Method, apparatus, storage medium and electronic device for determining eye movement position

Abstract

The present application discloses a method, apparatus, storage medium and electronic device for determining an eye movement position, which relates to the field of artificial intelligence technology. The method includes: collecting multiple face images of a target object at different directions and different angles; determining the face feature information of each face image according to target feature information to obtain multiple face feature information, wherein the target feature information at least includes: feature information corresponding to the midline of the nose of each face, feature information corresponding to the alae nasi of each face, and feature information corresponding to the cheeks of each face; determining a target head movement model according to the multiple face feature information; and determining the eye movement position of both eyes of the target object according to the target head movement model. Through the present application, the problem of inaccurate detection accuracy of the eye movement position in the related art is solved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology. Specifically, it relates to a method, device, storage medium, and electronic device for determining eye movement positions. Background Art

[0002] Optimization of a camera gaze tracking system based on head pose analysis. During the process of implementing gaze tracking using a webcam, head pose analysis is introduced to optimize gaze tracking. In the prior art, the method of introducing head pose is: using the webcam video data stream to construct an algorithm for head pose features and calculating head pose similarity. This algorithm can effectively estimate the similarity of head poses between two frames in the video stream. However, a series of calibration operations need to be performed in advance, which affects the user experience and cannot collect eye movement information without the user's awareness, resulting in inaccurate accuracy of the detected eye movement positions.

[0003] Regarding the problem of inaccurate detection accuracy of eye movement positions in the related art, no effective solution has been proposed yet. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, storage medium, and electronic device for determining eye movement positions, so as to solve the problem of inaccurate detection accuracy of eye movement positions in the related art.

[0005] To achieve the above objective, according to one aspect of this application, a method for determining eye movement positions is provided. The method includes: collecting multiple face images of a target object in different directions and at different angles; determining the face feature information of each face image according to target feature information, obtaining multiple face feature information, where the target feature information at least includes: feature information corresponding to the midline of the nose of each face, feature information corresponding to the nasal wings of each face, and feature information corresponding to the cheeks of each face; determining a target head movement model according to the multiple face feature information; and determining the eye movement positions of the two eyes of the target object according to the target head movement model.

[0006] Further, determining the face feature information of each face image according to target feature information and obtaining multiple face feature information includes: identifying each face image according to a preset identifier to obtain the identified face image, where the identified face image at least includes: the orientation information of the face relative to a preset coordinate and the angle information of the face relative to the preset coordinate; and matching the identified face image with the target feature information to obtain the face feature information of each face image.

[0007] Further, determining a target head movement model according to the multiple face feature information includes: extracting facial feature data from the face feature information, where the facial features at least include feature data corresponding to the orientation information and feature data corresponding to the angle information; training an original head movement model with the facial feature data to obtain the target head movement model.

[0008] Further, before determining the eye movement positions of the target object's both eyes according to the target head movement model, the method further includes: connecting the coordinates where the imaging device is located to a preset position to obtain a target connection line, where the preset position is the central position between the both eyes of the target object; constructing a target angle according to the target connection line and the shooting direction of the imaging device, where the target angle is used to represent the angular offset of the target object's face relative to the preset coordinates.

[0009] Further, before determining the eye movement positions of the target object's both eyes according to the target head movement model, the method further includes: when the target orientation information corresponding to the target object's face is determined, calculating the eyeball feature information corresponding to the target object's face according to a target eye movement model.

[0010] Further, determining the eye movement positions of the target object's both eyes according to the target head movement model includes: determining the rotation angle of the target object's head based on the target head movement model; determining the eye movement positions according to the rotation angle of the head, the eyeball feature information, and the angular offset.

[0011] Further, determining the rotation angle of the target object's head based on the target head movement model includes: inputting the facial feature data into the target head movement model; calculating the rotation angle of the target object's head based on the target head movement model for the facial feature data.

[0012] To achieve the above object, according to another aspect of the present application, there is provided a device for determining eye movement positions. The device includes: an acquisition unit, configured to acquire multiple face images of a target object at different directions and different angles; a first determination unit, configured to determine face feature information of each face image according to target feature information to obtain multiple face feature information, where the target feature information at least includes: feature information corresponding to the midline of the nose of each face, feature information corresponding to the nasal wings of each face, and feature information corresponding to the cheeks of each face; a second determination unit, configured to determine a target head movement model according to the multiple face feature information; and a third determination unit, configured to determine the eye movement positions of the target object's both eyes according to the target head movement model.

[0013] Further, the first determination unit includes: an identification module, configured to identify each face image according to a preset identification to obtain an identified face image, where the identified face image at least includes: the orientation information of the face relative to a preset coordinate and the angle information of the face relative to the preset coordinate; a matching module, configured to match the identified face image with the target feature information to obtain the face feature information of each face image.

[0014] Further, the second determination unit includes: an extraction module, configured to extract the facial feature data from the face feature information, where the facial features at least include the feature data corresponding to the orientation information and the feature data corresponding to the angle information; a training module, configured to train an original head movement model with the facial feature data to obtain the target head movement model.

[0015] Further, the device further includes: a connection unit, configured to connect the coordinate where the imaging device is located to a preset position to obtain a target connection line before determining the eye movement positions of the target object's eyes according to the target head movement model, where the preset position is the central position between the eyes of the target object; a construction unit, configured to construct a target included angle according to the target connection line and the shooting direction of the imaging device, where the target included angle is used to represent the angle offset of the target object's face relative to the preset coordinate.

[0016] Further, the device further includes: a calculation unit, configured to calculate the eye ball feature information corresponding to the face of the target object according to a target eye movement model when the target orientation information corresponding to the face of the target object is determined before determining the eye movement positions of the target object's eyes according to the target head movement model.

[0017] Further, the third determination unit includes: a first determination module, configured to determine the rotation angle of the head of the target object based on the target head movement model; a second determination module, configured to determine the eye movement positions according to the rotation angle of the head, the eye ball feature information, and the angle offset.

[0018] Further, the first determination module includes: an input sub-module, configured to input the facial feature data into the target head movement model; a calculation sub-module, configured to calculate the facial feature data based on the target head movement model to obtain the rotation angle of the head of the target object.

[0019] Through the present application, the following steps are adopted: collecting multiple face images of a target object from different directions and angles; determining the face feature information of each face image according to the target feature information, so as to obtain multiple face feature information, wherein the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the nasal wings of each face, and the feature information corresponding to the cheeks of each face; determining a target head movement model according to the multiple face feature information; and determining the eye movement positions of the two eyes of the target object according to the target head movement model, thereby solving the problem of inaccurate detection accuracy of eye movement positions in the related art. By obtaining the eye movement positions of the two eyes of the target object through the determined target head movement model, the effect of improving the detection accuracy of eye movement positions is achieved. Description of the Drawings

[0020] The drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0021] Figure 1 is a flowchart of a method for determining eye movement positions according to an embodiment of this application;

[0022] Figure 2 is a schematic diagram of face feature points of a method for determining eye movement positions according to an embodiment of this application;

[0023] Figure 3 is a schematic diagram of generating a target head movement model of a method for determining eye movement positions according to an embodiment of this application;

[0024] Figure 4 is a schematic diagram of face offset of a method for determining eye movement positions according to an embodiment of this application;

[0025] Figure 5 is a schematic diagram of determining eye movement positions of a method for determining eye movement positions according to an embodiment of this application;

[0026] Figure 6 is a schematic diagram of a device for determining eye movement positions according to an embodiment of this application;

[0027] Figure 7 is a network architecture schematic diagram of an electronic device for determining eye movement positions according to an embodiment of this application. Detailed Embodiments

[0028] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the drawings and combine the embodiments to detail this application.

[0029] To enable those skilled in the art to better understand the solution of this application, the technical solution in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so as to describe the embodiments of this application here. In addition, the terms "include" and "have" and any of their deformations are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0031] It should be noted that the user information (including but not limited to the user's target device, user personal information, etc.) and data (including but not limited to the data for display, analysis data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0032] According to the embodiments of this application, a method for determining the eye movement position is provided.

[0033] Figure 1 is a flowchart of the method for determining the eye movement position according to the embodiments of this application. As Figure 1 shown, the method includes the following steps:

[0034] Step S101, collect multiple face images of the target object in different directions and at different angles.

[0035] It should be noted that the imaging device of this application can not only collect multiple face images, but also collect the RGB information in the face images.

[0036] Step S102, determine the face feature information of each face image according to the target feature information, and obtain multiple face feature information, where the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the wing of the nose of each face, and the feature information corresponding to the cheek of each face.

[0037] Specifically, after collecting multiple face images from different directions and angles, each face needs to be marked according to a preset identifier.

[0038] Optionally, in the method for determining the eye movement position provided in the embodiments of the present application, determining the face feature information of each face image according to the target feature information, and obtaining multiple face feature information includes: identifying each face image according to a preset identifier to obtain the identified face image, wherein the identified face image at least includes: the orientation information of the face relative to the preset coordinate, and the angle information of the face relative to the preset coordinate; matching the identified face image with the target feature information to obtain the face feature information of each face image.

[0039] For example, according to the marking criteria specified in Table 1, label each face image, mark the orientation and angle of each face to obtain the identified face image, and match the identified face image with Figure 2 the target feature information in to extract the face feature information of each face image. As shown in Figure 2 , selecting the 11-13 nasal midline feature points, 21-22 nasal wing edge feature points, and 31-32 cheek edge feature points as the features for calculating the head direction and angle can effectively improve the accuracy of the camera in calculating the eye movement position.

[0040] Table 1

[0041]

[0042] Step S103, determining the target head movement model according to the multiple face feature information.

[0043] Specifically, as shown in Figure 3 , determining the training data of the training model according to the facial feature data, and extracting facial feature points for model training. Using the feature points as input data and the marked points as the correct output data for algorithm model training until the model accuracy reaches the threshold, and then outputting the trained target head movement model.

[0044] Optionally, in the method for determining the eye movement position provided in the embodiments of the present application, determining the target head movement model according to the multiple face feature information includes: extracting the facial feature data in the face feature information, wherein the facial features at least include the feature data corresponding to the orientation information and the feature data corresponding to the angle information; training the original head movement model through the facial feature data to obtain the target head movement model.

[0045] Specifically, after marking the direction and angle of the corresponding face image, extracting the facial feature data, generating training data from the facial feature data, and training the algorithm of the original head movement model based on the training data to generate a target head movement model, the final effect of this model is that when inputting the face image collected by the camera, it can output the current orientation and angle of the face, for example: 15 degrees to the left, thereby effectively improving the accuracy of the camera's calculation of the eye movement position.

[0046] Step S104, determine the eye movement positions of the two eyes of the target object according to the target head movement model.

[0047] For example, before determining the eye movement positions of the two eyes of the target object according to the target head movement model, it is also necessary to calculate the face offset of the current target object.

[0048] Optionally, in the method for determining the eye movement position provided in the embodiments of the present application, before determining the eye movement positions of the two eyes of the target object according to the target head movement model, the method further includes: connecting the coordinates where the camera device is located to a preset position to obtain a target connection line, where the preset position is the central position between the two eyes of the target object; constructing a target angle according to the target connection line and the shooting direction of the camera device, where the target angle is used to represent the angular offset of the face of the target object relative to the preset coordinate.

[0049] Specifically, an example of the face offset is Figure 4 as shown. Calculate the offset of the current face according to the position of the center of the two eyes. For example: when the current subject is at a position to the left of the camera, the target angle formed by the connection line between the center of the two eyes and the camera and the shooting direction of the camera is 10 degrees, that is, the angular offset of the face of the target object relative to the preset coordinate is 10 degrees. By calculating the face offset, the accuracy of the camera's calculation of the eye movement position is effectively improved.

[0050] Optionally, in the method for determining the eye movement position provided in the embodiments of the present application, before determining the eye movement positions of the two eyes of the target object according to the target head movement model, the method further includes: when the target orientation information corresponding to the face of the target object is determined, calculating the eyeball feature information corresponding to the face of the target object according to the target eye movement model.

[0051] Specifically, calculate the eyeball feature information corresponding to the face of the target object through the target eye movement model, so as to accurately determine the eye movement positions of the two eyes of the target object subsequently.

[0052] Optionally, in the method for determining the eye movement position provided in the embodiments of the present application, determining the eye movement positions of both eyes of the target object according to the target head movement model includes: determining the rotation angle of the head of the target object based on the target head movement model; determining the eye movement positions according to the rotation angle of the head, the eyeball feature information, and the angle offset.

[0053] Specifically, as Figure 5 shown, by comprehensively calculating the angle calculated by the eye movement model according to the eyeball feature information, the rotation angle of the head of the target object determined by the target head movement model, and the face offset angle, the position of the current line of sight is finally generated, making the eye movement positions of both eyes of the target object in the present application more accurate.

[0054] Specifically, determining the rotation angle of the head of the target object based on the target head movement model includes: inputting the facial feature data into the target head movement model; calculating the facial feature data based on the target head movement model to obtain the rotation angle of the head of the target object. By obtaining the rotation angle of the head, the accuracy of calculating the eye movement position is improved.

[0055] In the method for determining the eye movement position provided in the embodiments of the present application, by collecting multiple face images of the target object in different directions and at different angles; determining the facial feature information of each face image according to the target feature information to obtain multiple facial feature information, where the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the nasal wings of each face, and the feature information corresponding to the cheeks of each face; determining the target head movement model according to the multiple facial feature information; and determining the eye movement positions of both eyes of the target object according to the target head movement model, the problem that the detection accuracy of the eye movement position in the related art is not accurate enough is solved. By obtaining the eye movement positions of both eyes of the target object through the determined target head movement model, the effect of improving the detection accuracy of the eye movement position is achieved.

[0056] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0057] The embodiments of the present application further provide a device for determining the eye movement position. It should be noted that the device for determining the eye movement position in the embodiments of the present application can be used to execute the method for determining the eye movement position provided in the embodiments of the present application. The following introduces the device for determining the eye movement position provided in the embodiments of the present application.

[0058] Figure 6Schematic diagram of a device for determining eye movement position according to an embodiment of the present application. As Figure 6 shown, the device includes: an acquisition unit 601, a first determination unit 602, a second determination unit 603, and a third determination unit 604.

[0059] Specifically, the acquisition unit 601 is configured to acquire multiple face images of a target object in different directions and at different angles;

[0060] The first determination unit 602 is configured to determine the face feature information of each face image according to the target feature information, and obtain multiple face feature information, where the target feature information at least includes: feature information corresponding to the midline of the nose of each face, feature information corresponding to the nasal wings of each face, and feature information corresponding to the cheeks of each face;

[0061] The second determination unit 603 is configured to determine a target head movement model according to the multiple face feature information;

[0062] The third determination unit 604 is configured to determine the eye movement positions of the two eyes of the target object according to the target head movement model.

[0063] In summary, the device for determining eye movement position provided by the embodiment of the present application acquires multiple face images of a target object in different directions and at different angles through the acquisition unit 601; the first determination unit 602 determines the face feature information of each face image according to the target feature information, and obtains multiple face feature information, where the target feature information at least includes: feature information corresponding to the midline of the nose of each face, feature information corresponding to the nasal wings of each face, and feature information corresponding to the cheeks of each face; the second determination unit 603 determines a target head movement model according to the multiple face feature information; the third determination unit 604 determines the eye movement positions of the two eyes of the target object according to the target head movement model, and solves the problem that the detection accuracy of the eye movement position in the related art is not accurate enough. The eye movement positions of the two eyes of the target object are obtained through the determined target head movement model, thereby achieving the effect of improving the detection accuracy of the eye movement position.

[0064] Further, the first determination unit includes: an identification module, configured to identify each face image according to a preset identification, and obtain the identified face image, where the identified face image at least includes: the orientation information of the face relative to the preset coordinate and the angle information of the face relative to the preset coordinate; a matching module, configured to match the identified face image with the target feature information to obtain the face feature information of each face image.

[0065] Further, the second determination unit includes: an extraction module, configured to extract facial feature data from the facial feature information, where the facial features at least include feature data corresponding to the orientation information and feature data corresponding to the angle information; a training module, configured to train an original head movement model with the facial feature data to obtain the target head movement model.

[0066] Further, the apparatus further includes: a connection unit, configured to connect the coordinates where the camera device is located with a preset position to obtain a target connection line before determining the eye movement positions of the target object's both eyes according to the target head movement model, where the preset position is the central position between the both eyes of the target object; a construction unit, configured to construct a target angle according to the target connection line and the shooting direction of the camera device, where the target angle is used to represent the angular offset of the target object's face relative to the preset coordinate.

[0067] Further, the apparatus further includes: a calculation unit, configured to calculate the eyeball feature information corresponding to the target object's face according to a target eye movement model in the case where the target orientation information corresponding to the target object's face is determined before determining the eye movement positions of the target object's both eyes according to the target head movement model.

[0068] Further, the third determination unit includes: a first determination module, configured to determine the rotation angle of the target object's head based on the target head movement model; a second determination module, configured to determine the eye movement positions according to the rotation angle of the head, the eyeball feature information, and the angular offset.

[0069] Further, the first determination module includes: an input sub-module, configured to input the facial feature data into the target head movement model; a calculation sub-module, configured to calculate the facial feature data based on the target head movement model to obtain the rotation angle of the target object's head.

[0070] The apparatus for determining the eye movement positions includes a processor and a memory. The above-mentioned acquisition unit 601, first determination unit 602, second determination unit 603, third determination unit 604, etc. are all stored in the memory as program units, and the corresponding functions are implemented by the processor executing the above program units stored in the memory.

[0071] The processor includes a kernel, and the kernel retrieves the corresponding program units from the memory. One or more kernels can be set, and the eye movement positions are determined by adjusting the kernel parameters.

[0072] The memory may include non-permanent memory in the form of computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0073] An embodiment of the present invention provides a storage medium with a program stored thereon, and when the program is executed by a processor, the method for determining the eye movement position is implemented.

[0074] An embodiment of the present invention provides a processor for running a program, and when the program runs, the method for determining the eye movement position is executed.

[0075] As Figure 7 shown, an embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: collecting multiple face images of a target object at different directions and different angles; determining the face feature information of each face image according to the target feature information, and obtaining multiple face feature information, where the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the alae nasi of each face, and the feature information corresponding to the cheeks of each face; determining a target head movement model according to the multiple face feature information; and determining the eye movement position of the two eyes of the target object according to the target head movement model.

[0076] When the processor executes the program, the following steps are also implemented: identifying each face image according to a preset identifier to obtain the identified face image, where the identified face image at least includes: the orientation information of the face relative to the preset coordinate and the angle information of the face relative to the preset coordinate; and matching the identified face image with the target feature information to obtain the face feature information of each face image.

[0077] When the processor executes the program, the following steps are also implemented: extracting the facial feature data from the face feature information, where the facial features at least include the feature data corresponding to the orientation information and the feature data corresponding to the angle information; and training the original head movement model through the facial feature data to obtain the target head movement model.

[0078] When the processor executes the program, the following steps are also implemented: Before determining the eye movement positions of the two eyes of the target object according to the target head movement model, connect the coordinates where the imaging device is located with a preset position to obtain a target connection line, where the preset position is the central position between the two eyes of the target object; construct a target angle according to the target connection line and the shooting direction of the imaging device, where the target angle is used to represent the angular offset of the face of the target object relative to the preset coordinates.

[0079] When the processor executes the program, the following steps are also implemented: Before determining the eye movement positions of the two eyes of the target object according to the target head movement model, when the target orientation information corresponding to the face of the target object is determined, calculate the eyeball feature information corresponding to the face of the target object according to the target eye movement model.

[0080] When the processor executes the program, the following steps are also implemented: Determine the rotation angle of the head of the target object based on the target head movement model; determine the eye movement positions according to the rotation angle of the head, the eyeball feature information, and the angular offset.

[0081] When the processor executes the program, the following steps are also implemented: Input the facial feature data into the target head movement model; perform calculations on the facial feature data based on the target head movement model to obtain the rotation angle of the head of the target object.

[0082] The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0083] This application also provides a computer program product, which when executed on a data processing device is adapted to execute a program initialized with the following method steps: Collect multiple face images of a target object at different directions and different angles; determine the facial feature information of each face image according to the target feature information to obtain multiple facial feature information, where the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the nasal wings of each face, the feature information corresponding to the cheeks of each face; determine a target head movement model according to the multiple facial feature information; determine the eye movement positions of the two eyes of the target object according to the target head movement model.

[0084] When executed on a data processing device, it is also adapted to execute a program initialized with the following method steps: Identify each face image according to a preset identifier to obtain the identified face image, where the identified face image at least includes: the orientation information of the face relative to the preset coordinates, the angular information of the face relative to the preset coordinates; match the identified face image with the target feature information to obtain the facial feature information of each face image.

[0085] When executed on a data processing device, it is also adapted to execute a program initialized with the following method steps: extracting facial feature data from the facial feature information, where the facial features at least include the feature data corresponding to the orientation information and the feature data corresponding to the angle information; training an original head movement model with the facial feature data to obtain the target head movement model.

[0086] When executed on a data processing device, it is also adapted to execute a program initialized with the following method steps: before determining the eye movement positions of the target object's two eyes according to the target head movement model, connecting the coordinates where the camera device is located to a preset position to obtain a target connection line, where the preset position is the central position between the two eyes of the target object; constructing a target angle according to the target connection line and the shooting direction of the camera device, where the target angle is used to represent the angular offset of the target object's face relative to the preset coordinates.

[0087] When executed on a data processing device, it is also adapted to execute a program initialized with the following method steps: before determining the eye movement positions of the target object's two eyes according to the target head movement model, calculating the eyeball feature information corresponding to the target object's face according to a target eye movement model under the condition that the target orientation information corresponding to the target object's face is determined.

[0088] When executed on a data processing device, it is also adapted to execute a program initialized with the following method steps: determining the rotation angle of the target object's head based on the target head movement model; determining the eye movement positions according to the rotation angle of the head, the eyeball feature information, and the angular offset.

[0089] When executed on a data processing device, it is also adapted to execute a program initialized with the following method steps: inputting the facial feature data into the target head movement model; calculating the facial feature data based on the target head movement model to obtain the rotation angle of the target object's head.

[0090] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, as well as the combination of flows and / or blocks in the flowchart and / or block diagram. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a means for implementing the specified functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 or a means for implementing the functions specified in multiple blocks.

[0092] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the specified functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in the process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0094] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0095] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0096] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0097] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0099] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining eye movement position, characterized in that, Including: Collecting multiple face images of a target object from different directions and angles; Determining the face feature information of each face image according to the target feature information, obtaining multiple face feature information, wherein the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the nasal wings of each face, and the feature information corresponding to the cheeks of each face; Determining a target head movement model according to the multiple face feature information; Determining the eye movement positions of the two eyes of the target object according to the target head movement model, wherein the rotation angle of the head of the target object is determined based on the target head movement model; the eye movement positions are determined according to the rotation angle of the head, the eyeball feature information, and the angle offset; the angle offset is a face offset, and according to the position of the center of the two eyes, the current face offset is calculated, and the output result of the target head movement model, the result calculated by the face offset, and the eyeball feature information of the target eye movement model are input into the line-of-sight positioning model to obtain the eye movement positions of the two eyes of the target object.

2. The method according to claim 1, wherein Determining the face feature information of each face image according to the target feature information, obtaining multiple face feature information includes: Identifying each face image according to a preset identifier to obtain the identified face image, wherein the identified face image at least includes: the orientation information of the face relative to the preset coordinates, and the angle information of the face relative to the preset coordinates; Matching the identified face image with the target feature information to obtain the face feature information of each face image.

3. The method according to claim 2, wherein Determining a target head movement model according to the multiple face feature information includes: Extracting the facial feature data in the face feature information, wherein the facial feature data at least includes the feature data corresponding to the orientation information and the feature data corresponding to the angle information; Training the original head movement model through the facial feature data to obtain the target head movement model.

4. The method according to claim 3, wherein Before determining the eye movement positions of the two eyes of the target object according to the target head movement model, the method further includes: Connecting the coordinates where the imaging device is located with a preset position to obtain a target connection line, wherein the preset position is the central position between the two eyes of the target object; Constructing a target angle according to the target connection line and the shooting direction of the imaging device, wherein the target angle is used to represent the angle offset of the face of the target object relative to the preset coordinates.

5. The method according to claim 4, wherein Before determining the eye movement positions of the two eyes of the target object according to the target head movement model, the method further includes: Calculating the eyeball feature information corresponding to the face of the target object according to a target eye movement model when the target orientation information corresponding to the face of the target object is determined.

6. The method according to claim 5, wherein Determining the rotation angle of the head of the target object based on the target head movement model includes: Inputting the facial feature data into the target head movement model; Calculating the facial feature data based on the target head movement model to obtain the rotation angle of the head of the target object.

7. An eye movement position determination device, characterized in that Including: A collecting unit for collecting multiple face images of a target object from different directions and angles; A first determination unit, configured to determine the face feature information of each face image according to the target feature information, so as to obtain multiple face feature information, where the target feature information at least includes: the feature information corresponding to the midline of the nose of each face, the feature information corresponding to the alae nasi of each face, and the feature information corresponding to the cheeks of each face; A second determination unit, configured to determine a target head movement model according to the multiple face feature information; A third determination unit, configured to determine the eye movement positions of the two eyes of the target object according to the target head movement model, where the rotation angle of the head of the target object is determined based on the target head movement model; the eye movement positions are determined according to the rotation angle of the head, the eyeball feature information, and the angle offset; the angle offset is a face offset, and according to the positions of the centers of the two eyes, the current face offset is calculated, and the output result of the target head movement model, the result calculated from the face offset, and the eyeball feature information of the target eye movement model are input into a line-of-sight positioning model to obtain the eye movement positions of the two eyes of the target object.

8. A computer-readable storage medium, characterized in that, The storage medium includes a stored program, where the program, when executed by a processor, implements the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, Comprising one or more processors and a memory, the memory is used to store one or more programs, where when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

Images