Distortion removal method and device for binocular image, intelligent wearable equipment and medium

Abstract

The invention relates to the technical field of image processing, and discloses a binocular image distortion removing method and device, an intelligent wearable device and a medium, and the method comprises the steps: determining a target waveguide distortion processing model, and determining a target image offset comparison table according to a target intelligent wearable device and the target waveguide distortion processing model; and performing distortion correction on the original left eye image and the original right eye image according to the target image offset comparison table to generate a target left eye image and a target right eye image. Through the above mode, the target waveguide distortion processing model is determined through the target intelligent wearable device, the target image offset comparison table is determined according to the model, distortion correction is effectively performed on the original left eye image and the original right eye image, and the target left eye image and the target right eye image are correspondingly generated. The synchronism of the left eye image and the right eye image collected by the intelligent wearable device through the waveguide technology is improved, and the distortion degree of the synthesized binocular image is further reduced.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a binocular image dedistortion method, device, smart wearable device and medium. Background Art

[0002] With the rapid development of extended reality technology, smart wearable devices have gradually become an important tool for users to interact with the virtual world. However, in the image display process of smart wearable devices, waveguide technology, as one of the core imaging technologies, is widely used in the optical system of smart wearable devices due to its efficient optical propagation characteristics. However, due to the nonlinear optical properties of the waveguide itself, when transmitting images through the waveguide, especially in the process of binocular image synthesis, the asynchrony between the left and right eye images causes image distortion, resulting in picture distortion. The waveguide distortion correction method in the related art is not sufficient to effectively solve the problem of image distortion caused by the asynchrony between the left and right eye images during the waveguide transmission process. Therefore, how to improve the synchronization of the smart wearable device in the process of collecting the left and right eye images through the waveguide technology to synthesizing and displaying the binocular image, and then reduce the degree of distortion of the synthesized binocular image has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides a binocular image dedistortion method, apparatus, smart wearable device and medium, which improve the synchronization of the smart wearable device in the process of collecting left-eye images and right-eye images through waveguide technology to synthesizing and displaying binocular images, thereby reducing the degree of distortion of the synthesized binocular image.

[0004] In a first aspect, the present application provides a method for dedistorting a binocular image, the method comprising:

[0005] Determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model;

[0006] The original left-eye image and the original right-eye image are acquired through the target smart wearable device, and the original left-eye image and the original right-eye image are respectively subjected to distortion correction according to the target image offset comparison table to generate a target left-eye image and a target right-eye image.

[0007] In a second aspect, the present application further provides a binocular image dedistortion device, the device comprising:

[0008] An offset comparison table determination module is used to determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model;

[0009] The target image dedistortion module is used to obtain the original left-eye image and the original right-eye image through the target smart wearable device, and perform distortion correction on the original left-eye image and the original right-eye image according to the target image offset comparison table to generate a target left-eye image and a target right-eye image.

[0010] In a third aspect, the present application also provides a smart wearable device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the binocular image dedistortion method as described above when executing the computer program.

[0011] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the binocular image dedistortion method as described above.

[0012] The present application discloses a binocular image dedistortion method, device, smart wearable device and medium, the binocular image dedistortion method includes determining a target waveguide distortion processing model through a target smart wearable device, and determining a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model; obtaining the original left-eye image and the original right-eye image through the target smart wearable device, and performing distortion correction on the original left-eye image and the original right-eye image according to the target image offset comparison table, to generate a target left-eye image and a target right-eye image. Through the above method, the present application determines a target waveguide distortion processing model through a target smart wearable device, and determines a target image offset comparison table according to the model, effectively performing distortion correction on the original left-eye image and the original right-eye image, respectively, and correspondingly generating a target left-eye image and a target right-eye image, thereby improving the synchronization of the left-eye image and the right-eye image collected by the smart wearable device through waveguide technology, thereby reducing the degree of distortion of the synthetic binocular image. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 is a schematic flow chart of a binocular image dedistortion method provided in the first embodiment of the present application;

[0015] Figure 2 is a schematic flow chart of a binocular image dedistortion method provided in the second embodiment of the present application;

[0016] Figure 3 is a schematic flow chart of a binocular image dedistortion method provided in the third embodiment of the present application;

[0017] Figure 4 A schematic block diagram of a binocular image dedistortion device provided in an embodiment of the present application;

[0018] Figure 5 A schematic block diagram of the structure of a smart wearable device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0021] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] The embodiments of the present application provide a binocular image dedistortion method, apparatus, smart wearable device and medium. The binocular image dedistortion method can be applied to smart wearable devices, and the target waveguide distortion processing model is determined by the target smart wearable device, and the target image offset comparison table is determined according to the model, so as to effectively perform distortion correction on the original left-eye image and the original right-eye image respectively, and generate the target left-eye image and the target right-eye image accordingly, thereby reducing the image distortion and improving the synchronization of the binocular images in the smart wearable device. The smart wearable device can be an AR (Augmented Reality, enhanced display) device, or a VR (Virtua l Reality, virtual reality) device or other smart wearable device with image acquisition function, which is not limited here.

[0024] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0025] See also Figure 1 , Figure 1 It is a schematic flow chart of a binocular image dedistortion method provided by the first embodiment of the present application, which is used to determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table according to the model, effectively perform distortion correction on the original left-eye image and the original right-eye image respectively, and generate a target left-eye image and a target right-eye image accordingly, thereby improving the synchronization of the left-eye image and the right-eye image collected by the smart wearable device through the waveguide technology, thereby reducing the degree of distortion of the synthetic binocular image.

[0026] like Figure 1 As shown, the binocular image dedistortion method specifically includes steps S10 to S30.

[0027] Step S10: determining a target waveguide distortion processing model through a target smart wearable device, and determining a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model;

[0028] Specifically, according to the target waveguide distortion processing model, an offset model is established to calculate the image offset and the image offset under different distortion conditions is calculated using the offset model. The calculated offsets are organized into a comparison table, which can be quickly searched and applied according to the type or model of the smart wearable device in the subsequent correction process.

[0029] Step S20: obtaining an original left-eye image and an original right-eye image through the target smart wearable device, and performing distortion correction on the original left-eye image and the original right-eye image respectively according to the target image offset comparison table to generate a target left-eye image and a target right-eye image.

[0030] In a specific embodiment, according to the target image offset comparison table, the offset corresponding to the current waveguide distortion is selected, and the selected offset is applied to the original left eye image and the original right eye image to perform distortion correction. The corrected images are the target left eye image and the target right eye image.

[0031] In one embodiment, the smart wearable device is an AR glasses as an example to illustrate this embodiment. Based on the characteristics of waveguide technology, the resolution of the image transmitted by waveguide technology is the same, that is, the resolution of the original left-eye image and the target left-eye image is the same. The same resolution means that the number of pixels in each original left-eye image and the target left-eye image is the same, and the pixels in each original left-eye image and each target left-eye image are one-to-one corresponding. Similarly, the resolution of the original right-eye image and the target right-eye image is also the same. The target image offset comparison table corresponding to the AR glasses is obtained in advance, and the target image offset comparison table records the offset of each pixel in detail. In the binocular image synthesis process of AR glasses, the target image offset comparison table performs waveguide distortion correction on the left and right images respectively.

[0032] The AR glasses obtain the original left-eye image and the original right-eye image. left (x, y), according to the target image offset corresponding to the target image offset table LUT left (x, y) Determine the offset between the coordinate value (x, y) of each distorted pixel and its standard position, that is, Δx, Δy. Determine the offset of each pixel through the target image offset comparison table:

[0033] That is, the pixel coordinate value in the target left image.

[0034] The target image offset comparison table records the pixel offsets of all pixels. Taking the original left-eye image and the target left-eye image as examples, after obtaining the coordinate values ​​of each original pixel in the original left-eye image, the pixel coordinate values ​​of the corresponding pixel in the target left-eye image can be obtained by subtracting the pixel offset corresponding to the pixel from the coordinate values ​​of each original pixel.

[0035] The present embodiment discloses a binocular image dedistortion method, which includes determining a target waveguide distortion processing model through a target smart wearable device, and determining a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model; obtaining an original left-eye image and an original right-eye image through the target smart wearable device, and performing distortion correction on the original left-eye image and the original right-eye image according to the target image offset comparison table, to generate a target left-eye image and a target right-eye image. In the above manner, the present application determines a target waveguide distortion processing model through a target smart wearable device, and determines a target image offset comparison table according to the model, effectively performing distortion correction on the original left-eye image and the original right-eye image, respectively, and correspondingly generating a target left-eye image and a target right-eye image, thereby reducing image distortion and improving the synchronization of binocular images in AR smart wearable devices.

[0036] See also Figure 2 , Figure 2 This is a schematic flow chart of a binocular image dedistortion method provided in the second embodiment of the present application, which is used to provide personalized distortion correction for different smart wearable devices by building matching waveguide distortion processing models for different preset smart wearable device types. By matching the target device type with the preset device type, the wide compatibility of the waveguide distortion processing model is ensured, and the synchronization of the binocular images in the smart wearable device is improved. By determining the target image offset comparison table, the original image can be more accurately distorted, reducing visual distortion, thereby enhancing the user's immersion and comfort.

[0037] based on Figure 1 The embodiment shown, this embodiment Figure 2 As shown, step S10 includes steps S101 to S103.

[0038] Step S101: determining at least one preset waveguide distortion processing model matching each preset smart wearable device according to the preset device type of each preset smart wearable device;

[0039] Specifically, the optical parameters of various preset smart wearable devices (such as AR glasses of different brands and models) are collected. The optical parameters may be resolution, field of view, band, distortion, illumination uniformity, light incident angle, etc. The commonalities and characteristics of waveguides in different device types are identified according to the above optical parameters, and a preset waveguide distortion processing model is constructed for each preset smart wearable device type, that is, a corresponding relationship between various preset smart wearable devices and preset waveguide distortion processing models is established.

[0040] Step S102: Match the target device type of the target smart wearable device with each of the preset device types;

[0041] Specifically, the device brand or model of the target smart wearable device is matched with the preset device types of all preset smart wearable devices, and the target waveguide distortion processing model is determined according to the above correspondence.

[0042] Step S103: Determine the preset waveguide distortion processing model corresponding to the preset device type that matches the target device type as the target waveguide distortion processing model.

[0043] In one embodiment, since different preset smart wearable devices correspond to different preset waveguide distortion processing models, the target waveguide distortion processing model can be determined according to the target device type.

[0044] The binocular image dedistortion method disclosed in this embodiment includes determining at least one preset waveguide distortion processing model that matches each preset smart wearable device according to the preset device type of each preset smart wearable device; matching the target device type of the target smart wearable device with each preset device type; determining the preset waveguide distortion processing model corresponding to the preset device type that matches the target device type as the target waveguide distortion processing model, and determining the target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model; obtaining the original left-eye image and the original right-eye image through the target smart wearable device, and performing distortion correction on the original left-eye image and the original right-eye image respectively according to the target image offset comparison table to generate a target left-eye image and a target right-eye image. In the above manner, the present application provides personalized distortion correction for different smart wearable devices by building matching waveguide distortion processing models for different preset smart wearable device types. By matching the target device type with the preset device type, the wide compatibility of the waveguide distortion processing model is ensured, which improves the synchronization of binocular images in smart wearable devices. At the same time, by determining the target image offset comparison table, the original image can be more accurately corrected for distortion, reducing visual distortion, thereby enhancing the user's immersion and comfort.

[0045] See also Figure 3 , Figure 3 This is a schematic flow chart of a binocular image dedistortion method provided in the third embodiment of the present application. Through calibration and distortion correction, the image quality of binocular images displayed by smart wearable devices is improved, and the impact of distortion on the visual experience is reduced. The corrected image is more realistic and natural, which enhances the user's immersion and comfort, and improves the overall user experience.

[0046] based on Figure 1 The embodiment shown, this embodiment Figure 3As shown, step S10 includes step S104 to step S105.

[0047] Step S104: acquiring a calibration image, and determining the calibration image displayed by the target smart wearable device as the image to be calibrated, wherein the calibration image is an undistorted image, and the image to be calibrated is a distorted image;

[0048] In a specific embodiment, an image without distortion is selected or created, and this image will be used as a calibration image, and it is ensured that the quality of the calibration image meets the calibration requirements, such as resolution, contrast, and brightness.

[0049] The calibration image is displayed through the target smart wearable device, that is, the calibration image displayed by the target smart wearable device passes through the waveguide and will be distorted, that is, the image to be calibrated.

[0050] Step S105: calibrate the image to be calibrated by using the target waveguide distortion processing model and the calibration image to determine the target image offset comparison table.

[0051] Specifically, the calibration image is compared with the image to be calibrated to analyze the distortion characteristics, such as the type, degree and distribution of distortion. In smart wearable devices, different smart wearable devices are prone to different types of distortion depending on the image acquisition components they are equipped with. Distortion types usually include barrel distortion and pincushion distortion. Barrel distortion refers to the distortion phenomenon caused by the optical system that the imaging picture is barrel-shaped and expanded, which is common in wide-angle lens imaging; pincushion distortion refers to the phenomenon that the imaging picture "contracts" toward the middle caused by the optical system, which is common in telephoto lens imaging.

[0052] The target waveguide distortion processing model is used to calculate the image offset according to the difference between the calibration image and the image to be calibrated, and the calculated offsets corresponding to all pixel points are organized into a target image offset comparison table.

[0053] This embodiment improves the image quality of binocular images displayed by smart wearable devices through calibration and distortion correction, reduces the impact of distortion on visual experience, and makes the corrected images more realistic and natural, thereby enhancing the user's sense of immersion and comfort and improving the overall user experience.

[0054] based on Figure 3 In the embodiment shown, in this embodiment, step S105 includes:

[0055] Acquire the calibration coordinate value of each calibration pixel point in the calibration image, and the coordinate value of the pixel point to be calibrated corresponding to each calibration pixel point in the image to be calibrated, wherein each calibration pixel point corresponds to each pixel point to be calibrated in a one-to-one manner;

[0056] Calculating pixel point offsets according to the calibrated coordinate values ​​and the coordinate values ​​to be calibrated;

[0057] According to the offset of each pixel point, the target image offset comparison table is determined.

[0058] Specifically, the coordinate values ​​of each calibration pixel in the calibration image are obtained. These coordinate values ​​are distortion-free, that is, the coordinate values ​​of each calibration pixel in the calibration image are used as reference standards. In the image to be calibrated captured by the target smart wearable device, the corresponding pixel points in the calibration image are found and their coordinate values ​​are obtained. In view of the transfer characteristics of waveguide technology, the coordinate values ​​of each pixel in the image to be calibrated are distorted and need to be corrected.

[0059] For each pair of corresponding calibrated pixels and pixels to be calibrated, calculate the difference between their coordinate values, which is the offset of the pixel, and record the offset of each pixel to provide data for the subsequent creation of the comparison table.

[0060] According to the calculated offset of each pixel point, a target image offset comparison table is created, and the target image offset comparison table corresponds the coordinate value in the calibration image to the corresponding offset.

[0061] In a specific embodiment, the pixel point offset is calculated according to each of the calibrated coordinate values ​​and each of the coordinate values ​​to be calibrated, including:

[0062] Acquire each calibration pixel point in the preset calibration image and each to-be-calibrated pixel point in each to-be-calibrated image;

[0063] The coordinate difference between each of the calibrated pixel points and the corresponding pixel point to be calibrated is calculated, and each of the coordinate differences is determined as the pixel point offset.

[0064] Specifically, a calibration image is selected and displayed through the waveguide. Traditional calibration patterns (such as checkerboard patterns, dot arrays, grid patterns, or stripe patterns) can only provide information at the corresponding corner points, and the camera needs to shoot multiple times to calculate the distortion of the entire image. Using a deep learning model, the difference between each pixel in the image to be calibrated and the calibration image taken by the smart wearable device is calculated only once, and a distorted image I is obtained in advance after being transmitted through the waveguide. dist (x,y) and a calibration image I ref (x, y), the calibration image is a distortion-free image, and their resolutions are the same. The degree of image distortion is quantified by calculating the offset between the two at each pixel position (x, y). The offset can be calculated using the following formula:

[0065] ΔI(x,y)=I dist (x,y)-Iref (x, y), ΔI(x, y) is the offset of each pixel.

[0066] Based on the above embodiments, the present application generates an accurate pixel offset by accurately calculating the coordinate difference between the calibrated pixel points and the pixel points to be calibrated, thereby providing relatively different distortion elimination methods for different types of smart wearable devices, thereby optimizing the performance of the smart wearable devices, so that various smart wearable devices can provide stable and reliable display effects in different application scenarios, and improve the synchronization of binocular images.

[0067] In a specific embodiment, step S20 includes:

[0068] Respectively obtain the coordinate value of each original left-eye pixel point in the original left-eye image and the coordinate value of each original right-eye pixel point in the original right-eye image;

[0069] The original left-eye pixel point coordinate value and the original right-eye pixel point coordinate value are respectively corrected by the target image offset comparison table to generate a target left-eye pixel point coordinate value and a target right-eye pixel point coordinate value;

[0070] The target left-eye image and the target right-eye image are generated according to the target left-eye pixel coordinate values ​​and the target right-eye pixel coordinate values ​​respectively.

[0071] In the specific embodiment, the original left-eye image is taken as an example for explanation. Assume that there are only two original left-eye pixel coordinates in the original left-eye image, namely A(X a , Y a ) and B(X b , Y b ), and the pixel offset corresponding to point A is (ΔX a , ΔY a ), the pixel offset corresponding to point B is (ΔX b , ΔY b ), then the coordinates of the left pixel point after distortion correction are calculated according to the coordinates of point A and point B and their corresponding pixel offsets. The specific calculation method is as follows:

[0072] For point A:

[0073] The corrected left pixel coordinate value A(X A , Y A )=(X a +ΔX a , Y a +ΔY a );

[0074] For point B:

[0075] The corrected left pixel coordinate value B(X B , Y B )=(X b +ΔX b , Y b +ΔY b ).

[0076] For the original left-eye image with only two original left-eye pixel coordinates, after the two points A and B are distorted, the target left-eye image obtained is the image after distortion elimination. The distortion elimination process of the target right-eye image is the same as that of the target left-eye image.

[0077] It can be understood that, for ease of understanding, this embodiment only simplifies the number of original left-eye pixel coordinates, and does not impose any restrictions on the number of original left-eye pixel coordinates in actual applications.

[0078] In a specific embodiment, the original left-eye pixel coordinate value and the original right-eye pixel coordinate value are respectively corrected by the target image offset comparison table to generate the target left-eye pixel coordinate value and the target right-eye pixel coordinate value, respectively, including:

[0079] Determine the pixel point offsets corresponding to the original left-eye pixel point coordinate values ​​and the original right-eye pixel point coordinate values ​​from the target image offset comparison table;

[0080] Generate the target left-eye pixel coordinate value according to each of the original left-eye pixel coordinate values ​​and each of the pixel offsets;

[0081] The target right-eye pixel coordinate value is generated according to each of the original right-eye pixel coordinate values ​​and each of the pixel offsets.

[0082] Specifically, the correction process of the right image is similar to that of the left image. right (x, y) also needs to use the target waveguide distortion processing model for distortion correction. As in the above embodiment, the target image offset comparison table LUT right (x, y) records the offset Δx, Δy between each pixel of the right eye image and the standard image. The correction formula for the right eye image is:

[0083] is the target right eye image, and the target right eye image corrected by the correction formula will also be corrected to a distortion-free state.

[0084] See also Figure 4 , Figure 4The embodiment of the present application provides a schematic block diagram of a binocular image dedistortion device, which is used to perform the above binocular image dedistortion method. The binocular image dedistortion device can be configured on a server.

[0085] like Figure 4 As shown, the binocular image dedistortion device 400 includes:

[0086] An offset comparison table determination module 410 is used to determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model;

[0087] The target image dedistortion module 420 is used to obtain the original left eye image and the original right eye image through the target smart wearable device, and perform distortion correction on the original left eye image and the original right eye image according to the target image offset comparison table to generate a target left eye image and a target right eye image.

[0088] Furthermore, the offset comparison table determination module 410 includes:

[0089] A waveguide distortion processing model determination submodule, used to determine at least one preset waveguide distortion processing model matching each preset smart wearable device according to a preset device type of each preset smart wearable device;

[0090] A device type matching submodule, used to match the target device type of the target smart wearable device with each of the preset device types;

[0091] The target waveguide distortion processing model determination submodule is used to determine the preset waveguide distortion processing model corresponding to the preset device type matching the target device type as the target waveguide distortion processing model.

[0092] Furthermore, the offset comparison table determination module 410 includes:

[0093] A calibration image and to-be-calibrated image acquisition submodule, used to acquire a calibration image, and determine the calibration image displayed by the target smart wearable device as the to-be-calibrated image, wherein the calibration image is a distortion-free image, and the to-be-calibrated image is a distorted image;

[0094] The target image offset comparison table determination submodule is used to calibrate the image to be calibrated by using the target waveguide distortion processing model and the calibration image to determine the target image offset comparison table.

[0095] Furthermore, the target image offset comparison table determination submodule includes:

[0096] A calibration coordinate value and to-be-calibrated coordinate value acquisition unit, used to acquire the calibration coordinate value of each calibration pixel point in the calibration image, and the to-be-calibrated coordinate value of the to-be-calibrated pixel point corresponding to each calibration pixel point in the to-be-calibrated image, wherein each calibration pixel point corresponds to each to-be-calibrated pixel point in a one-to-one manner;

[0097] A pixel point offset calculation unit, used for calculating a pixel point offset according to each of the calibrated coordinate values ​​and each of the coordinate values ​​to be calibrated;

[0098] The target image offset comparison table determining unit is used to determine the target image offset comparison table according to the offset of each pixel point.

[0099] Furthermore, the pixel offset calculation unit includes:

[0100] A pixel point acquisition subunit, used for acquiring each calibration pixel point in the preset calibration image and each pixel point to be calibrated in each image to be calibrated;

[0101] The pixel point offset calculation subunit is used to calculate the coordinate difference between each of the calibrated pixel points and the corresponding pixel point to be calibrated, and determine each of the coordinate differences as the pixel point offset.

[0102] Furthermore, the target image dedistortion module 420 includes:

[0103] The original pixel point coordinate value acquisition submodule is used to respectively acquire the coordinate value of each original left-eye pixel point in the original left-eye image and the coordinate value of each original right-eye pixel point in the original right-eye image;

[0104] A target pixel point coordinate value generating submodule is used to respectively correct the original left-eye pixel point coordinate value and the original right-eye pixel point coordinate value through the target image offset comparison table to generate a target left-eye pixel point coordinate value and a target right-eye pixel point coordinate value respectively;

[0105] The target image generation submodule is used to generate the target left-eye image and the target right-eye image according to the target left-eye pixel coordinate values ​​and the target right-eye pixel coordinate values ​​respectively.

[0106] Furthermore, the target pixel point coordinate value generation submodule includes:

[0107] A pixel offset determination unit, used to determine the pixel offsets corresponding to the original left-eye pixel coordinate values ​​and the original right-eye pixel coordinate values ​​from the target image offset comparison table;

[0108] A target left-eye pixel point coordinate value generating unit, used for generating the target left-eye pixel point coordinate value according to each of the original left-eye pixel point coordinate values ​​and each of the pixel point offsets;

[0109] The target right pixel point coordinate value generating unit is used to generate the target right pixel point coordinate value according to each of the original right pixel point coordinate values ​​and each of the pixel point offsets.

[0110] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0111] The above-mentioned device can be implemented in the form of a computer program. Figure 5 The system runs on the smart wearable device shown.

[0112] See also Figure 5 , Figure 5 1 is a schematic block diagram of the structure of a smart wearable device provided in an embodiment of the present application. The smart wearable device may be a server.

[0113] See also Figure 5 The smart wearable device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0114] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any binocular image dedistortion method.

[0115] The processor is used to provide computing and control capabilities to support the operation of the entire smart wearable device.

[0116] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any binocular image dedistortion method.

[0117] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the smart wearable device to which the scheme of the present application is applied. The specific smart wearable device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0119] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0120] Determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model;

[0121] The original left-eye image and the original right-eye image are acquired through the target smart wearable device, and the original left-eye image and the original right-eye image are respectively subjected to distortion correction according to the target image offset comparison table to generate a target left-eye image and a target right-eye image.

[0122] In one embodiment, a target waveguide distortion processing model is determined by a target smart wearable device to achieve:

[0123] According to the preset device type of each preset smart wearable device, determining at least one preset waveguide distortion processing model matching each of the preset smart wearable devices;

[0124] Matching the target device type of the target smart wearable device with each of the preset device types;

[0125] The preset waveguide distortion processing model corresponding to the preset device type matching the target device type is determined as the target waveguide distortion processing model.

[0126] In one embodiment, according to the target smart wearable device and the target waveguide distortion processing model, a target image offset comparison table corresponding to the target smart wearable device is determined to achieve:

[0127] Acquire a calibration image, and determine the calibration image displayed by the target smart wearable device as an image to be calibrated, wherein the calibration image is an undistorted image, and the image to be calibrated is a distorted image;

[0128] The image to be calibrated is calibrated by using the target waveguide distortion processing model and the calibration image to determine the target image offset comparison table.

[0129] In one embodiment, the image to be calibrated is calibrated by using the target waveguide distortion processing model and the calibration image to determine the target image offset comparison table, which is used to achieve:

[0130] Acquire the calibration coordinate value of each calibration pixel point in the calibration image, and the coordinate value of the pixel point to be calibrated corresponding to each calibration pixel point in the image to be calibrated, wherein each calibration pixel point corresponds to each pixel point to be calibrated in a one-to-one manner;

[0131] Calculating pixel point offsets according to the calibrated coordinate values ​​and the coordinate values ​​to be calibrated;

[0132] According to the offset of each pixel point, the target image offset comparison table is determined.

[0133] In one embodiment, the pixel point offset is calculated according to each of the calibrated coordinate values ​​and each of the coordinate values ​​to be calibrated, so as to achieve:

[0134] Acquire each calibration pixel point in the preset calibration image and each to-be-calibrated pixel point in each to-be-calibrated image;

[0135] The coordinate difference between each of the calibrated pixel points and the corresponding pixel point to be calibrated is calculated, and each of the coordinate differences is determined as the pixel point offset.

[0136] In one embodiment, the original left-eye image and the original right-eye image are respectively subjected to distortion correction according to the target image offset comparison table to generate a target left-eye image and a target right-eye image, so as to achieve:

[0137] Respectively obtain the coordinate value of each original left-eye pixel point in the original left-eye image and the coordinate value of each original right-eye pixel point in the original right-eye image;

[0138] The original left-eye pixel point coordinate value and the original right-eye pixel point coordinate value are respectively corrected by the target image offset comparison table to generate a target left-eye pixel point coordinate value and a target right-eye pixel point coordinate value;

[0139] The target left-eye image and the target right-eye image are generated according to the target left-eye pixel coordinate values ​​and the target right-eye pixel coordinate values ​​respectively.

[0140] In one embodiment, the original left pixel coordinate value and the original right pixel coordinate value are respectively corrected by the target image offset comparison table to generate the target left pixel coordinate value and the target right pixel coordinate value, respectively, for achieving:

[0141] Determine the pixel point offsets corresponding to the original left-eye pixel point coordinate values ​​and the original right-eye pixel point coordinate values ​​from the target image offset comparison table;

[0142] Generate the target left-eye pixel coordinate value according to each of the original left-eye pixel coordinate values ​​and each of the pixel offsets;

[0143] The target right-eye pixel coordinate value is generated according to each of the original right-eye pixel coordinate values ​​and each of the pixel offsets.

[0144] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any binocular image dedistortion method provided in the embodiment of the present application.

[0145] The computer-readable storage medium may be an internal storage unit of the smart wearable device described in the foregoing embodiment, such as a hard disk or memory of the smart wearable device. The computer-readable storage medium may also be an external storage device of the smart wearable device, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card), etc., equipped on the smart wearable device.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A binocular image dedistortion method, characterized in that: include: Determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model; The original left-eye image and the original right-eye image are acquired through the target smart wearable device, and the original left-eye image and the original right-eye image are respectively subjected to distortion correction according to the target image offset comparison table to generate a target left-eye image and a target right-eye image.

2. The binocular image dedistortion method according to claim 1, characterized in that: The step of determining a target waveguide distortion processing model by using a target smart wearable device includes: According to the preset device type of each preset smart wearable device, determining at least one preset waveguide distortion processing model matching each of the preset smart wearable devices; Matching the target device type of the target smart wearable device with each of the preset device types; The preset waveguide distortion processing model corresponding to the preset device type matching the target device type is determined as the target waveguide distortion processing model.

3. The binocular image dedistortion method according to claim 1, characterized in that: The step of determining a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model includes: Acquire a calibration image, and determine the calibration image displayed by the target smart wearable device as an image to be calibrated, wherein the calibration image is an undistorted image, and the image to be calibrated is a distorted image; The image to be calibrated is calibrated using the target waveguide distortion processing model and the calibration image to determine the target image offset comparison table.

4. The binocular image dedistortion method according to claim 3, characterized in that: The step of calibrating the image to be calibrated by using the target waveguide distortion processing model and the calibration image to determine the target image offset comparison table includes: Acquire the calibration coordinate value of each calibration pixel point in the calibration image, and the coordinate value of the pixel point to be calibrated corresponding to each calibration pixel point in the image to be calibrated, wherein each calibration pixel point corresponds to each pixel point to be calibrated in a one-to-one manner; Calculating pixel point offsets according to the calibrated coordinate values ​​and the coordinate values ​​to be calibrated; According to the offset of each pixel point, the target image offset comparison table is determined.

5. The binocular image dedistortion method according to claim 4, characterized in that: The calculating the pixel point offset according to each of the calibrated coordinate values ​​and each of the coordinate values ​​to be calibrated includes: Acquire each calibration pixel point in the preset calibration image and each to-be-calibrated pixel point in each to-be-calibrated image; The coordinate difference between each of the calibrated pixel points and the corresponding pixel point to be calibrated is calculated, and each of the coordinate differences is determined as the pixel point offset.

6. The binocular image dedistortion method according to claim 1, characterized in that: The step of respectively performing distortion correction on the original left-eye image and the original right-eye image according to the target image offset comparison table to generate a target left-eye image and a target right-eye image comprises: Respectively obtain the coordinate value of each original left-eye pixel point in the original left-eye image and the coordinate value of each original right-eye pixel point in the original right-eye image; The original left-eye pixel point coordinate value and the original right-eye pixel point coordinate value are respectively corrected by the target image offset comparison table to generate a target left-eye pixel point coordinate value and a target right-eye pixel point coordinate value; The target left-eye image and the target right-eye image are generated according to the target left-eye pixel coordinate values ​​and the target right-eye pixel coordinate values ​​respectively.

7. The binocular image dedistortion method according to claim 6, characterized in that: The method of respectively correcting the original left-eye pixel coordinate value and the original right-eye pixel coordinate value by using the target image offset comparison table to generate a target left-eye pixel coordinate value and a target right-eye pixel coordinate value respectively includes: Determine the pixel point offsets corresponding to the original left-eye pixel point coordinate values ​​and the original right-eye pixel point coordinate values ​​from the target image offset comparison table; Generate the target left-eye pixel coordinate value according to each of the original left-eye pixel coordinate values ​​and each of the pixel offsets; The target right-eye pixel coordinate value is generated according to each of the original right-eye pixel coordinate values ​​and each of the pixel offsets.

8. A binocular image dedistortion device, characterized in that: include: An offset comparison table determination module is used to determine a target waveguide distortion processing model through a target smart wearable device, and determine a target image offset comparison table corresponding to the target smart wearable device according to the target smart wearable device and the target waveguide distortion processing model; The target image dedistortion module is used to obtain the original left-eye image and the original right-eye image through the target smart wearable device, and perform distortion correction on the original left-eye image and the original right-eye image according to the target image offset comparison table to generate a target left-eye image and a target right-eye image.

9. A smart wearable device, characterized in that: The smart wearable device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the binocular image dedistortion method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the binocular image dedistortion method according to any one of claims 1 to 7.

Images