Parameter adjusting method and device and 3D display equipment

Abstract

The invention provides a parameter adjustment method and device and 3D display equipment, and relates to the 3D display technology, and the method comprises the steps: obtaining a face image of a user through a camera; according to the face image, determining a first distance between a left eye pupil and a right eye pupil of the user in the face image and a first face geometric parameter of the user; determining an actual second face geometric parameter of the user, wherein the first face set parameter and the second face geometric parameter are used for indicating the same reference feature of the face of the user; determining a second distance between the user and the camera according to the first face geometric parameter, the second face geometric parameter and the focal length of the camera; determining the interpupillary distance of the user according to the first distance, the second distance and the focal length of the camera; and according to the interpupillary distance, adjusting an imaging parameter of the 3D display equipment so as to enable the imaging parameter to be matched with the interpupillary distance. Based on the scheme, the pupil distance of the current user can be accurately obtained and the imaging parameters can be adaptively adjusted, so that the viewing experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of 3D display technology, and more specifically, to methods, apparatus and 3D display devices for parameter adjustment. Background Technology

[0002] 3D display technology creates a sense of depth by presenting images with parallax to the left and right eyes separately and then fusing the images together. To achieve comfortable viewing, the imaging parameters of a 3D display device, such as the optical center distance, need to match the user's (viewer's) physiological interpupillary distance; otherwise, ghosting, depth distortion, or even dizziness may occur.

[0003] Currently, 3D display devices typically default to a fixed interpupillary distance (IPD) for the user (e.g., 65mm). The initial imaging parameters are set based on this fixed value, and after the image is displayed to the user, the user is allowed to manually fine-tune the imaging parameters based on their subjective feelings. Moreover, when other users use the device after the current user has finished using it, the aforementioned complete imaging parameter calibration process still needs to be repeated because the IPD of different users is different.

[0004] Therefore, how to accurately obtain the current interpupillary distance of a user when using a 3D display device and adaptively adjust the imaging parameters to avoid the need for manual fine-tuning by the user is an urgent problem to be solved. Summary of the Invention This application provides a method, apparatus, and 3D display device for parameter adjustment, which can accurately obtain the current user's interpupillary distance and adaptively adjust the imaging parameters to avoid manual fine-tuning by the user, thereby improving the user's viewing experience.

[0005] In a first aspect, a method for parameter adjustment is provided, the method comprising: acquiring a user's facial image via a camera; determining, based on the facial image, a first distance between the user's left and right pupils in the facial image and a first facial geometric parameter of the user; determining the user's actual second facial geometric parameter, wherein the first facial geometric parameter and the second facial geometric parameter are used to indicate the same reference feature of the user's face; determining a second distance between the user and the camera based on the first facial geometric parameter, the second facial geometric parameter, and the focal length of the camera; determining the user's interpupillary distance based on the first distance, the second distance, and the focal length of the camera; and adjusting the imaging parameters of a 3D display device according to the interpupillary distance to match the imaging parameters with the interpupillary distance.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, the camera is mounted on a 3D display device and is a monocular camera, and the imaging parameters include the optical center distance of the 3D display device and the virtual camera baseline.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the first pixel coordinates of the user's left pupil in the face image and the second pixel coordinates of the user's right pupil in the face image are determined based on the face image; and a first distance is determined based on the first pixel coordinates and the second pixel coordinates.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the leftmost third pixel coordinate and the rightmost fourth pixel coordinate of the user's facial outline are determined based on the facial image; and a first facial geometric parameter is determined based on the third pixel coordinate and the fourth pixel coordinate, the first facial geometric parameter being used to indicate the width of the user's face in the facial image.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, multiple facial key points of the user are determined based on the facial image; facial feature parameters related to reference features are determined based on the multiple facial key points; the facial feature parameters are input into a trained regression model to determine second facial geometric parameters. The regression model is established based on calibration samples, which include the mapping relationship between multiple sets of facial feature parameters and actual facial geometric parameters.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, multiple sets of facial feature parameters determined based on multiple frames of facial images of the user are input into the regression model, so that the regression model outputs multiple third facial geometric parameters; the multiple third facial geometric parameters are weighted and averaged to determine the second facial geometric parameter; or, the median of the multiple third facial geometric parameters is determined as the second facial geometric parameter.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the face image is determined to be obtained based on a single viewpoint before determining the first distance between the user's left and right pupils in the face image and the user's first facial geometric parameters based on the face image.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the aforementioned user includes a first user, the aforementioned imaging parameters include a first imaging parameter, the first imaging parameter being matched with a first interpupillary distance of the first user, and a first facial identification feature of the first user is determined based on the facial image of the first user, the first facial identification feature including facial features used to uniquely identify the first user; a first association relationship is established between the first facial identification feature and the first imaging parameter, the first association relationship being used to adjust the imaging parameters of the 3D display device to the first imaging parameter when the first facial identification feature is acquired again.

[0013] In a second aspect, a 3D display device is provided, including a monocular camera and a controller, wherein the monocular camera is used to acquire an image of a user's face, and the controller is used to execute a method as described in any possible implementation of the method design in the first aspect above.

[0014] Thirdly, a parameter adjustment apparatus is provided, comprising a module or unit for performing a method in any possible implementation of the method design described in the first aspect above.

[0015] Fourthly, a parameter adjustment device is provided, comprising a processor and a memory, wherein the processor and the memory are connected, wherein the memory is used to store program code, and the processor is used to call the program code to execute the method in any possible implementation of the method design of the first aspect above.

[0016] Fifthly, a computer-readable storage medium is provided storing a computer program that is executed by a processor to implement the method in any possible implementation of the method design of the first aspect.

[0017] In a sixth aspect, a computer program product is provided, including instructions that, when executed by a processor, cause a computer to perform any possible implementation of the method design of the first aspect described above.

[0018] Based on the above technical solution, even facial images acquired through a monocular camera can obtain the user's actual interpupillary distance and adaptively adjust the imaging parameters of the 3D display device. This eliminates the need for the user to manually fine-tune the device's imaging parameters based on subjective feelings, thereby simplifying the user's operation of the 3D display device and improving the user's viewing experience. Attached Figure Description

[0019] Figure 1 This is a schematic diagram illustrating the principle of glasses-free 3D technology. Figure 2 This is a schematic diagram illustrating the principle of light refraction based on a cylindrical lens; Figure 3 This is a flowchart illustrating a parameter adjustment method 300 proposed in an embodiment of this application; Figure 4 This is a flowchart illustrating a method 400 for determining the geometric parameters of a second face according to an embodiment of this application. Figure 5 This is a flowchart illustrating a method 500 for determining interpupillary distance using a binocular camera, as proposed in an embodiment of this application. Figure 6 This is a business process diagram for adjusting the imaging parameters of a 3D display device according to an embodiment of this application; Figure 7This is a schematic block diagram of a parameter adjustment device 700 provided in an embodiment of this application. Detailed Implementation

[0020] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0021] This application will present various aspects, embodiments, or features relating to a system comprising multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches are also possible. Furthermore, in the embodiments of this application, the words "exemplary," "for example," etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" in the embodiments of this application should not be construed as being better or more advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplary" is intended to present the concept in a concrete manner. The business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0022] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0023] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0024] 3D display technology, also known as glasses-free 3D technology, is a cutting-edge display technology that achieves stereoscopic visual effects without the need for special glasses. This technology primarily utilizes the parallax characteristic of human binoculars. When a person's two eyes observe an object, the image information received differs due to the different positions of the eyes. The brain processes this difference to generate a sense of depth. Glasses-free 3D technology simulates this binocular parallax by precisely projecting the corresponding pixels for each eye onto the viewer's left and right eyes respectively, thus creating a three-dimensional visual image. Based on this technology, users can obtain stereoscopic images from the display panel without the need for other optical devices (such as optical glasses).

[0025] The core principle of naked-eye 3D technology is to separate the images for the left and right eyes using techniques such as visual light barriers, lenticular lens technology, or directional light source technology, thereby creating three-dimensional perception through binocular parallax. Specifically, visual light barrier technology uses a liquid crystal layer to block light, allowing the left and right eyes to receive different images. Lenticular lens technology uses microlens arrays to refract light, achieving multi-angle stereoscopic display. Directional light source technology can precisely control the direction of light, enhancing the stereoscopic effect.

[0026] Figure 1 This is a schematic diagram illustrating the principle of glasses-free 3D technology.

[0027] refer to Figure 1 As shown, glasses-free 3D works by combining hardware beam splitting (e.g., grating-based hardware beam splitting) with software algorithms. It splits the light according to the coded data distribution, controlling the projection of light used to display the image onto different positions, thus allowing the corresponding image portion to enter the target user's left and right eyes. The image received by the left eye is called the left-eye image (or left view), and the image received by the right eye is called the right-eye image (or right view). The implementation paths of glasses-free 3D technology can be divided into three categories: light barrier technology, lenticular lens technology, and directional light source technology.

[0028] Parallax barrier technology is a common method in glasses-free 3D technology. By placing a barrier with a specific pattern in front of the display screen—a parallax barrier—this barrier allows images viewed from different angles to be separated, ensuring that the left and right eyes see different images. When these images are fused by the brain, a 3D effect is produced. The key to parallax barrier technology lies in the design of the barrier pattern, which is typically composed of a series of tiny stripes or grids. The arrangement of these stripes or grids determines the image separation effect. When the user is standing in a designated viewing position, the left and right eyes see different images separated by the barrier pattern, thus creating a stereoscopic effect. However, parallax barrier technology also has some limitations. First, the viewing angle is limited; if the user's position or angle deviates from the optimal viewing area, ghosting or image distortion may occur. Second, the presence of the barrier pattern may affect screen brightness. Furthermore, the cost of parallax barrier technology is relatively high, limiting its application in certain fields.

[0029] Lens technology is another common glasses-free 3D technology. Figure 2 This is a schematic diagram illustrating the principle of light refraction based on a cylindrical lens.

[0030] refer to Figure 2 As shown, lenticular lens technology uses a series of tiny lenses covering the display screen. Each lens focuses a different portion of the image onto the user's left or right eye, allowing them to see a 3D effect without glasses. The key to lenticular lens technology lies in the arrangement and focal length of the lenses, as well as the design of the display's left and right eye image alignment (also known as the alignment cycle). By adjusting the lens arrangement, focal length, and alignment cycle, the naked-eye 3D effect can be improved. Compared to light barrier technology, lenticular lens technology offers a wider viewing angle, allowing users to see a clear 3D effect over a greater range.

[0031] Pointed backlighting technology refers to adding a directional backlight layer, combined with a fast-response liquid crystal display (LCD) panel and driving method, to allow 3D content to enter the user's left and right eyes in a sequential manner, creating parallax. This technology offers high brightness and supports lossless switching, but the devices are thicker and more expensive, and it is mostly used in specific scenarios.

[0032] In addition, naked-eye 3D technology also involves image mapping technology and interlacing technology.

[0033] Parallax technology arranges different images or perspectives on the display screen, allowing the left and right eyes to see different images. Taking the aforementioned parallax barrier technology as an example, a parallax barrier is placed in front of the screen to block some light. Correspondingly, the image on the screen is divided into multiple pixels or pixel groups, each corresponding to a specific perspective. The slits or openings of the parallax barrier are precisely designed to ensure that each eye only sees its corresponding pixel or pixel group. Because the image on the screen is divided through slits, the left and right eyes see different parts of the image, thus creating a sense of depth.

[0034] Taking the aforementioned lenticular lens technology as an example, this technology involves covering the screen with a cylindrical lens to divide the image into sub-images at different angles. Correspondingly, the image is segmented into multiple sub-images on the screen, each corresponding to a specific viewing angle. The cylindrical lens refracts each sub-image in different directions, ensuring that the left and right eyes can see their corresponding sub-images. Because the image pixels under each lens are divided into multiple sub-pixels and refracted in different directions through the lens, the left and right eyes see different combinations of sub-pixels through the lens, thus creating a sense of depth.

[0035] The interlacing technique in glasses-free 3D refers to a specific display technology used to alternately display images for the left and right eyes on glasses-free 3D display devices. This allows the brain to synthesize the images seen by the left and right eyes into a stereoscopic image with a sense of depth without the need for 3D glasses. This technology utilizes the persistence of vision effect, which means that when images are switched rapidly in a sufficiently short period of time, the human eye will combine multiple images into a continuous picture.

[0036] In glasses-free 3D interleaving technology, because the left and right eye images need to be displayed simultaneously, the resolution of each eye image is typically half the total resolution of the display. Furthermore, to ensure smooth switching between the left and right eye images and eliminate flicker, glasses-free 3D interleaving technology requires a refresh rate of at least 120Hz. This allows each eye to see a 60Hz image, maintaining image smoothness. Glasses-free 3D interleaving technology can employ different alternation methods, such as vertical alternation or horizontal alternation. This method determines the display order of the left and right eye images and the viewer's viewing experience.

[0037] As naked-eye 3D technology matures and becomes more widespread, its application areas will continue to expand. In addition to advertising, entertainment, and education, naked-eye 3D technology will gradually be applied to emerging fields such as smart homes, virtual reality (VR), and augmented reality (AR).

[0038] However, regardless of the technology used to achieve glasses-free 3D display, to ensure users (viewers) can see clear and well-defined 3D images for comfortable viewing, a prerequisite must be met: the imaging parameters of the 3D display device must match the user's inter-pupillary distance (IPD). These imaging parameters include the optical center distance (OCD) and the virtual camera baseline. If the imaging parameters do not match the user's IPD, ghosting, depth distortion, and even dizziness may occur.

[0039] Interpupillary distance (IPD) refers to the physiological distance between the pupils of a person's two eyes, such as the projection distance between the center of the right pupil and the center of the left pupil on the Frankfurt plane (approximately a horizontal plane). For example, the IPD of an adult is usually in the range of [54mm, 74mm]. It can be seen that IPD is an unchangeable physiological parameter that varies from person to person.

[0040] Optical center distance refers to the physical optical axis distance between the left and right lenses or gratings of a 3D display device. This distance can be adjusted by motor drive to match the user's interpupillary distance.

[0041] The virtual camera baseline refers to two virtual cameras created in the 3D scene coordinate system during the rendering stage of the graphics pipeline within a 3D display device. These virtual cameras are located on the left and right sides of the overall space. The entrance pupil distance between these two virtual cameras is a software parameter, usually set to the current user's interpupillary distance. Based on this, the two virtual cameras can render left and right disparity maps separately, which are then merged and output to the screen. This ensures that the pixel disparity on the screen is consistent with the user's interpupillary distance, allowing the user to obtain a clear and stereoscopic image.

[0042] However, at present, 3D display devices usually default to a fixed value for the user's interpupillary distance (e.g., 65mm). The initial imaging parameters are set based on this fixed value. After the image is displayed to the user, the user needs to manually fine-tune the imaging parameters of the device based on their subjective feelings so that the user can obtain a clear and stereoscopic image.

[0043] Furthermore, since the interpupillary distance varies among different users, when other users use the 3D display device after the current user has finished using it, directly reusing the imaging parameters of the 3D display device adjusted by the previous user usually cannot guarantee that the current user can obtain a clear and stereoscopic image. Therefore, the current user still needs to re-execute the aforementioned complete imaging parameter calibration process.

[0044] The aforementioned problems make the use of 3D display devices cumbersome, thus reducing the user's viewing experience.

[0045] In view of this, embodiments of this application propose a method, apparatus, and 3D display device for parameter adjustment, which can accurately obtain the current user's interpupillary distance and adaptively adjust the imaging parameters to avoid manual fine-tuning by the user, thereby improving the user's viewing experience.

[0046] Figure 3 This is a flowchart illustrating a parameter adjustment method 300 proposed in an embodiment of this application.

[0047] In this method 300, the object whose parameters are adjusted can be a 3D display device, which may include a naked-eye 3D display screen (including grating type, lens type or directional backlight type), a stereoscopic projection system (based on dual-machine polarization or time-division projection), etc.

[0048] S310: Captures the user's facial image via camera.

[0049] In some possible embodiments, a user's facial image refers to an image that includes at least the complete facial area of ​​the user, which may include key parts such as the user's forehead, eyes, nose, mouth, and chin, and may even include hair, ears, neck, etc.

[0050] In some possible embodiments, the camera described above can be a monocular camera or a binocular camera; however, this embodiment focuses on a scheme for determining the user's interpupillary distance based on facial images acquired by a monocular camera. Therefore, when the camera is a monocular camera, the following operations can be performed.

[0051] S320: Based on the face image, determine a first distance between the user's left and right pupils in the face image and the user's first facial geometric parameters.

[0052] Since facial images are composed of pixels, and the position of each pixel can be represented by pixel coordinates, the difference between the horizontal coordinates of two pixel coordinates refers to the number of pixels between the two points along the x-axis of the coordinate system, and the difference between the vertical coordinates of two pixel coordinates refers to the number of pixels between the two points along the y-axis of the coordinate system. In a facial image, the user's left and right pupils can be abstracted as two specific pixels in the facial image. Therefore, the aforementioned first distance can be obtained through the pixel coordinates corresponding to these two pixels.

[0053] In some possible embodiments, the first pixel coordinates of the user's left pupil in the face image and the second pixel coordinates of the user's right pupil in the face image can be determined based on the face image; then, a first distance can be determined based on the first pixel coordinates and the second pixel coordinates.

[0054] For example, the first distance can be used to represent the straight-line distance from the center of the user's left pupil to the center of the right pupil. The first pixel coordinate can be used to indicate the position of the left pupil's center, and the second pixel coordinate can be used to indicate the position of the right pupil's center. These two coordinates can be understood as the row and column numbers of the corresponding points in the entire pixel array used to construct the face image. The horizontal axis represents the column number of the pixel array in which the point is located, and the vertical axis represents the row number of the pixel array in which the point is located. Based on these two pixel coordinates, the number of pixels separating the centers of the left and right pupils can be determined.

[0055] For example, the coordinates of the first pixel are denoted as P. l (x1, y1), mark the second pixel coordinates as P r (x2, y2). The difference between the x-coordinates of the first and second pixels is denoted as Δx. p , △x p = x2 - x1; the difference between the ordinates of the first and second pixel coordinates is denoted as Δy. p , △y p = y2 - y1; then the pixel distance d between the first pixel coordinate and the second pixel coordinate is... p It can be expressed by the following formula (1): (1) By pixel distance d p The number of pixels between the first and second pixel coordinates can be determined. Furthermore, the camera's pixel size is a fundamental hardware parameter, so the first distance d1 can be represented by the following formula (2): (2) In some possible embodiments, face image detection technology can directly obtain the horizontal and vertical distances of the pupil center in the face image relative to the origin of the face image (e.g., the lower left corner of the face image), and use these two distances as the horizontal and vertical coordinates of the pupil center. These coordinates can also be the first pixel coordinates or the second pixel coordinates mentioned above. Based on this, the values ​​included in the first and second pixel coordinates are all values ​​with units. For example, the first pixel coordinate (50mm, 100mm) means that the horizontal distance of the user's right pupil center in the face image relative to the lower left corner is 50mm, and the vertical distance is 100mm; the second pixel coordinate (120mm, 101mm) means that the horizontal distance of the user's left pupil center in the face image relative to the lower left corner is 120mm, and the vertical distance is 101mm. Based on this pixel representation, the d shown in the above formula (1) pIt can be directly used to represent the first distance d1, i.e., d p =d1, eliminating the need to calculate the distance between two points in a face image using pixel dimensions. Face image detection technology essentially identifies multiple key points on a face in an image, directly determining their positions within the image. Since the centers of a person's pupils happen to fall within these key points, the horizontal and vertical distances of the pupil centers relative to the origin (e.g., the lower left corner) can be directly obtained and used as the coordinates of the pupil centers.

[0056] S330: Determine the user's actual second facial geometry parameters, where the first facial set parameters and the second facial geometry parameters are used to indicate the same reference feature of the user's face.

[0057] In some possible embodiments, the first facial geometric parameter may include various geometric parameters relating to facial features, such as face width, face length, forehead width, etc. Similarly, the second facial geometric parameter must represent a consistent facial feature (reference feature). For example, if the first facial geometric parameter is the width of the user's face as presented in the facial image, such as 20mm, then the second facial geometric parameter corresponds to the user's actual face width, such as 140mm.

[0058] In some possible embodiments, the aforementioned second facial geometric parameters can be preset reference values, such as 140mm, 135mm, etc. There can be multiple preset reference values, corresponding to different user age groups, genders, etc. For example, in practical applications, the user's age group, gender, etc., can be analyzed based on the user's facial image, and then the preset reference value can be adaptively adjusted.

[0059] S340: Determine the second distance between the user and the camera based on the first facial geometry parameters, the second facial geometry parameters, and the camera's focal length.

[0060] For ease of understanding, the following uses the first and second facial geometric parameters as an example to illustrate the detailed process of determining the second distance.

[0061] Similar to the aforementioned embodiment regarding the calculation of the distance between the centers of the left and right pupils, the face width represented by the first facial geometric parameter can also be determined by pixel coordinates. For example, based on the facial image, the coordinates of the third leftmost pixel and the fourth rightmost pixel of the user's facial outline can be determined; then, the first facial geometric parameter can be determined based on the third and fourth pixel coordinates.

[0062] For example, if the face image detection technology can take the points at the farthest ends of the face contour as key points, then the third pixel coordinates and fourth pixel coordinates obtained based on the technology can be used to indicate the horizontal and vertical distances of these two points in the face image relative to the image origin (e.g., the lower left corner point), and the first face geometric parameters can be determined by referring to formula (1).

[0063] For example, if the third and fourth pixel coordinates are only used as the row and column numbers of the corresponding points in the pixel array of the entire face image, then after determining the pixel distance between the third and fourth pixel coordinates (refer to formula (1)), it is also necessary to multiply this pixel distance by the camera's pixel size (refer to formula (2)) to determine the distance between these two points in the face image. In this example, since the first and second face geometry parameters are used to indicate the user's face width, the pixel size (pixel_size) can be represented by the following formula (3): pixel_size= sensor_width / image_width(3) Here, sensor_width refers to the physical width of the camera lens's field of view, such as 4.8mm, and image_width refers to the horizontal number of pixels in the face image, such as 1920 pixels.

[0064] Furthermore, since the camera's focal length is a known hardware parameter, the second distance d2 mentioned above can be expressed by the following formula (4): (4) Where, d f1 d is used to represent the first facial geometric parameters mentioned above. f2 The second facial geometry parameter is used to represent the above-mentioned second facial geometry parameter, and f is used to represent the focal length of the camera. If the third pixel coordinate and the fourth pixel coordinate are used to indicate the horizontal distance and vertical distance of these two points relative to the lower left corner point in the facial image, then in the above formula (4), d f2 You can skip multiplying by pixel_size and simply replace the denominator on the right-hand side of the equation with d. f2 That's all.

[0065] S350: Determines the user's interpupillary distance based on the first distance, the second distance, and the camera's focal length.

[0066] As can be seen from the foregoing embodiments, the first distance and the second distance are parameters that can be calculated, and the focal length of the camera is a known camera hardware parameter. Therefore, based on the imaging model (pinhole imaging principle), the first distance can be converted into the actual physical distance, i.e., the user's interpupillary distance.

[0067] In some possible embodiments, the interpupillary distance can be determined by the following formula (5): (5) IPD is used to represent interpupillary distance.

[0068] S360: Adjusts the imaging parameters of the 3D display device according to the interpupillary distance to match the imaging parameters with the interpupillary distance.

[0069] The imaging parameters include the optical center distance of the 3D display device and the virtual camera baseline.

[0070] In some possible embodiments, adjusting the imaging parameters to match the interpupillary distance may refer to adjusting the optical center distance to be equal to the user's interpupillary distance and adjusting the virtual camera baseline to be equal to the user's interpupillary distance.

[0071] This completes the process of determining the user's actual interpupillary distance from the facial image acquired by a monocular camera and adaptively adjusting the imaging parameters of the 3D display device.

[0072] In some possible embodiments, the method 300 described above can be executed by a controller built into the 3D display device to avoid manual adjustment by the user.

[0073] Based on the above technical solution, even facial images acquired through a monocular camera can obtain the user's actual interpupillary distance and adaptively adjust the imaging parameters of the 3D display device. This eliminates the need for the user to manually fine-tune the device's imaging parameters based on subjective feelings, thereby simplifying the user's operation of the 3D display device and improving the user's viewing experience.

[0074] In determining the second distance, it is necessary to obtain the second facial geometric parameters. As can be seen from the aforementioned embodiments, the second facial geometric parameters can be a preset parameter. However, in actual applications, the facial features of users are diverse. Therefore, if one or more preset parameters are fixed, there may be a situation where the second facial geometric parameters do not match the corresponding facial features of the current user, resulting in an error in the final pupil distance.

[0075] In view of this, the embodiments of this application further propose a method for determining the second facial geometric parameters, so that the second facial geometric parameters can match the corresponding facial features of the current user as much as possible, thereby ensuring the accuracy of determining the interpupillary distance based on the facial image obtained by a monocular camera proposed in the embodiments of this application.

[0076] Figure 4 This is a flowchart illustrating a method 400 for determining the geometric parameters of a second face according to an embodiment of this application.

[0077] refer to Figure 4As shown, the method 400 may include the following operations: S410: Determine multiple facial key points of the user based on the facial image.

[0078] The facial image is the facial image of the user currently viewing the 3D display device, obtained by a monocular camera in the aforementioned embodiment.

[0079] In some possible embodiments, the aforementioned multiple facial key points can be obtained through a MediaPipeFace Mesh detection model. Based on this detection model, 468 3D key points can be output simultaneously in an image or video stream, covering the eyes, eyebrows, nose, mouth, cheeks, and contours.

[0080] S420: Determine facial feature parameters related to reference features based on multiple facial key points.

[0081] Among them, the reference feature parameters refer to the parameters of the user's facial features jointly indicated by the first facial geometric parameters and the second facial geometric parameters, such as the distance between the two cheekbone points and the distance between the two ear points.

[0082] S430: Input the facial feature parameters into the trained regression model to determine the second facial geometric parameters. The regression model is built based on calibration samples, which include the mapping relationship between multiple sets of facial feature parameters and actual facial geometric parameters.

[0083] In some possible embodiments, the regression model described above can be modeled based on the principle of linear regression or on the principle of random forest.

[0084] In some possible embodiments, when the above-mentioned multiple facial key points are obtained through a facial 3D mesh detection model, in order to reduce the amount of computation, the 468 points involved in the detection model can be further sparsely sampled, for example, only 12 reference points that are strongly correlated with rigid geometry (left and right outer corners of the eyes, left and right tragus, tip of the nose, top of the chin, etc.) can be retained, so as to ensure accuracy and reduce the input dimension of the regression model.

[0085] Based on the above technical solution, the corresponding facial geometric parameters are obtained by using a pre-trained regression model based on the facial feature parameters obtained from the key points of the user's face in the image. Since the regression model has undergone large-scale 3D facial data calibration, it can compress the mapping error from key points to facial geometric parameters to the sub-millimeter level. Therefore, it can ensure that the second facial geometric parameters match the corresponding facial features of the current user, thereby ensuring the accuracy of determining the interpupillary distance based on the facial image obtained by a monocular camera proposed in this application embodiment.

[0086] In some possible embodiments, based on the above method 400, multiple sets of facial feature parameters determined from multiple frames of facial images of the user can be input into the regression model respectively, so that the regression model outputs multiple third facial geometric parameters, and then the multiple third facial geometric parameters are weighted and averaged to determine the second facial geometric parameter; or, the median of the multiple third facial geometric parameters can be determined as the second facial geometric parameter.

[0087] Based on the above technical solution, the accuracy of the obtained second facial geometric parameters can be further improved, and noise interference in single-frame facial images can be reduced.

[0088] In some possible embodiments, the method for adjusting parameters proposed in this application can also be applied to 3D display devices equipped with binocular cameras. However, the method for obtaining the user's interpupillary distance varies depending on the type of camera. Since S320 and subsequent operations are performed in the above method 300, it is explained that the following operation was performed before S320: determining that the face image is obtained based on a single viewpoint.

[0089] After acquiring the facial image, the following operations can be performed: determine the acquisition method of the facial image, which includes single-view acquisition or dual-view acquisition, where dual-view acquisition refers to acquisition through a camera that includes both left and right viewpoints.

[0090] In some possible embodiments, the method of acquiring face images can also be extended to multi-view acquisition, that is, the number of viewpoints for acquiring the image is greater than 2. However, the subsequent related operations of face images acquired based on multi-view acquisition are in principle the same as the subsequent related operations of face images acquired based on dual-view acquisition. For ease of description, the embodiments of this application only describe the subsequent operations of face images acquired based on dual-view acquisition in detail.

[0091] If the face image is acquired through a single viewpoint, there is one face image. If the face image is acquired through a dual viewpoint, there are two face images, including a left-eye face image (acquired through the left-eye camera) and a right-eye face image (acquired through the right-eye camera). There is a parallax between the left-eye face image and the right-eye face image.

[0092] If a facial image is acquired through dual viewpoints, the user's interpupillary distance can be determined in the following way.

[0093] Figure 5 This is a flowchart illustrating a method 500 for determining interpupillary distance using a binocular camera, as proposed in an embodiment of this application.

[0094] refer to Figure 5 As shown, the method 500 includes the following operations: S510: Based on the left eye face image, determine the fifth pixel coordinate of the user's left pupil and the sixth pixel coordinate of the right pupil in the left eye face image. Based on the right eye face image, determine the seventh pixel coordinate of the user's left pupil and the eighth pixel coordinate of the right pupil in the right eye face image.

[0095] The aforementioned pixel coordinates can be used to represent the coordinates of the center of the user's pupil. The methods for determining the third and fourth distances are the same as those for determining the first distance mentioned in the previous embodiments, and will not be repeated here.

[0096] S520: Determine the left eye pupil disparity based on the fifth and seventh pixel coordinates, and determine the right eye pupil disparity based on the sixth and eighth pixel coordinates.

[0097] In some possible embodiments, the fifth and seventh pixel coordinates can be matched along the epipolar line to determine the left eye pupil parallax, and the sixth and eighth pixel coordinates can be matched along the epipolar line to determine the right eye pupil parallax. Here, the epipolar line is a forced search line in stereo vision. For example, any point on the imaging plane of the left eye camera (e.g., the center of the left eye pupil) will necessarily correspond to a straight line on the imaging plane of the right eye camera; this straight line is the epipolar line.

[0098] S530: Based on the fifth or seventh pixel coordinates, the sixth or eighth pixel coordinates, the left eye pupil parallax, the right eye pupil parallax, the intrinsic parameters of the left and right eye cameras, and the baseline length, determine the first three-dimensional coordinates of the left eye pupil and the second three-dimensional coordinates of the right eye pupil in the world coordinate system.

[0099] In this context, intrinsic parameters refer to the camera's focal length, principal point, and radial or tangential distortion coefficients. Baseline length refers to the Euclidean distance between the optical centers of the left and right eye cameras.

[0100] In some possible embodiments, the first three-dimensional coordinates and the second three-dimensional coordinates can be determined by triangulation and based on the parameters described above.

[0101] Taking the left pupil as an example: based on the focal length f of the left eye camera l Baseline length b and left eye pupillary disparity d l This allows us to determine the vertical depth Z from the left pupil to the optical center of the left eye camera. l Z l =(f l · b) / d l .

[0102] Therefore, based on the above fifth pixel coordinates and the above vertical depth Z... l Focal length f lThe coordinates of the left eye camera's principal point are used to determine the first three-dimensional coordinates, marked as (X1, Y1, Z1), the fifth pixel coordinates as (x_l, y_l), and the coordinates of the left eye camera's principal point as (c_x, x_y).

[0103] Then, X1 = (x_l) c_x) · Z l / f l ; Y1= (y_l c_y) · Z l / f l ; Z1=Z l .

[0104] The above process calculates the first three-dimensional coordinates based on the fifth pixel coordinate of the left eye pupil in the left eye face image, using parameters such as the left eye camera intrinsics. Alternatively, it can be replaced by calculating the first three-dimensional coordinates based on the seventh pixel coordinate of the right eye face image, using parameters such as the right eye camera intrinsics.

[0105] As for the calculation of the second three-dimensional coordinates of the right pupil, the principle is the same as that for the calculation of the first three-dimensional coordinates of the left pupil, and will not be repeated here.

[0106] S540: Calculate the Euclidean distance between the first three-dimensional coordinates and the second three-dimensional coordinates to determine the user's interpupillary distance.

[0107] After determining the user's interpupillary distance, similar to the aforementioned method 300, the imaging parameters of the 3D display device can be adaptively adjusted to match the imaging parameters with the interpupillary distance.

[0108] Based on the above technical solution, when the camera mounted on the 3D display device is a binocular camera, it is still possible to determine the user's physiological interpupillary distance, so as to adaptively adjust the imaging parameters of the 3D display device and avoid the user manually adjusting the imaging parameters based on subjective feelings, thereby helping to improve the user's viewing experience.

[0109] The 3D display device can have one or more users. If there is only one user, the imaging parameters of the 3D display device can be fixed after adjustment, and the imaging parameters do not need to be readjusted when the user uses the 3D display device subsequently. If there are multiple users, after adjusting the imaging parameters of the 3D display device based on user A's interpupillary distance (IPD), user B takes over using the 3D display device, and user A and user B have different IPDs. In this case, the parameter adjustment method proposed in this application allows the 3D display device to adaptively adjust the imaging parameters based on user B's IPD to match user B's IPD. When user A takes over using the 3D display device again, the 3D display device needs to re-execute the method proposed in this application. If user A and user B repeatedly alternate using the 3D display device, the method proposed in this application needs to be repeatedly executed, resulting in significant computational overhead. Therefore, this application proposes a mechanism for binding users to imaging parameters.

[0110] In some possible embodiments, taking the first user as an example, the imaging parameters that match the first interpupillary distance of the first user, determined by the method proposed in this application, are the first imaging parameters. When the first user uses the 3D display device for the first time, the first facial identification feature of the first user can be determined based on the facial image of the first user. The first facial identification feature includes facial features used to uniquely identify the first user. Then, a first association relationship is established between the first facial identification feature and the first imaging parameter. This first association relationship is used to adjust the imaging parameters of the 3D display device to the first imaging parameter when the first facial identification feature is obtained again.

[0111] The aforementioned first association relationship can be stored locally on the 3D display device or on the cloud server of the 3D display device. Similarly, if the second user has a second facial identification feature and the second interpupillary distance of the second user matches the second imaging parameter, then a second association relationship can be established. This second association relationship is used to indicate the mapping relationship between the second facial identification feature and the second imaging parameter.

[0112] Therefore, after obtaining the user's facial image, the user's facial identification features can be obtained from the facial image, and the stored candidate associations can be retrieved to determine whether the facial identification features match any candidate association. If they match, the imaging parameters in the candidate association can be reused.

[0113] In some possible embodiments, since the imaging parameters and the user's interpupillary distance are usually the same in value, the above-established correlation can also be a correlation between the user's facial features and the user's interpupillary distance.

[0114] Based on the above technical solution, the user's interpupillary distance obtained by the method proposed in this application is associated with the user's facial identification features. When the same user uses the 3D display device again, the user's interpupillary distance and corresponding imaging parameters can be directly determined. It is not necessary to repeat the method proposed in this application for the same user, thereby reducing computational overhead and realizing a fast response to the adjustment of the imaging parameters of the 3D display device.

[0115] In summary, based on the methods proposed in the foregoing embodiments, this application also proposes a business logic that is compatible with both monocular and binocular cameras in acquiring face images, and determines the user's interpupillary distance based on the face images, and adaptively adjusts the imaging parameters of the 3D display device.

[0116] Figure 6 This is a business process diagram for adjusting the imaging parameters of a 3D display device, as proposed in an embodiment of this application.

[0117] S610: Captures the user's facial image via camera.

[0118] S615: Determine the user's facial identification features based on the facial image.

[0119] S620: Determine whether there is a target association in the candidate association set that matches the user's facial identifier features. If yes, proceed to S623; otherwise, proceed to S625.

[0120] S623: Adjust the imaging parameters of the 3D display device to the target imaging parameters recorded in the target association relationship.

[0121] S625: Determine the method of acquiring the face image. If it is a single-viewpoint acquisition, proceed to S630; if it is a dual-viewpoint acquisition, proceed to S640.

[0122] S630: Based on the face image, determine the first distance between the user's left and right pupils in the face image and the user's first facial geometric parameters.

[0123] S633: Determine the user's actual second facial geometry parameters, where the first facial set parameters and the second facial geometry parameters are used to indicate the same reference feature of the user's face.

[0124] S635: Determine the second distance between the user and the camera based on the first facial geometry parameters, the second facial geometry parameters, and the camera's focal length.

[0125] S637: Determine the user's interpupillary distance based on the first distance, the second distance, and the camera's focal length. Proceed to S650.

[0126] For detailed descriptions of the related extensions of S630 to S637, please refer to the corresponding embodiments mentioned above, which will not be repeated here.

[0127] S640: Based on the left eye face image, determine the fifth pixel coordinate of the user's left pupil and the sixth pixel coordinate of the right pupil in the left eye face image. Based on the right eye face image, determine the seventh pixel coordinate of the user's left pupil and the eighth pixel coordinate of the right pupil in the right eye face image.

[0128] S643: Determine the left eye pupil disparity based on the fifth and seventh pixel coordinates, and determine the right eye pupil disparity based on the sixth and eighth pixel coordinates.

[0129] S645: Based on the fifth or seventh pixel coordinates, the sixth or eighth pixel coordinates, the left eye pupil parallax, the right eye pupil parallax, the intrinsic parameters of the left and right eye cameras, and the baseline length, determine the first three-dimensional coordinates of the left eye pupil and the second three-dimensional coordinates of the right eye pupil in the world coordinate system.

[0130] S647: Calculate the Euclidean distance between the first and second 3D coordinates to determine the user's interpupillary distance. Proceed to S650.

[0131] For detailed descriptions of the related extensions of S640 to S647, please refer to the corresponding embodiments described above, which will not be repeated here.

[0132] S650: Adjust the imaging parameters of the 3D display device to the target imaging parameters based on the interpupillary distance, which are matched with the interpupillary distance.

[0133] S660: Establish a correlation between the user's facial identification features and the above target imaging parameters, and store them in the candidate correlation set.

[0134] This completes the business process for adjusting the imaging parameters of the 3D display device.

[0135] Furthermore, embodiments of this application also provide an apparatus for adjusting parameters to implement any of the above methods, the apparatus including units (or means) for implementing any of the above methods.

[0136] Figure 7 This is a schematic block diagram of a parameter adjustment device 700 provided in an embodiment of this application.

[0137] refer to Figure 7 As shown, the device 700 includes: The acquisition unit 710 is used to acquire a user's facial image via a camera.

[0138] The first determining unit 720 is used to determine, based on the face image, a first distance between the user's left and right pupils in the face image and the user's first facial geometric parameters.

[0139] The second determining unit 730 is used to determine the user's actual second facial geometric parameters, wherein the first facial set parameters and the second facial geometric parameters are used to indicate the same reference feature of the user's face.

[0140] The third determining unit 740 is used to determine a second distance between the user and the camera based on the first facial geometric parameters, the second facial geometric parameters, and the focal length of the camera; and to determine the user's interpupillary distance based on the first distance, the second distance, and the focal length of the camera.

[0141] The adjustment unit 750 is used to adjust the imaging parameters of the 3D display device according to the interpupillary distance so that the imaging parameters match the interpupillary distance.

[0142] In some possible embodiments, the camera is mounted on a 3D display device and is a monocular camera. The imaging parameters include the optical center distance of the 3D display device and the virtual camera baseline.

[0143] In some possible embodiments, the first determining unit 720 is specifically used to: determine the first pixel coordinates of the user's left pupil in the face image and the second pixel coordinates of the user's right pupil in the face image based on the face image; and determine a first distance based on the first pixel coordinates and the second pixel coordinates.

[0144] In some possible embodiments, the second determining unit 730 is specifically used to: determine the leftmost third pixel coordinate and the rightmost fourth pixel coordinate of the outer contour of the user's face based on the face image; and determine a first face geometric parameter based on the third pixel coordinate and the fourth pixel coordinate, the first face geometric parameter being used to indicate the width of the user's face in the face image.

[0145] In some possible embodiments, the third determining unit 740 is specifically used to: determine multiple facial key points of the user based on the facial image; determine facial feature parameters related to reference features based on the multiple facial key points; input the facial feature parameters into a trained regression model to determine second facial geometric parameters, wherein the regression model is established based on calibration samples, and the calibration samples include the mapping relationship between multiple sets of facial feature parameters and actual facial geometric parameters.

[0146] In some possible embodiments, the third determining unit 740 is specifically used to: input multiple sets of facial feature parameters determined based on multiple frames of facial images of the user into a regression model, so that the regression model outputs multiple third facial geometric parameters; perform a weighted average of the multiple third facial geometric parameters to determine a second facial geometric parameter; or, determine the median of the multiple third facial geometric parameters as the second facial geometric parameter.

[0147] In some possible embodiments, before the first determining unit 710 determines, based on the face image, a first distance between the user's left and right pupils in the face image and the user's first facial geometric parameters, the first determining unit 710 is further configured to: determine that the face image is acquired based on a single viewpoint.

[0148] In some possible embodiments, the device 700 further includes a fourth determining unit 760. Taking the example that the user includes a first user, the imaging parameters include a first imaging parameter, and the first imaging parameter matches the first interpupillary distance of the first user, the fourth determining unit 760 is used to: determine a first facial identifier feature of the first user based on the facial image of the first user, the first facial identifier feature including facial features used to uniquely identify the first user; establish a first association relationship between the first facial identifier feature and the first imaging parameter, the first association relationship being used by the adjusting unit 750 to directly adjust the imaging parameters of the 3D display device to the first imaging parameter when the obtaining unit 710 obtains the first facial identifier feature again. In some possible embodiments, at least two of the above-mentioned first determining unit 720, second determining unit 730, third determining unit 740 and fourth determining unit 760 can be integrated into the same processor to exist as a single determining unit.

[0149] Furthermore, this application also proposes a parameter adjustment device, which includes a processor and a memory connected together. The memory is used to store program code, and the processor is used to call the program code to execute any of the methods proposed in this application.

[0150] This application also provides a computer program product, which includes computer program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0151] This application also provides a computer-readable medium storing program code that, when run on a computer, causes the computer to perform the methods described in the above embodiments.

[0152] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0153] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0155] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0156] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0157] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0158] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of parameter adjustment, characterized by, The method comprises: acquiring a face image of a user through a camera; determining a first distance between left and right pupils of the user in the face image and a first face geometry parameter of the user according to the face image; determining an actual second face geometry parameter of the user, the first face geometry parameter and the second face geometry parameter being used to indicate a same reference feature of the face of the user; determining a second distance between the user and the camera according to the first face geometry parameter, the second face geometry parameter and a focal length of the camera; determining a interpupillary distance of the user according to the first distance, the second distance and the focal length of the camera; and adjusting an imaging parameter of a 3D display device according to the interpupillary distance, so as to match the imaging parameter with the interpupillary distance.

2. The method of claim 1, wherein, The camera is mounted on the 3D display device, and the camera is a monocular camera, and the imaging parameter comprises an optical center distance and a virtual camera baseline of the 3D display device.

3. The method according to claim 1 or 2, characterized in that, The determining the first distance between the left and right pupils of the user in the face image according to the face image comprises: determining a first pixel coordinate of the left pupil of the user in the face image and a second pixel coordinate of the right pupil of the user in the face image according to the face image; and determining the first distance according to the first pixel coordinate and the second pixel coordinate.

4. The method according to any one of claims 1 to 3, characterized in that, The determining the first face geometry parameter of the user according to the face image comprises: determining a third pixel coordinate of a leftmost side and a fourth pixel coordinate of a rightmost side of an outer contour of the face of the user according to the face image; and determining the first face geometry parameter according to the third pixel coordinate and the fourth pixel coordinate, the first face geometry parameter being used to indicate a width of the face of the user in the face image.

5. The method according to any one of claims 1 to 4, characterized in that, The determining the actual second face geometry parameter of the user comprises: determining a plurality of face key points of the user according to the face image; determining a face feature parameter related to the reference feature according to the plurality of face key points; inputting the face feature parameter into a trained regression model to determine the second face geometry parameter, the regression model being established based on a calibration sample, and the calibration sample comprising a mapping relationship between a plurality of sets of the face feature parameter and actual face geometry parameters.

6. The method of claim 5, wherein, The inputting the face feature parameter into the trained regression model to determine the second face geometry parameter comprises: inputting a plurality of sets of the face feature parameter determined according to a plurality of face images of the user into the regression model respectively, so that the regression model outputs a plurality of third face geometry parameters; and determining the second face geometry parameter by weighted averaging the plurality of third face geometry parameters, or determining a median value of the plurality of third face geometry parameters as the second face geometry parameter.

7. The method according to any one of claims 1 to 6, characterized in that, Before the determining the first distance between the left and right pupils of the user in the face image and the first face geometry parameter of the user according to the face image, the method further comprises: It is determined that the face image is acquired based on single view.

8. The method according to any one of claims 1 to 7, characterized in that, The user includes a first user, and the imaging parameter includes a first imaging parameter, the first imaging parameter being matched with a first interpupillary distance of the first user, and the method further includes: According to the face image of the first user, a first face identification feature of the first user is determined, the first face identification feature including face features for uniquely identifying the first user; The first face identification feature is associated with the first imaging parameter to establish a first association relationship, the first association relationship being used to adjust the imaging parameter of the 3D display device to the first imaging parameter when the first face identification feature is acquired again.

9. A 3D display device, characterized by comprising: The apparatus includes a monocular camera and a controller, the monocular camera being used to acquire a face image of a user, and the controller being used to execute the method according to any one of claims 1 to 8.

10. An apparatus for parameter adjustment, characterized by The apparatus includes a module or unit for executing the method according to any one of claims 1 to 8.

11. An apparatus for parameter adjustment, characterized by The apparatus includes at least one processor coupled with at least one memory, the at least one processor being used to execute computer programs or instructions stored in the at least one memory to make the apparatus execute the method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program being executed by a processor to implement the method according to any one of claims 1 to 8.

13. A computer program product, characterised in that, The computer readable storage medium stores a computer program, the computer program being executed by a processor to implement the method according to any one of claims 1 to 8. The computer readable storage medium stores a computer program, the computer program being executed by a processor to implement the method according to any one of claims 1 to 8.

Images