09-07 | 中国银联股份有限公司 | 一种眼球跟踪的方法及装置 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3385885A4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CA3025964A1 (en) | 2017-06-08 |
| US10699420B2 (en) | 2020-06-30 |
| TWI611353B (zh) | 2018-01-11 |
| CA3025964C (en) | 2021-09-14 |
| CN105930762A (zh) | 2016-09-07 |
| US20180365844A1 (en) | 2018-12-20 |
| TW201721516A (zh) | 2017-06-16 |
| EP3385885A4 (en) | 2018-12-19 |
| EP3385885A1 (en) | 2018-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017092679A1 (zh) | 一种眼球跟踪的方法及装置、设备 | |
| CN107209849B (zh) | 眼睛跟踪 | |
| US10504008B1 (en) | System and method for relocalization and scene recognition | |
| US10395094B2 (en) | Method and apparatus for detecting glasses in a face image | |
| TW202011733A (zh) | 對影像進行目標取樣的方法及裝置 | |
| CN103907123B (zh) | 深度图像中的人的头部的检测 | |
| US11615643B2 (en) | Methods, systems, and media for evaluating images | |
| US10254831B2 (en) | System and method for detecting a gaze of a viewer | |
| US20140168367A1 (en) | Calibrating visual sensors using homography operators | |
| US9082000B2 (en) | Image processing device and image processing method | |
| US11386710B2 (en) | Eye state detection method, electronic device, detecting apparatus and computer readable storage medium | |
| US20190066311A1 (en) | Object tracking | |
| CN112307806A (zh) | 头部姿态检测装置和方法 | |
| WO2023249694A1 (en) | Object detection and tracking in extended reality devices | |
| CN111738085B (zh) | 实现自动驾驶同时定位与建图的系统构建方法及装置 | |
| US20170109569A1 (en) | Hybrid face recognition based on 3d data | |
| US10296802B2 (en) | Image processing device, image processing method, and computer program product | |
| CN107995442A (zh) | 视频数据的处理方法、装置及计算设备 | |
| US11741620B1 (en) | Plane detection using depth sensor and semantic information | |
| CN104156689B (zh) | 一种对目标对象的特征信息进行定位的方法和设备 | |
| US10013052B2 (en) | Electronic device, controlling method and storage medium | |
| US12067770B2 (en) | Image processing apparatus, image processing method, and storage medium for determining a number of persons in an input image | |
| CN111507139A (zh) | 图像效果生成方法、装置和电子设备 | |
| JP2013029996A (ja) | 画像処理装置 | |
| US12380730B2 (en) | Authentication device, authentication method, and computer readable storage medium |
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: 16869989 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2016869989 Country of ref document: EP |
|
| ENP | Entry into the national phase |
Ref document number: 2016869989 Country of ref document: EP Effective date: 20180702 |
|
| ENP | Entry into the national phase |
Ref document number: 3025964 Country of ref document: CA |