Distortion detection method, device, apparatus and storage medium

Abstract

The application discloses a distortion detection method, device and equipment and a storage medium. The method comprises the following steps: acquiring a distortion imaging image of an augmented reality (AR) glasses to be detected; performing contour extraction on each feature detection area in the distortion imaging image to obtain a contour detection area corresponding to each feature detection area; and detecting whether the AR glasses to be detected generates distortion according to the area distance between each contour detection area. The embodiment of the application realizes automatic detection of AR glasses distortion.

Description

Distortion detection methods, devices, equipment and storage media Technical Field

[0001] This invention relates to the field of imaging quality detection technology, and in particular to a distortion detection method, apparatus, device, and storage medium. Background Technology

[0002] With the rapid development of information technology, the ways in which humans acquire and process information have shifted from a singular to a diversified approach. AR (Augmented Reality) glasses, as a medium for human-computer information transmission and interaction, have developed rapidly in the past few years.

[0003] As a visual aid, the image quality of AR glasses directly impacts the user experience. Distortion is a crucial indicator for evaluating the quality of an optical system. With the continuous upgrades to AR glasses, the field of view has gradually increased to provide a better sense of immersion, leading to severe distortion of the image plane and affecting the viewing experience. In certain measurement applications based on AR glasses, the impact of distortion is even more significant.

[0004] Current distortion detection solutions mostly rely on customized development, and the detection equipment is relatively large. Therefore, developing a simple and universal solution for automated and effective distortion detection in AR glasses has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a distortion detection method, apparatus, device, and storage medium to achieve automated detection of distortion in AR glasses.

[0006] According to one aspect of the present invention, a distortion detection method is provided, the method comprising:

[0007] Obtain the distortion image of the augmented reality (AR) glasses under test;

[0008] Contour extraction is performed on each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region;

[0009] Based on the regional distance between each of the contour detection regions, it is determined whether the AR glasses under test have distortion.

[0010] According to another aspect of the present invention, a distortion detection device is provided, the device comprising:

[0011] The distortion image acquisition module is used to acquire the distortion image of the augmented reality (AR) glasses under test.

[0012] The contour detection region determination module is used to extract the contours of each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region.

[0013] The distortion detection module is used to detect whether the AR glasses under test have distortion based on the regional distance between each of the contour detection areas.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the distortion detection method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the distortion detection method according to any embodiment of the present invention.

[0019] This invention's embodiment extracts the contours of each feature detection region in the distorted image of the AR glasses under test, obtaining the corresponding contour detection region. Based on the distance between these contour detection regions, it detects whether the AR glasses under test have distortion, thus achieving automated distortion detection. In this method, distortion detection of AR glasses under test can be effectively achieved without the need for bulky, custom-developed distortion detection equipment, improving detection efficiency and saving significant manpower and material resources. Furthermore, this distortion detection solution is universal and applicable to distortion detection of various types of AR glasses.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1A is a flowchart of a distortion detection method according to Embodiment 1 of the present invention;

[0023] Figure 1B is a schematic diagram of a distortion image acquisition device according to Embodiment 1 of the present invention;

[0024] Figure 1C is a distortion detection image provided according to Embodiment 1 of the present invention;

[0025] Figure 1D is a schematic diagram of the contour detection region of a binarized distortion image provided in Embodiment 1 of the present invention;

[0026] Figure 2A is a flowchart of a distortion detection method according to Embodiment 2 of the present invention;

[0027] Figure 2B is a schematic diagram of the contour detection area of ​​a distorted image provided according to Embodiment 2 of the present invention;

[0028] Figure 3A is a flowchart of a distortion detection method according to Embodiment 3 of the present invention;

[0029] Figure 3B is a schematic diagram of the distortion of an AR glasses under test according to Embodiment 3 of the present invention;

[0030] Figure 4 is a schematic diagram of a distortion detection device according to Embodiment 4 of the present invention;

[0031] Figure 5 is a schematic diagram of the structure of an electronic device that implements the distortion detection method of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1A is a flowchart of a distortion detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the distortion detection of AR glasses. The method can be executed by a distortion detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. As shown in Figure 1A, the method includes:

[0036] S110. Obtain the distorted image of the augmented reality (AR) glasses under test.

[0037] The distortion image can be obtained by acquiring the AR glasses under test by projecting the distortion detection image onto them using an image acquisition device. For example, the image acquisition device can be a camera. The distortion detection image can be a label image with at least one feature detection point. The position and number of feature detection points can be preset in the distortion detection image by relevant technicians according to actual needs.

[0038] It should be noted that during the process of acquiring the distorted image of the AR glasses under test by the image acquisition device, the center of the waveguide plate at the end of the AR glasses under test needs to coincide with the midline of the visual axis. The midline of the visual axis is also the center line of the relative position between the human eye and the AR glasses under test.

[0039] During the acquisition of distortion images, technicians can use handheld image acquisition devices to capture distortion images of the AR glasses under test. However, this method may be susceptible to camera shake during the acquisition process, resulting in lower accuracy of the acquired distortion images. To further improve the accuracy of distortion image acquisition and thus the accuracy of subsequent distortion detection of the AR glasses under test, the following device can be used to acquire distortion images.

[0040] Figure 1B shows a schematic diagram of a distortion image acquisition device. This device includes a lens 1, a camera 2, a camera mounting bracket 3, AR glasses under test 4, and glasses mounting bracket 5. The lens 1 is positioned directly above the center of the field of view of the AR glasses under test 4. Specifically, the camera 2 is connected to the camera mounting bracket 3 via the space on the upper platform 6. The lower platform 7 is used to fix the camera mounting bracket 3 onto the optical platform. One side of the AR glasses under test 4 is pressed tightly against the rubber pad 10, and the other side is pressed tightly against the rubber pad 9 of the reinforcing block 8. The T-shaped slide rail of the reinforcing block 8 is inserted into the T-shaped slide groove of the glasses mounting bracket 5. The reinforcing block 8 and the glasses mounting bracket 5 are pressed together using the fixing bolts on the reinforcing block 8. The glasses mounting bracket 5 is adjusted so that the center of the waveguide plate on the side of the AR glasses under test coincides with the centerline 11 of the visual axis. After the AR glasses 4 to be tested are fixed in place, the camera 2 can capture images of the AR glasses 4 with the projected distortion detection image through the lens 1, and obtain the distortion image of the AR glasses 4 to be tested.

[0041] S120. Extract the contours of each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region.

[0042] In this context, the feature detection regions correspond to the feature detection points on the distortion detection image; specifically, each feature detection point corresponds to a specific feature detection region. Figure 1C shows a distortion detection image. The gray square areas in the image represent the feature detection regions. The distortion detection image in Figure 1C contains nine feature detection regions.

[0043] For example, a preset binarization segmentation algorithm can be used to dynamically binarize the distorted image, resulting in a binarized distorted image. The binarization segmentation algorithm can be preset by relevant technical personnel; for example, it could be the OTSU (Otsu Thresholding) algorithm. A preset contour localization method is then used to extract contours from the binarized distorted image, obtaining the contour detection regions corresponding to each feature detection region. Figure 1D shows a schematic diagram of the contour detection regions of a binarized distorted image. For example, the findContours function from the OpenCV machine learning software library can be used for contour extraction.

[0044] S130. Based on the area distance between each contour detection area, detect whether the AR glasses under test have distortion.

[0045] For example, the center coordinates of each contour detection area can be determined, and the distance between each contour detection area can be determined based on the center coordinates of each area. Thus, the distortion of the AR glasses under test can be detected based on the distance between the areas.

[0046] For example, the coordinates of the center of each contour detection area are determined as follows:

[0047]

[0048] Among them, (x i ,y i () represents the coordinates of the center of the i-th contour detection region; Represents the x-coordinate of the j-th pixel in the i-th contour detection region; This represents the ordinate of the j-th pixel in the i-th contour detection region. M represents the number of contour detection regions; N represents the number of pixels on the i-th contour.

[0049] In one optional embodiment, detecting whether the AR glasses under test have distortion based on the area distance between each contour detection area includes: determining at least one reference contour detection area in the same preset reference direction; and detecting whether the AR glasses under test have distortion in the preset reference direction based on the area distance between each reference contour detection area.

[0050] The preset reference direction can include a horizontal direction and a vertical direction. Correspondingly, the reference contour detection area in the horizontal direction is called the horizontal contour detection area, and the reference contour detection area in the vertical direction is called the vertical contour detection area. Specifically, the horizontal contour detection area is used to detect whether the AR glasses under test produce vertical distortion in the horizontal direction; the vertical contour detection area is used to detect whether the AR glasses under test produce horizontal distortion in the vertical direction.

[0051] For example, at least one horizontal contour detection region is determined in the horizontal direction, and the horizontal region distance of the at least one horizontal contour detection region in the horizontal direction is determined. If the horizontal region distances are the same, it is determined that the AR glasses under test do not have vertical distortion in the horizontal direction; if the horizontal region distances are different, it is determined that the AR glasses under test have vertical distortion in the horizontal direction.

[0052] For example, at least one vertical contour detection region is determined in the vertical direction, and the vertical region distance of the at least one vertical contour detection region in the vertical direction is determined. If the vertical region distances are the same, it is determined that the AR glasses under test do not have horizontal distortion in the vertical direction; if the vertical region distances are different, it is determined that the AR glasses under test have horizontal distortion in the vertical direction.

[0053] This optional embodiment detects whether the AR glasses under test have distortion in a preset reference direction by measuring the area distance between each reference contour detection area. This achieves accurate detection of whether the AR glasses under test have vertical distortion in the horizontal direction and accurate detection of whether the AR glasses under test have horizontal distortion in the vertical direction.

[0054] This invention's embodiment extracts the contours of each feature detection region in the distorted image of the AR glasses under test, obtaining the corresponding contour detection region. Based on the distance between these contour detection regions, it detects whether the AR glasses under test have distortion, thus achieving automated distortion detection. In this method, distortion detection of AR glasses under test can be effectively achieved without the need for bulky, custom-developed distortion detection equipment, improving detection efficiency and saving significant manpower and material resources. Furthermore, this distortion detection solution is universal and applicable to distortion detection of various types of AR glasses.

[0055] Example 2

[0056] Figure 2A is a flowchart of a distortion detection method provided in Embodiment 2 of the present invention. This embodiment is an optimization and improvement based on the above technical solutions.

[0057] Furthermore, the step "detecting whether the AR glasses under test are distorted based on the area distance between each contour detection area" is refined to "determining at least one reference contour detection area in the same preset reference direction; detecting whether the AR glasses under test are distorted in the preset reference direction based on the area distance between each reference contour detection area".

[0058] Furthermore, the preset reference direction includes the horizontal direction; the reference contour detection area includes the horizontal contour detection area; accordingly, the step "determine at least one reference contour detection area in the same preset reference direction" is refined to "determine at least one horizontal contour detection area with a horizontal correlation in the horizontal direction". Similarly, the step "detect whether the AR glasses under test produce distortion in the preset reference direction based on the area distance between each reference contour detection area" is refined to "detect whether the AR glasses under test produce vertical distortion in the horizontal direction based on the area distance between each horizontal contour detection area". This improves the detection method for whether the AR glasses under test produce vertical distortion.

[0059] As shown in Figure 2A, the method includes the following specific steps:

[0060] S210. Obtain the distorted image of the augmented reality (AR) glasses to be tested.

[0061] S220. Extract the contours of each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region.

[0062] S230. Determine at least one horizontal contour detection region that has a horizontal correlation in the horizontal direction.

[0063] A horizontally correlated horizontal contour detection region can be at least one horizontal contour detection region on the same horizontal axis in a distorted image.

[0064] In an optional embodiment, determining at least one horizontal contour detection region having a horizontal correlation in the horizontal direction includes: taking the leftmost and rightmost contour detection regions located on the same horizontal line in the distorted image as a group of horizontal contour detection regions to obtain at least one horizontal contour detection group; wherein each horizontal contour detection region in each horizontal contour detection group has a horizontal correlation.

[0065] For example, Figure 2B shows a schematic diagram of the contour detection region of a distorted image. This schematic diagram of the contour detection region corresponding to the distorted image contains nine contour detection regions. Contour detection regions A, B, and C are located on the same horizontal line; contour detection regions D, E, and F are located on the same horizontal line; and contour detection regions G, H, and I are located on the same horizontal line.

[0066] Among the contour detection regions A, B, and C located on the same horizontal line, contour detection region A is the leftmost contour detection region on the horizontal line, and contour detection region C is the rightmost contour detection region on the horizontal line. Therefore, contour detection regions A and C can be considered as a horizontal contour detection region group. Similarly, among the contour detection regions D, E, and F located on the same horizontal line, contour detection region D is the leftmost contour detection region on the horizontal line, and contour detection region F is the rightmost contour detection region on the horizontal line. Therefore, contour detection regions D and F can be considered as a horizontal contour detection region group. Likewise, among the contour detection regions G, H, and I located on the same horizontal line, contour detection region G is the leftmost contour detection region on the horizontal line, and contour detection region I is the rightmost contour detection region on the horizontal line. Therefore, contour detection regions G and I can be considered as a horizontal contour detection region group. Thus, this distortion image can correspond to three horizontal contour detection region groups.

[0067] S240. Based on the area distance between each horizontal contour detection area, detect whether the AR glasses under test produce vertical distortion in the horizontal direction.

[0068] For example, the center point of each horizontal contour detection area can be determined, and the distance between each horizontal contour area can be determined based on the center point of each area, thereby further detecting whether the AR glasses produce vertical distortion in the horizontal direction.

[0069] In one optional embodiment, detecting whether the AR glasses under test produce vertical distortion in the horizontal direction based on the area distance between each horizontal contour detection area includes: defining a first horizontal detection area group as the group of horizontal contour detection areas whose horizontal contour detection areas are located at the center of the distorted image; and defining a second horizontal detection area group as the group of horizontal contour detection areas whose horizontal contour detection areas are located at the bottom of the distorted image; determining a first horizontal area distance between each horizontal contour detection area in the first horizontal detection area group; and determining a second horizontal area distance between each horizontal contour detection area in the second horizontal detection area group; and detecting whether the AR glasses under test produce vertical distortion in the horizontal direction based on the first horizontal distance and the second horizontal distance.

[0070] Figure 2B shows a schematic diagram of the contour detection region of a distorted image. The first horizontal detection region group located at the center of the distorted image can be a horizontal contour detection region group including contour detection region A and contour detection region C. The second horizontal detection region group located at the bottom of the distorted image can be a horizontal contour detection region group including contour detection region D and contour detection region F.

[0071] The first horizontal distance between contour detection regions A and C in the first horizontal detection region group is determined; and the second horizontal distance between contour detection regions D and F in the second horizontal detection region group is determined. If the difference between the first and second horizontal distances is less than a preset distance difference threshold, the AR glasses under test are considered to have no vertical distortion in the horizontal direction. If the difference between the first and second horizontal distances is not less than the preset distance difference threshold, the AR glasses under test are considered to have vertical distortion in the horizontal direction. The distance difference threshold can be preset by relevant technicians; for example, the distance difference threshold can be 0.5 mm.

[0072] The distance between the first and second horizontal regions can be determined by the coordinates of the center point of each contour detection region.

[0073] If it is determined that the AR glasses under test produce vertical distortion in the horizontal direction, the following method for determining vertical distortion can be used to determine the vertical distortion produced by the AR glasses under test.

[0074]

[0075] Among them, V Distortion X represents the specific value of vertical distortion; X is the distance to the first horizontal region; X bottom This represents the distance to the second-level region.

[0076] This embodiment determines at least one horizontal contour detection region with a horizontal correlation in the horizontal direction. Based on the region distance between each horizontal contour detection region, it detects whether the AR glasses under test have vertical distortion in the horizontal direction, thus realizing the detection of whether the AR glasses under test have vertical distortion. By using the first horizontal distance within the first group of horizontal detection regions and the second horizontal distance within the second group of horizontal detection regions to detect whether the AR glasses under test have vertical distortion in the horizontal direction, the accuracy of vertical distortion detection for the AR glasses under test is improved.

[0077] Example 3

[0078] Figure 3A is a flowchart of a distortion detection method provided in Embodiment 3 of the present invention. This embodiment is an optimization and improvement based on the above technical solutions.

[0079] Furthermore, the step "detecting whether the AR glasses under test are distorted based on the area distance between each contour detection area" is refined to "determining at least one reference contour detection area in the same preset reference direction; detecting whether the AR glasses under test are distorted in the preset reference direction based on the area distance between each reference contour detection area".

[0080] Furthermore, the preset reference direction includes the vertical direction; the reference contour detection area includes the horizontal contour detection area; accordingly, the step "determine at least one reference contour detection area in the same preset reference direction" is refined to "determine at least one vertical contour detection area with a vertical correlation in the vertical direction". Similarly, the step "detect whether the AR glasses under test produce distortion in the preset reference direction based on the area distance between each reference contour detection area" is refined to "detect whether the AR glasses under test produce horizontal distortion in the vertical direction based on the area distance between each vertical contour detection area". This improves the detection method for whether the AR glasses under test produce horizontal distortion.

[0081] As shown in Figure 3A, the method includes the following specific steps:

[0082] S310. Obtain the distorted image of the augmented reality (AR) glasses under test.

[0083] S320. Extract the contours of each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region.

[0084] S330. Determine at least one vertical contour detection region that has a vertical correlation in the vertical direction.

[0085] A vertical contour detection region that has a vertical correlation in the vertical direction can be at least one vertical contour detection region on the same vertical axis in the distorted image.

[0086] In an optional embodiment, determining at least one vertical contour detection region that has a vertical correlation in the vertical direction includes: taking the uppermost and lowermost contour detection regions located on the same vertical line in the distorted image as a vertical contour detection region group to obtain at least one vertical contour detection group; wherein each vertical contour detection region in each vertical contour detection group has a vertical correlation.

[0087] For example, Figure 2B shows a schematic diagram of the contour detection region of a distorted image. This schematic diagram of the contour detection region corresponding to the distorted image contains nine contour detection regions. Specifically, contour detection regions H, B, and E are located on the same vertical line; contour detection regions G, A, and D are located on the same vertical line; and contour detection regions I, C, and F are located on the same vertical line.

[0088] Among the contour detection regions H, B, and E located on the same vertical line, contour detection region H is the uppermost contour detection region on the vertical line, and contour detection region E is the lowermost contour detection region on the vertical line. Therefore, contour detection regions H and E can be considered as a single vertical contour detection region group. Similarly, among the contour detection regions G, A, and D located on the same vertical line, contour detection region G is the uppermost contour detection region on the vertical line, and contour detection region D is the lowermost contour detection region on the vertical line. Therefore, contour detection regions G and D can be considered as a single vertical contour detection region group. Likewise, among the contour detection regions I, C, and F located on the same vertical line, contour detection region I is the uppermost contour detection region on the vertical line, and contour detection region F is the lowermost contour detection region on the vertical line. Therefore, contour detection regions I and F can be considered as a single vertical contour detection region group. Thus, this distortion image can correspond to three vertical contour detection region groups.

[0089] S340. Based on the area distance between each vertical contour detection area, detect whether the AR glasses under test produce horizontal distortion in the vertical direction.

[0090] For example, the center point of each vertical contour detection area can be determined, and the distance between each vertical contour area can be determined based on the center point of each area, thereby further detecting whether the AR glasses produce horizontal distortion in the horizontal direction.

[0091] In one optional embodiment, detecting whether the AR glasses under test produce horizontal distortion in the vertical direction based on the area distance between each vertical contour detection area includes: defining a first vertical detection area group as the vertical contour detection area group whose vertical contour detection areas are located at the center of the distorted image; and defining a second vertical detection area group as the vertical contour detection area group whose vertical contour detection areas are located at the rightmost position of the distorted image; determining a first vertical area distance between each vertical contour detection area in the first vertical detection area group; and determining a second vertical area distance between each vertical contour detection area in the second vertical detection area group; and detecting whether the AR glasses under test produce horizontal distortion in the vertical direction based on the first vertical distance and the second vertical distance.

[0092] Figure 2B shows a schematic diagram of the contour detection region of a distorted image. The first vertical detection region group, located at the center of the distorted image, can be a vertical contour detection region group including contour detection region H and contour detection region E. The second vertical detection region group, located at the rightmost position of the distorted image, can be a vertical contour detection region group including contour detection region I and contour detection region F.

[0093] The first vertical region distance between contour detection region H and contour detection region E in the first vertical detection region group is determined; and the second vertical region distance between contour detection region I and contour detection region F in the second vertical detection region group is determined. If the difference between the first and second vertical region distances is less than a preset distance difference threshold, it can be considered that the AR glasses under test do not produce horizontal distortion in the vertical direction. If the difference between the first and second vertical region distances is not less than the preset distance difference threshold, it can be considered that the AR glasses under test produce horizontal distortion in the vertical direction. The distance difference threshold can be preset by relevant technicians; for example, the distance difference threshold can be 0.5 mm.

[0094] The distance between the first vertical region and the distance between the second vertical region can be determined by the coordinates of the center point of each contour detection region.

[0095] If it is determined that the AR glasses under test produce horizontal distortion in the vertical direction, the following method for determining horizontal distortion can be used to determine the horizontal distortion produced by the AR glasses under test.

[0096]

[0097] Among them, H Distortion Y represents the specific value of horizontal distortion; Y is the distance of the first vertical region; Y left This represents the distance to the second vertical region.

[0098] Figure 3B shows a distortion diagram of an AR glasses under test. The AR glasses under test exhibit vertical distortion in the horizontal direction and horizontal distortion in the vertical direction.

[0099] This embodiment identifies at least one vertical contour detection region with a vertical correlation in the vertical direction. Based on the distance between these regions, it detects whether the AR glasses under test exhibit horizontal distortion in the vertical direction, thus achieving the detection of horizontal distortion in the AR glasses under test. By using a first vertical distance within a first group of vertical detection regions and a second vertical distance within a second group of vertical detection regions to detect whether the AR glasses under test exhibit horizontal distortion in the vertical direction, the accuracy of horizontal distortion detection for the AR glasses under test is improved.

[0100] Example 4

[0101] Figure 4 is a schematic diagram of a distortion detection device provided in Embodiment 4 of the present invention. The distortion detection device provided in this embodiment of the present invention is applicable to the distortion detection of AR glasses. This distortion detection device can be implemented in hardware and / or software. As shown in Figure 4, the device specifically includes: a distortion image acquisition module 401, a contour detection region determination module 402, and a distortion detection module 403.

[0102] The distortion image acquisition module 401 is used to acquire the distortion image of the augmented reality AR glasses under test;

[0103] The contour detection region determination module 402 is used to extract the contours of each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region.

[0104] The distortion detection module 403 is used to detect whether the AR glasses under test are distorted based on the area distance between each of the contour detection areas.

[0105] This invention's embodiment extracts the contours of each feature detection region in the distorted image of the AR glasses under test, obtaining the corresponding contour detection region. Based on the distance between these contour detection regions, it detects whether the AR glasses under test have distortion, thus achieving automated distortion detection. In this method, distortion detection of AR glasses under test can be effectively achieved without the need for bulky, custom-developed distortion detection equipment, improving detection efficiency and saving significant manpower and material resources. Furthermore, this distortion detection solution is universal and applicable to distortion detection of various types of AR glasses.

[0106] Optionally, the distortion detection module 403 includes:

[0107] A reference detection area determination unit is used to determine at least one reference contour detection area in the same preset reference direction;

[0108] The distortion detection unit is used to detect whether the AR glasses under test are distorted in the preset reference direction based on the area distance between each of the reference contour detection areas.

[0109] Optionally, the preset reference direction includes a horizontal direction; the reference contour detection area includes a horizontal contour detection area;

[0110] Accordingly, the reference detection area determination unit includes:

[0111] The horizontal detection region determination subunit is used to determine at least one horizontal contour detection region that has a horizontal correlation in the horizontal direction;

[0112] Accordingly, the distortion detection unit includes:

[0113] The vertical distortion detection subunit is used to detect whether the AR glasses under test produce vertical distortion in the horizontal direction based on the area distance between each of the horizontal contour detection areas.

[0114] Optionally, the preset reference direction includes a vertical direction; the reference contour detection area includes a horizontal contour detection area;

[0115] Accordingly, the reference detection area determination unit includes:

[0116] The vertical detection region determination subunit is used to determine at least one vertical contour detection region that has a vertical correlation in the vertical direction;

[0117] Accordingly, the distortion detection unit includes:

[0118] The horizontal distortion detection subunit is used to detect whether the AR glasses under test produce horizontal distortion in the vertical direction based on the area distance between each of the vertical contour detection areas.

[0119] Optionally, the horizontal detection region determining sub-unit is specifically used for:

[0120] In the distorted image, the leftmost and rightmost contour detection regions located on the same horizontal line are grouped into a horizontal contour detection region group to obtain at least one horizontal contour detection group; wherein, each horizontal contour detection region in each horizontal contour detection group has a horizontal correlation relationship.

[0121] Optionally, the vertical distortion detection subunit is specifically used for:

[0122] The horizontal contour detection region group whose horizontal contour detection region is located at the center position of the distorted image map is designated as the first horizontal detection region group; and...

[0123] The horizontal contour detection region group located at the bottom of the distorted image map is designated as the second horizontal detection region group.

[0124] Determine the first horizontal region distance between each horizontal contour detection region within the first horizontal detection region group; and,

[0125] Determine the distance between the second horizontal regions within the second horizontal detection region group;

[0126] Based on the first horizontal distance and the second horizontal distance, detect whether the AR glasses under test produce vertical distortion in the horizontal direction.

[0127] Optionally, the vertical detection region determining sub-unit is specifically used for:

[0128] In the distorted image, the uppermost and lowermost contour detection regions located on the same vertical line are grouped as a vertical contour detection region group to obtain at least one vertical contour detection group; wherein, each vertical contour detection region in each vertical contour detection group has a vertical correlation relationship.

[0129] Optionally, the horizontal distortion detection subunit is specifically used for:

[0130] The vertical contour detection region group located at the center of the distorted image map is designated as the first vertical detection region group; and...

[0131] The vertical contour detection region group located at the rightmost position of the distorted image map in each of the vertical contour detection region groups is regarded as the second vertical detection region group.

[0132] Determine the first vertical region distance between each vertical contour detection region within the first vertical detection region group; and,

[0133] Determine the distance between the second vertical regions within the second vertical detection region group;

[0134] Based on the first vertical distance and the second vertical distance, detect whether the AR glasses under test produce horizontal distortion in the vertical direction.

[0135] The distortion detection device provided in this embodiment of the invention can execute the distortion detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0136] Example 5

[0137] Figure 5 illustrates a schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0138] As shown in Figure 5, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded into the RAM 53 from storage unit 58. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0139] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0140] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as distortion detection methods.

[0141] In some embodiments, the distortion detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the distortion detection method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the distortion detection method by any other suitable means (e.g., by means of firmware).

[0142] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0146] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0147] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0148] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A distortion detection method, characterized in that, include: A distortion image of the augmented reality (AR) glasses under test is obtained; the distortion image is obtained by image acquisition of the AR glasses under test with a projected distortion detection image by an image acquisition device; contour extraction is performed on each feature detection region in the distortion image to obtain the contour detection region corresponding to each feature detection region; the feature detection region has a corresponding relationship with the feature detection point on the distortion detection image, and any feature detection point corresponds to a corresponding feature detection region. Identify at least one reference contour detection region in the same preset reference direction; The preset reference directions include a horizontal direction and a vertical direction; correspondingly, the reference contour detection area in the horizontal direction is the horizontal contour detection area, and the reference contour detection area in the vertical direction is the vertical contour detection area; the horizontal contour detection area in the horizontal direction is used to detect whether the AR glasses under test produce vertical distortion in the horizontal direction; the vertical contour detection area in the vertical direction is used to detect whether the AR glasses under test produce horizontal distortion in the vertical direction; based on the area distance between each of the reference contour detection areas, it is detected whether the AR glasses under test produce distortion in the preset reference direction.

2. The method according to claim 1, characterized in that, The preset reference direction includes a horizontal direction; the reference contour detection area includes a horizontal contour detection area; correspondingly, determining at least one reference contour detection area in the same preset reference direction includes: determining at least one horizontal contour detection area with a horizontal correlation in the horizontal direction; correspondingly, detecting whether the AR glasses under test produce distortion in the preset reference direction based on the area distance between each of the reference contour detection areas includes: detecting whether the AR glasses under test produce vertical distortion in the horizontal direction based on the area distance between each of the horizontal contour detection areas.

3. The method according to claim 1, characterized in that, The preset reference direction includes a vertical direction; the reference contour detection area includes a horizontal contour detection area; correspondingly, determining at least one reference contour detection area in the same preset reference direction includes: determining at least one vertical contour detection area with a vertical correlation in the vertical direction; correspondingly, detecting whether the AR glasses under test produce distortion in the preset reference direction based on the area distance between each of the reference contour detection areas includes: detecting whether the AR glasses under test produce horizontal distortion in the vertical direction based on the area distance between each of the vertical contour detection areas.

4. The method according to claim 2, characterized in that, The determination of at least one horizontal contour detection region having a horizontal correlation in the horizontal direction includes: taking the leftmost contour detection region and the rightmost contour detection region located on the same horizontal line in the distorted image as a horizontal contour detection region group to obtain at least one horizontal contour detection group; wherein, each horizontal contour detection region in each horizontal contour detection group has a horizontal correlation.

5. The method according to claim 4, characterized in that, The step of detecting whether the AR glasses under test produce vertical distortion in the horizontal direction based on the area distance between each of the horizontal contour detection areas includes: defining a first horizontal detection area group as the group of horizontal contour detection areas whose horizontal contour detection areas are located at the center of the distorted image; defining a second horizontal detection area group as the group of horizontal contour detection areas whose horizontal contour detection areas are located at the bottom of the distorted image; determining a first horizontal area distance between each horizontal contour detection area in the first horizontal detection area group; and determining a second horizontal area distance between each horizontal contour detection area in the second horizontal detection area group; and detecting whether the AR glasses under test produce vertical distortion in the horizontal direction based on the first horizontal area distance and the second horizontal area distance.

6. The method according to claim 3, characterized in that, The determination of at least one vertical contour detection region with a vertical correlation in the vertical direction includes: taking the uppermost and lowermost contour detection regions located on the same vertical line in the distorted image as a vertical contour detection region group to obtain at least one vertical contour detection group; wherein each vertical contour detection region in each vertical contour detection group has a vertical correlation.

7. The method according to claim 6, characterized in that, The step of detecting whether the AR glasses under test produce horizontal distortion in the vertical direction based on the regional distance between each of the vertical contour detection regions includes: defining a first vertical detection region group as the vertical contour detection region group whose vertical contour detection regions are located at the center of the distorted image; and defining a second vertical detection region group as the vertical contour detection region group whose vertical contour detection regions are located at the rightmost position of the distorted image; determining a first vertical regional distance between each vertical contour detection region in the first vertical detection region group; and determining a second vertical regional distance between each vertical contour detection region in the second vertical detection region group; and detecting whether the AR glasses under test produce horizontal distortion in the vertical direction based on the first vertical regional distance and the second vertical regional distance.

8. A distortion detection device, characterized in that, include: The distortion image acquisition module is used to acquire the distortion image of the augmented reality (AR) glasses under test; the distortion image is obtained by image acquisition of the AR glasses under test with a projected distortion detection image by an image acquisition device. The contour detection region determination module is used to extract the contours of each feature detection region in the distorted image to obtain the contour detection region corresponding to each feature detection region; the feature detection region has a corresponding relationship with the feature detection point on the distorted image, and any feature detection point corresponds to a corresponding feature detection region. The distortion detection module is used to detect whether the AR glasses under test have distortion based on the area distance between each of the contour detection areas. The distortion detection module includes: a reference detection area determination unit, used to determine at least one reference contour detection area in the same preset reference direction; The preset reference directions include a horizontal direction and a vertical direction; correspondingly, the reference contour detection area in the horizontal direction is a horizontal contour detection area, and the reference contour detection area in the vertical direction is a vertical contour detection area; the horizontal contour detection area in the horizontal direction is used to detect whether the AR glasses under test produce vertical distortion in the horizontal direction; the vertical contour detection area in the vertical direction is used to detect whether the AR glasses under test produce horizontal distortion in the vertical direction; the distortion detection unit is used to detect whether the AR glasses under test produce distortion in the preset reference directions based on the area distance between each of the reference contour detection areas.

9. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the distortion detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the distortion detection method according to any one of claims 1-7.

Images