Projector detection method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a projector detection method, device and equipment and a storage medium, which are used for automatically detecting whether a projector has a light leakage defect or not. The method comprises the following steps: acquiring a first image of a projection plane shot by a camera; the projection plane comprises a projection area and a non-projection area for projection imaging of the projector; acquiring angular point coordinates of a projection area in the first image; dividing a non-projection area into a plurality of sub-areas according to the angular point coordinates of the projection area; and obtaining feature information of each sub-region, and obtaining a detection result that whether the projector is qualified or not according to the feature information of each sub-region. According to the embodiment of the invention, the non-projection area is divided into a plurality of sub-areas, so that refined detection of the light leakage area is realized; the feature information of the sub-regions is acquired, so that tiny light leakage in a non-projection region can be more sensitively captured, and the detection precision of the light leakage is improved; through the automatic processing process, the requirement of manual visual inspection is reduced, and the detection speed is greatly improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of projection vision calibration, and in particular to projector detection methods, devices, equipment and storage media. Background Art

[0002] Projectors are used to display images and videos, and play an important role in modern conference rooms, education, home entertainment and other fields. A good projector should have high image quality, accurate color reproduction and clear details. Light leakage is one of the common quality problems of projectors, which will cause the image contrast to decrease, affect the viewing experience, and even make the content difficult to recognize.

[0003] Traditional projector inspection methods mainly rely on manual visual inspection or simple automated equipment. Manual visual inspection requires direct observation of the projected image with the human eye to check whether there is a light leakage area. This method is inefficient, easily affected by subjective factors, and is not practical on the production line. Using automated equipment, such as optical instruments, to test the brightness and contrast of the projected image often fails to accurately locate the light leakage area, and has limited detection capabilities for tiny light leaks. Summary of the invention

[0004] Based on the above problems, the embodiments of the present application provide a projector detection method, device, equipment and storage medium, the purpose of which is to automatically and accurately detect whether there is a light leakage defect in the projector, so as to improve the detection efficiency and accuracy.

[0005] In a first aspect, an embodiment of the present application provides a projector detection method, comprising:

[0006] Acquire a first image of a projection plane captured by a camera; the projection plane includes a projection area and a non-projection area where the projector projects an image;

[0007] Obtaining the coordinates of the corner points of the projection area in the first image;

[0008] Dividing the non-projection area into a plurality of sub-areas according to the coordinates of the corner points of the projection area;

[0009] Acquire characteristic information of each of the sub-areas, and obtain a test result of whether the projector is qualified according to the characteristic information of each of the sub-areas.

[0010] In one embodiment, obtaining the coordinates of corner points of the projection area in the first image includes:

[0011] Acquire the intrinsic parameter matrix and distortion coefficient of the camera, and use the intrinsic parameter matrix and the distortion coefficient to perform distortion correction on the second image to obtain a corrected second image; the second image is obtained by photographing the camera after projecting a preset calibration image onto a projection plane using the projector;

[0012] Calculating a mapping matrix according to the coordinates of the corner points of the corrected second image in the camera image coordinate system and the coordinates of the corner points of the preset calibration image in the display screen coordinate system;

[0013] According to the mapping matrix, the coordinates of the corner points of the projection area in the first image in the display screen coordinate system are obtained.

[0014] In one embodiment, the characteristic information of the sub-region includes the light signal intensity of the sub-region; and acquiring the characteristic information of each of the sub-regions and obtaining a test result of whether the projector is qualified according to the characteristic information of each of the sub-regions includes:

[0015] Calculating the optical signal intensity of each of the sub-areas;

[0016] If the light signal intensity of each of the sub-areas is not greater than the first preset threshold, determining that the projector is qualified;

[0017] If the light signal intensity of any of the sub-areas is greater than the first preset threshold, it is determined that the projector is unqualified.

[0018] In one embodiment, the feature information of the sub-region includes a feature map extracted in the sub-region by a classification model; the acquiring the feature information of each sub-region and obtaining a test result of whether the projector is qualified according to the feature information of each sub-region includes:

[0019] Dividing the first image according to the boundary of each sub-region to obtain a plurality of sub-region images;

[0020] Input each sub-region image into a classification model, and output the category to which each sub-region belongs;

[0021] If the category to which each of the sub-areas belongs indicates that there is no light leakage, then the projector is determined to be qualified;

[0022] If any of the sub-areas has a category representation indicating light leakage, determining that the projector is unqualified;

[0023] The classification model includes a feature extraction sub-model and a classification sub-model.

[0024] The feature extraction sub-model includes a convolution layer and a pooling layer, wherein the convolution layer is used to obtain a feature map corresponding to each sub-region according to each sub-region image; the pooling layer is used to perform a pooling operation on the feature map corresponding to each sub-region to reduce the dimension of the feature map corresponding to each sub-region;

[0025] The classification sub-model includes a fully connected layer and an output layer. The fully connected layer is used to perform fully connected processing on the feature map of each sub-region after dimensionality reduction; the output layer is used to standardize the feature vector of each sub-region after full connection processing through a Softmax function to obtain the probability distribution of each sub-region for each category, and determine that the category corresponding to the maximum value of the probability distribution is the category to which the sub-region belongs.

[0026] In one embodiment, the characteristic information of the sub-region includes a low-frequency signal and a high-frequency signal of the sub-region; the acquiring the characteristic information of each of the sub-regions and obtaining a test result of whether the projector is qualified according to the characteristic information of each of the sub-regions includes:

[0027] Applying Gaussian blur processing to each of the sub-regions to obtain a low-frequency signal of each of the sub-regions and a high-frequency signal of each of the sub-regions;

[0028] Calculating an average value of the low-frequency signal of each of the sub-regions, and determining a minimum average value and a maximum average value among the average values ​​of the low-frequency signals of the sub-regions;

[0029] If the difference between the maximum average value and the minimum average value is greater than a second preset threshold, it is determined that the projector is unqualified.

[0030] In one embodiment, the method further comprises:

[0031] If the difference between the maximum average value and the minimum average value is less than a second preset threshold, counting the number of high-frequency signals in each of the sub-areas;

[0032] If the number of high-frequency signals in any of the sub-areas is greater than a third preset threshold, the projector is determined to be unqualified; otherwise, the projector is determined to be qualified.

[0033] In one embodiment, the method further comprises:

[0034] Obtaining a light leakage marking result of each sub-region according to the light signal intensity of each sub-region;

[0035] The light leakage marking result of each sub-area and the detection result of whether the projector is qualified are uploaded to the host computer.

[0036] In a second aspect, an embodiment of the present application further provides a projector detection device, comprising:

[0037] An acquisition unit, configured to acquire a first image of a projection plane captured by a camera; the projection plane includes a projection area and a non-projection area where an image is projected by a projector;

[0038] The acquisition unit is further used to acquire the coordinates of the corner points of the projection area in the first image;

[0039] A processing unit, configured to divide the non-projection area into a plurality of sub-areas according to the coordinates of the corner points of the projection area;

[0040] The processing unit is further used to obtain feature information of each of the sub-areas, and obtain a test result of whether the projector is qualified according to the feature information of each of the sub-areas.

[0041] In a third aspect, an embodiment of the present application further provides a projector detection system, comprising a projector, a camera and a host computer, wherein the projector, the camera and the host computer are electrically connected;

[0042] The projector is used to project a preset image onto the projection plane; the projector is provided with an optical machine for generating and controlling the light source required by the projector;

[0043] The camera is used to image the projection plane to obtain image data;

[0044] The host computer includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, any one of the projector detection methods described above is implemented.

[0045] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is run on a projector detection system, any one of the above-mentioned projector detection methods is executed.

[0046] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0047] The embodiment of the present application obtains a first image of the projection plane taken by a camera; obtains the coordinates of the corner points of the projection area in the first image; divides the non-projection area into multiple sub-areas according to the coordinates of the corner points of the projection area; obtains the characteristic information of each sub-area, and obtains the test result of whether the projector is qualified according to the characteristic information of each sub-area. The embodiment of the present application divides the non-projection area into multiple sub-areas to achieve detailed detection of the light leakage area; and by obtaining the characteristic information of the sub-areas, it can more sensitively capture the tiny light leakage in the non-projection area, thereby improving the detection accuracy of the light leakage; through the above-mentioned automated processing process, the need for manual visual inspection is reduced, and the detection speed is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0049] Figure 1 A schematic diagram of a projector detection method provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of a projection plane provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a projection plane provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a deep learning structure provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of the structure of a projector detection device provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of a projector stage structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] 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 only 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.

[0056] Projectors are used to display images and videos, and play an important role in modern conference rooms, education, home entertainment and other fields. A good projector should have high image quality, accurate color reproduction and clear details. Light leakage is one of the common quality problems of projectors, which will cause the image contrast to decrease, affect the viewing experience, and even make the content difficult to recognize.

[0057] Traditional projector inspection methods mainly rely on manual visual inspection or simple automated equipment. Manual visual inspection requires direct observation of the projected image with the human eye to check whether there is a light leakage area. This method is inefficient, easily affected by subjective factors, and is not practical on the production line. Using automated equipment, such as optical instruments, to test the brightness and contrast of the projected image often fails to accurately locate the light leakage area, and has limited detection capabilities for tiny light leaks. Some other inspection methods may require repeated disassembly and assembly of the optical machine to adapt to different inspection standards, which is not only time-consuming and labor-intensive, but may also cause unnecessary damage to the optical machine. In addition, the above-mentioned inspection methods often fail to provide real-time feedback and control, making it difficult to adjust and optimize the production process in a timely manner during the production process.

[0058] Based on this, in various embodiments of the present application, different analysis methods are applied to the characteristic information of each sub-region to achieve comprehensive and efficient detection of light leakage defects in the projector.

[0059] The various embodiments of the present application are described in further detail below in conjunction with the accompanying drawings.

[0060] The present application embodiment provides a projector detection method, such as Figure 1 As shown, the method includes steps S101-S104.

[0061] S101: Acquire a first image of a projection plane captured by a camera; the projection plane includes a projection area and a non-projection area where an image is projected by a projector;

[0062] In the embodiment of the present application, the projector can be controlled to project a white blank pattern onto the projection plane, and a first image after the projection plane projects the white blank pattern is captured by the camera can be obtained. Furthermore, the first image captured by the camera can be subjected to distortion correction.

[0063] For specific projection planes, please refer to Figure 2 ,Depend on Figure 2 It can be seen that the imaging plane includes the entire projection plane. The projection plane is the entire screen range illuminated by the projector. The imaging plane refers to the plane inside the camera used to capture light and convert it into electronic signals. Figure 2 The red border in the middle represents the boundary of the entire imaging plane. The projection plane includes the area covered by the actual projected image of the projector (projection area) and the area not covered by the projected image of the projector (non-projection area). The projection area of ​​the projector is located at the center of the camera imaging plane. Figure 2 The blue border in the figure represents the boundary of the projection area. The projection area occupies approximately Ideally, only this area would have light and show the content of the image.

[0064] S102: Acquire the coordinates of the corner points of the projection area in the first image;

[0065] Corner points refer to points in an image that have obvious corner features. These corner points show a dramatic change from one direction to another in a local area of ​​the image, and usually appear at the intersection of two or more edges. Corner point coordinates are usually in pixels, indicating the position of the corner point in the image matrix. In actual operation, the method of obtaining corner points may include corner point detection algorithms such as Harris corner point detection, Shi-Tomas corner point detection, or FAST corner point detection to identify corner points in the image and extract the coordinates of each corner point. These corner point coordinates can be used for subsequent image analysis, such as calculating the geometric transformation of the region, analyzing image distortion, or performing image segmentation or splicing.

[0066] S103: Divide the non-projection area into a plurality of sub-areas according to the coordinates of the corner points of the projection area;

[0067] Using the corner point coordinates of the projection area as a reference, the system divides the non-projection area into multiple sub-areas. For example, a corner point coordinate can be extended in the horizontal and vertical directions within the plane to divide the plane into four sub-areas.

[0068] In practice, this division can be achieved through image processing software algorithms, such as using OpenCV's image segmentation functions, such as cv::watershed or cv::grabCut, to define the boundaries of the sub-regions based on the corner point coordinates and perform segmentation.

[0069] For example, according to the coordinates of the four corner points of the projector screen in the image, the non-projection area in the image can be divided into 8 sub-areas, and numbered 1 to 8 respectively. Figure 3 These sub-areas correspond to the parts of the projection plane where there is no projection. In theory, no light should appear in these areas. If light appears in these areas, it may indicate that there is a light leakage problem in the projector.

[0070] S104: Acquire feature information of each sub-region, and obtain a test result of whether the projector is qualified according to the feature information of each sub-region.

[0071] Ideally, the projector's optical machine should not have any light in the non-projection area (that is, the area where the projector is not projecting an image), which means that the pixel values ​​in these areas should be 0 or close to 0. Light leakage refers to the accidental projection of light by the projector's optical machine in the non-projection area due to physical defects in the optical machine or improper settings. Light leakage causes bright spots, light bands or halos in the non-projection area, appearing in the form of lower brightness at the edges, corners or the entire non-projection area of ​​the screen, making it look like light outside the projected content overflows into the non-projection area. Therefore, the pixel values ​​in these areas are significantly higher than other surrounding areas, appearing as scattered high-signal areas. These areas containing high signals contrast with the surrounding low-signal or no-signal background and can be identified.

[0072] By analyzing the characteristic information of each sub-area, it can be determined whether there is light leakage in the projector optical machine. The characteristic information includes but is not limited to data on brightness, contrast, color distribution, etc. These characteristic information reflect the optical characteristics of each sub-area, especially the possibility of light leakage. By analyzing these characteristic information, it can be determined whether there is abnormal light in the sub-area, such as whether there are unnecessary bright spots. Specifically, the quality of the projector can be evaluated by some preset qualification standards. For example, the brightness or contrast in the non-projection area must not exceed a certain threshold. If the brightness value or other characteristics of a sub-area exceed the threshold, it indicates that there may be light leakage in the area. By comprehensively analyzing the characteristic information of each sub-area, the system can make an overall judgment on the projector being tested to determine whether there are quality problems with the projector and whether it meets the qualification standards.

[0073] The embodiment of the present application obtains a first image of the projection plane taken by a camera; obtains the coordinates of the corner points of the projection area in the first image; divides the non-projection area into multiple sub-areas according to the coordinates of the corner points of the projection area; and obtains the test result of whether the projector is qualified according to the light signal intensity of each sub-area. The embodiment of the present application divides the non-projection area into multiple sub-areas, so that the system can perform a separate light signal intensity analysis on each sub-area, thereby improving the level of detail and differentiation of the detection; through the above-mentioned automated processing process, the need for manual visual inspection is reduced, and the detection speed and accuracy are greatly improved.

[0074] In one embodiment, obtaining the coordinates of the corner points of the projection area in the first image includes: obtaining the intrinsic parameter matrix and distortion coefficients of the camera, and using the intrinsic parameter matrix and the distortion coefficients to perform distortion correction on the second image to obtain the corrected second image; the second image is obtained by photographing the camera after a preset calibration image is projected onto a projection plane by a projector; calculating a mapping matrix according to the coordinates of the corner points of the corrected second image in the camera image coordinate system and the coordinates of the corner points of the preset calibration image in the display screen coordinate system; and obtaining the coordinates of the corner points of the projection area in the first image in the display screen coordinate system according to the mapping matrix.

[0075] In practical applications, the projector can be controlled to project a preset calibration image onto the projection plane, wherein the preset calibration image can be a checkerboard image. After projecting the checkerboard image onto the projection plane, the camera is triggered to take a photo to obtain a second image of the projection plane. The second image is displayed as a checkerboard pattern in the projection area, and the non-projection area is displayed as a darker or completely black image.

[0076] In order to eliminate the image distortion caused by the camera lens and make the obtained corner point coordinates more accurate, the camera that shoots the projection plane can be calibrated in advance to obtain the camera's intrinsic parameter matrix and distortion parameters. Then, the second image captured by the camera is subjected to distortion correction based on the intrinsic parameter matrix and distortion parameters to obtain the corrected second image.

[0077] According to the above embodiments, the method for determining the coordinates of the corner points of the second image can obtain the initial coordinates of each corner point in the second image in the camera image coordinate system through a corner detection algorithm. Taking the coordinates (x, y) of any corner point in the second image as an example, the initial coordinates (x, y) can be further corrected using the camera's intrinsic parameter matrix and distortion coefficient.

[0078] Specifically, the intrinsic parameter matrix contains the internal parameters of the camera, such as focal length, optical center, etc. These parameters describe the geometric relationship in the camera imaging process and are used to project points in three-dimensional space onto the two-dimensional image plane. The distortion coefficient describes the distortion effect of the lens, including radial distortion and tangential distortion. Distortion causes straight lines in the image to become curves, especially in the edge areas of the image. Before applying distortion correction, the initial coordinates of the image must first be normalized to the camera image coordinate system. Assuming (x, y) is the initial coordinate, the normalization process is:

[0079]

[0080] Among them, x norm and norm is the coordinate of the corner point after normalization to the camera image coordinate system, f x and f yis the focal length parameter in the intrinsic parameter matrix, c x and c y is the optical center coordinate in the camera intrinsic matrix.

[0081] Then radial and tangential distortion correction is performed using the following formulas:

[0082] 1) Radial distortion correction:

[0083] r 2 =x 2 norm +y 2 norm

[0084] x dist1 =x norm (1+k1r 2 +k2r 4 +k3r 6 )

[0085] y dist1 =y norm (1+k1r 2 +k2r 4 +k3r 6 )

[0086] 2) Tangential distortion correction:

[0087] x dist2 =x dist1 +2p1x norm y norm +p2(r 2 +2x 2 norm )

[0088] y dist2 =y dist1 +p1(r 2 +2y 2 norm )+2p2x norm y norm

[0089] The coordinates after distortion correction need to be remapped back to the camera image coordinate system:

[0090] x final =f x *x dist2 +c x

[0091] y final =f y *y dist2 +c y

[0092] Where r is the distance from the optical center of the image (c x , c y ) to a given pixel point, x dist1 and dist1 is the coordinate after applying the radial distortion coefficient, k1, k2, k3 are the radial distortion coefficients, x dist2 and dist2 are the coordinates after applying the tangential distortion coefficients, p1 and p2 are the tangential distortion coefficients, x final and final are the final coordinates remapped to the camera image coordinate system after distortion correction, that is, the coordinates of the corner points of the corrected second image.

[0093] By applying the above camera intrinsic parameter matrix and distortion coefficient to the corner point coordinates for distortion correction, the accuracy of the corner point coordinates can be significantly improved, especially when the corner point is located at the edge of the image or a wide-angle lens is used. The image distortion caused by the lens can be eliminated and more accurate corner point coordinates can be obtained, which can help subsequent calculations to obtain a more accurate mapping matrix.

[0094] Furthermore, it is necessary to calculate the mapping matrix according to the corner coordinates of the corrected second image in the camera image coordinate system and the corner coordinates of the preset calibration image in the display screen coordinate system. Specifically, a checkerboard detection algorithm (such as the findChessboardCorners function of OpenCV) can be used to respectively detect the corner coordinates in the preset calibration image (such as the checkerboard image) projected by the projector and the second image after distortion correction, so as to calculate the mapping matrix H between the camera image coordinate system and the display screen coordinate system.

[0095] The camera image coordinate system is a two-dimensional coordinate system that describes and locates the position of each pixel in the image captured by the camera. The coordinate system in the image captured by the camera is used to represent the pixel position in the image. The origin of the camera image coordinate system is usually in the upper left corner of the image, that is, the x-axis is from left to right in the horizontal direction, and the y-axis is from top to bottom in the vertical direction. To determine the coordinates of the feature points in the image in the camera image coordinate system, the edges of the feature points can be detected by an edge detection algorithm, and then the center coordinates of the feature points can be determined. Alternatively, the Hough transform method can be used to detect feature points of a specific shape (such as a circle) and determine their position coordinates. The edge detection algorithm and the Hough transform method are prior art and will not be described in detail here.

[0096] The mapping matrix can be understood as the coordinate mapping relationship between the display screen coordinate system and the camera image coordinate system. The mapping matrix can be used to convert the coordinates in the camera image coordinate system into the coordinates in the display screen coordinate system.

[0097] The display screen coordinate system is a coordinate system used to locate and render images or graphic elements on a display device (such as a computer monitor, TV screen, or mobile phone screen). The mapping relationship between the coordinates in the camera image coordinate system and the coordinates in the display screen coordinate system is as follows:

[0098]

[0099] in, is the homogeneous coordinate of the pixel point in the display screen coordinate system, x p and p are the horizontal and vertical coordinates of the pixel in the display screen coordinate system, 1 is the conventional representation in homogeneous coordinates, which is used to support the calculation of perspective transformation, H is the mapping matrix, is the homogeneous coordinate of the pixel in the camera image coordinate system. u and v are the horizontal and vertical coordinates of the pixel in the camera image coordinate system, respectively. The last 1 is also the conventional representation in homogeneous coordinates. Specifically, H is a 3*3 matrix.

[0100] In this way, according to the coordinate positions of the four corner points of the projection area in the first image in the camera image coordinate system, the calculated mapping matrix H can be used to obtain the coordinates of the corner points of the projection area in the first image in the display screen coordinate system.

[0101] In one embodiment, the characteristic information of the sub-region includes the light signal intensity of the sub-region; the characteristic information of each sub-region is obtained, and a test result of whether the projector is qualified is obtained based on the characteristic information of each sub-region, including: calculating the light signal intensity of each sub-region; if the light signal intensity of each sub-region is not greater than a first preset threshold, the projector is determined to be qualified; if there is any sub-region whose light signal intensity is greater than the first preset threshold, the projector is determined to be unqualified.

[0102] To calculate the light signal intensity of each sub-area (ie, a non-projection area where the projector does not project an image), it is necessary to analyze the captured image of each sub-area to measure the brightness or light intensity of each sub-area.

[0103] For example, the image of the non-projection area in the first image can be divided into multiple sub-area images according to the boundary of each sub-area, and the image of each sub-area is preprocessed. The preprocessing includes but is not limited to grayscale, histogram equalization, denoising, etc., so as to improve the accuracy of light signal intensity analysis.

[0104] Perform a statistical analysis on the light signal intensity of each sub-region in the first image. For example, the pixel amplitude of each sub-region is counted, and the pixel amplitude of each sub-region is compared by adopting a unified first preset threshold. If the light signal intensity of each sub-region does not exceed the first preset threshold, it is considered that the projector optical machine is qualified in quality, the light signal intensity of the projector optical machine meets the expected standards, and there is no obvious light leakage or other quality problems. For example, the light signal intensity of sub-region 1 is 0.05, which is lower than the first preset threshold of 0.1, so the sub-region is considered to have no light leakage. If the light intensity signal of any sub-region exceeds the first preset threshold, such as the light signal intensity of sub-region 3 is 0.15, which is higher than the first preset threshold of 0.1, then it is necessary to mark these sub-regions whose light signal intensity exceeds the first preset threshold as light leakage areas, and it is considered that the projector optical machine may have light leakage or other problems, requiring further inspection or repair. It should be noted that the light signal intensity can usually be calculated in the following ways: 1. Calculate the average value of all pixel amplitudes in the sub-region; 2. Calculate the brightest pixel amplitude in the sub-region; 3. Sum the pixel amplitudes of all pixels in the sub-region. The first preset threshold will be adjusted accordingly according to different light signal intensity calculation methods to ensure that it matches the result of the selected light intensity signal calculation method.

[0105] The embodiments of the present application can quickly and accurately evaluate the performance of the projector optical machine through an automated measurement and comparison process, which helps to improve production efficiency, reduce the subjectivity of manual inspection, and improve product reliability.

[0106] In one embodiment, the feature information of the sub-region includes a feature map extracted in the sub-region by a classification model; acquiring the feature information of each sub-region, and obtaining a test result of whether the projector is qualified according to the feature information of each sub-region, including: dividing the first image according to the boundary of each sub-region to obtain a plurality of sub-region images; inputting each sub-region image into the classification model, and outputting a category of each sub-region; if the category of each sub-region indicates that there is no light leakage, then the projector is determined to be qualified; if the category of any sub-region indicates that there is light leakage, then the projector is determined to be unqualified; wherein the classification model includes a feature extraction sub-model and a classification sub-model. The classification sub-model, the feature extraction sub-model includes a convolution layer and a pooling layer. The convolution layer is used to obtain the feature map corresponding to each sub-region according to the image of each sub-region; the pooling layer is used to perform a pooling operation on the feature map corresponding to each sub-region, and reduce the dimension of the feature map corresponding to each sub-region; the classification sub-model includes a fully connected layer and an output layer. The fully connected layer is used to perform a fully connected processing on the feature map after the dimension reduction of each sub-region; the output layer is used to standardize the feature vector after the fully connected processing of each sub-region through the Softmax function, obtain the probability distribution of each sub-region for each category, and determine that the category corresponding to the maximum value of the probability distribution is the category to which the sub-region belongs.

[0107] Specifically, it is necessary to build a five-layer classification model and set the number of categories to 2. Because the light signal intensity of each sub-region needs to be analyzed in detail, the first image needs to be divided according to the boundary of each sub-region to obtain multiple sub-region images. Therefore, the input of the classification model is the image of each sub-region. Next, each sub-region image is input into the pre-trained classification model. The task of the model is to identify whether there is light leakage in each sub-region. Therefore, the output of the classification model is a one-dimensional vector with two elements. The index of the maximum value of the one-dimensional vector is the predicted category (for example, "0" indicates that there is no light leakage in the current sub-region, and "1" indicates that there is light leakage in the current sub-region).

[0108] Please refer to Figure 4 , Figure 4A structural diagram of a classification model based on deep learning provided for an embodiment of the present application. The first three convolutional layers of the entire classification model are used to extract feature maps (e.g., brightness distribution of light, edge features, etc.) in each sub-region image. These feature maps describe the light intensity, texture and other features at different positions in the sub-region image. Each convolutional layer is followed by a maximum pooling layer (MaxPooling), which is used to perform dimensionality reduction operations on the feature maps obtained by the convolutional layer to reduce the amount of network calculations and simplify feature representation. The size of each convolution kernel is 3x3, and the number of output feature maps is 64, 128, and 256 respectively according to the level. Then two fully connected layers are used to calculate the long-range dependencies between high-frequency semantic information. For example, the fully connected layer 1 flattens the pooled feature map to generate a one-dimensional feature vector. Then, the fully connected layer 1 combines these local bright spot features with the context of the overall image by learning the long-range dependencies between high-frequency semantic features, for example, by comparing the local bright spots with the dark parts of other areas to further confirm whether there is light leakage, thereby obtaining the feature vector after the fully connected layer 1 is fully connected through 1000 neurons. The fully connected layer 2 is used to process the output of the fully connected layer 1 through 2000 neurons again to further condense information, so that the classification model can make a final judgment based on the feature information of the sub-area after the fully connected processing. Finally, the output layer uses the Softmax function to standardize the feature vector after the fully connected processing to obtain the probability distribution of each category. The calculation formula of the Softmax function is as follows:

[0109]

[0110] Among them, x i The linear transformation result of category i (i.e. the output of the fully connected layer), n is the total number of categories.

[0111] Since the task of the classification model is a binary classification problem ("light leakage" or "no light leakage"), there is

[0112] P(y=i|x) is the probability that the sub-region belongs to category i, and the output vector is in the form of [P(0),P(1)]. Assume that the model output is [0.3,0.7], which means that the model believes that the probability of light leakage in the sub-region is 70%.

[0113] Based on the output of the classification model, that is, the probability distribution of the category to which each sub-region belongs, determine whether there is light leakage in each sub-region. If the categories to which all sub-regions belong indicate that there is no light leakage, then it can be determined that the projector is qualified. If the category to which any sub-region belongs indicates that there is light leakage, then it can be determined that the projector is unqualified, and the sub-regions whose categories are characterized as light leakage are marked as light leakage areas, so that they can be uploaded to the host computer for unified detection and management later.

[0114] The embodiment of the present application utilizes deep learning technology to improve the accuracy and efficiency of detection through automated feature extraction and classification. By analyzing the light signal intensity of each sub-area, it is possible to accurately identify whether there is light leakage in the projector optical machine, thereby screening out unqualified products during production or quality control.

[0115] In one embodiment, the characteristic information of the sub-region includes a low-frequency signal and a high-frequency signal of the sub-region; the characteristic information of each sub-region is obtained, and a detection result of whether the projector is qualified is obtained based on the characteristic information of each sub-region, including: applying Gaussian blur processing to each sub-region to obtain a low-frequency signal of each sub-region and a high-frequency signal of each sub-region; calculating the average value of the low-frequency signal of each sub-region, and determining the minimum average value and the maximum average value among the average values ​​of the low-frequency signals of each sub-region; if the difference between the maximum average value and the minimum average value is greater than a second preset threshold value, the projector is determined to be unqualified.

[0116] by Figure 3 As an example, for each sub-area I i (i=1, 2, 3, 4, 5, 6, 7, 8) Perform Gaussian blur and calculate low-frequency and high-frequency signals. Gaussian blur smoothes the image by convolving the image with a weight matrix (also called a Gaussian kernel or Gaussian template) generated by a Gaussian function. The element values ​​of the Gaussian kernel are calculated based on the Gaussian distribution function. The weight of the center point is the largest and gradually decreases to the surrounding areas, simulating the bell curve of a normal distribution.

[0117] In image processing, low-frequency signals usually refer to areas in an image that change slowly or smoothly, such as backgrounds and flat areas, while high-frequency signals refer to areas in an image that change dramatically, such as edges and details. Through Gaussian blur processing, the low-frequency signal of an image can be obtained, and the difference between the light signal of the original image and the low-frequency signal can be regarded as the high-frequency signal.

[0118] The specific calculation formula is as follows:

[0119] Calculate the low-frequency signal: This formula represents the i-th sub-region I i Apply Gaussian blur operation to obtain the low-frequency signal of the sub-region

[0120] Calculate high frequency signals:

[0121] Calculate the average value of the low-frequency signal of each non-projected sub-region, and find the minimum average value Mean(I low ) min and the maximum mean value Mean(Ilow ) max .

[0122] When Mean(I low ) max -Mean(I low ) min >T low , that is, the difference between the maximum average value and the minimum average value is greater than the second preset threshold value T low , it can be directly judged that the projector optical machine has light leakage, determine that the projector is unqualified, and mark the area where the difference between the maximum average value and the minimum average value is greater than the second preset threshold as a light leakage area. For example, in all sub-areas, the minimum average value is 0.1 and the maximum average value is 0.5. If the difference between the maximum average value and the minimum average value is 0.4, and the set second preset threshold is 0.3, the difference exceeds the threshold, and the system will judge that the projector is unqualified, and that some sub-areas are too bright and may have light leakage.

[0123] The embodiments of the present application take into account that when a serious light leakage defect occurs in the optical and mechanical part of the projector, the area with serious light leakage will be particularly obvious in the low-frequency signal of the image. It should be understood that the low-frequency signal represents the smooth area and the overall background in the image. Under normal circumstances, the low-frequency signal should be relatively uniform, but in the case of severe light leakage, the area with severe light leakage will cause the intensity of the low-frequency signal to increase abnormally. Therefore, by calculating the average value of the low-frequency signal of each sub-area and comparing the maximum and minimum values ​​of these average values, it can be detected whether there is an abnormally increased signal intensity due to light leakage. If the difference between the maximum average value and the minimum average value exceeds the preset threshold, it can be determined that the projector has a light leakage problem, and the projector is judged to be unqualified.

[0124] In one embodiment, the method also includes: if the difference between the maximum average value and the minimum average value is less than a second preset threshold, then counting the number of high-frequency signals in each sub-area; if there is any sub-area where the number of high-frequency signals is greater than a third preset threshold, then determining that the projector is unqualified, otherwise determining that the projector is qualified.

[0125] The embodiment of the present application also takes into account that the light leakage of the optical machine is slight, and individual areas present sporadic high-brightness signals, which cannot be handled by low-frequency signals. At this time, by statistically analyzing high-frequency information, the performance of the light leakage of the optical machine in different areas can be reflected.

[0126] In addition, the embodiments of the present application also take into account the situation where the projector has slight light leakage. Slight light leakage usually means that the light leakage area is small and the brightness increase is not obvious. On the image, these areas may be just a few scattered pixels or small spots, rather than large bright areas. It can be understood that the low-frequency signal represents the smooth changes in the image and is mainly used to capture large areas of uniform color or gradients in the image. Since slight light leakage is generally distributed sporadically in a small range and is not enough to cause significant changes in the low-frequency signal, such slight anomalies may not be detected using low-frequency signal analysis. High-frequency signals represent rapid changes in the image, such as edges, textures, and details. Even a small increase in brightness will appear as an obvious peak in the high-frequency signal.

[0127] Therefore, by statistically analyzing the high-frequency signal, such as calculating the number of pixels in the high-frequency signal exceeding the third preset threshold, the distribution and intensity of these light signals can be quantified.

[0128] Specifically, Figure 3 As an example, for each sub-area I i The high-frequency images of (i=1, 2, 3, 4, 5, 6, 7, 8) are greater than the third preset threshold T high The number of elements Perform statistics, when there is a non-projected sub-region That is, if the number of high-frequency signals in any sub-region is greater than the third preset threshold, the sub-region where the number of high-frequency signals is greater than the third preset threshold can be marked as a light leakage region, and the projector optical machine is judged to have light leakage, and the projector is determined to be unqualified. That is, the number of high-frequency signals in each sub-area is less than or equal to the third preset threshold, so it can be determined that the light leakage phenomenon of the projector optical machine is not serious and the projector is qualified.

[0129] By counting the number of abnormally bright pixels above the threshold in the high-frequency signal, the existence and impact of slight light leakage can be accurately located and evaluated.

[0130] The embodiment of the present application adopts a multi-scale judgment method and comprehensively considers the characteristics of low-frequency signals and high-frequency signals, which can effectively reduce the misjudgment that may occur at a single scale, greatly reduce the influence of human subjective factors on the detection results, ensure the objectivity and consistency of light leakage detection, and improve the accuracy and reliability of detection. The embodiment of the present application conducts a comprehensive evaluation of the optical and mechanical parts of the projector from different signal levels to ensure that only projectors that meet the quality standards can be judged as qualified. Through this comprehensive analysis, the light leakage phenomenon of the projector optical machine can be more accurately identified and located, whether it is a large-area severe light leakage or a small-range slight light leakage, it can be effectively detected and evaluated.

[0131] In one embodiment, the method further includes: obtaining a light leakage marking result of each sub-area according to the light signal intensity of each sub-area; and uploading the light leakage marking result of each sub-area and the detection result of whether the projector is qualified to a host computer.

[0132] Based on the analysis of the optical signal intensity of each sub-region in the above-mentioned embodiments, the system will generate a light leakage marking result, indicating whether there is light leakage in each sub-region (such as "0" indicates no light leakage, "1" indicates light leakage). Specifically, the system can mark the light leakage region according to the following conditions: the sub-region whose optical signal intensity exceeds the first preset threshold; or the sub-region whose classification result indicates the existence of light leakage; or the sub-region whose difference between the maximum average value and the minimum average value exceeds the second preset threshold; or the sub-region whose number of high-frequency signals is greater than the third preset threshold. Furthermore, the degree of light leakage and its specific coordinates can also be marked in the light leakage marking result.

[0133] The inspection results of the light signal intensity of each sub-area, such as the above-mentioned embodiments, are uploaded to the host computer database to determine whether the projector is qualified through different analysis methods, so as to achieve real-time tracking of the machine status during the production process. Furthermore, a quality control report can be generated, or automated response measures can be triggered, such as stopping the production line to investigate and repair the problem. By centrally managing and analyzing the inspection data through the host computer, the reliability of the projector products produced can be ensured, while the production process can be optimized, and the problem of light leakage in the product can be discovered in time, and the problem can be further solved to improve production efficiency.

[0134] Through the above-mentioned embodiments, an automated detection system can be implemented to detect whether the optical machine of the projector has light leakage defects, light source dispersion, and other problems, so as to quickly and accurately screen out such unqualified products during the production process.

[0135] In order to implement the projector detection method of the embodiment of the present application, the embodiment of the present application also provides a projector detection device, such as Figure 5 As shown, the device comprises:

[0136] An acquisition unit 501 is used to acquire a first image of a projection plane captured by a camera; the projection plane includes a projection area and a non-projection area where an image is projected by a projector;

[0137] The acquisition unit 501 is further configured to acquire the coordinates of the corner points of the projection area in the first image;

[0138] A processing unit 502 is used to divide the non-projection area into a plurality of sub-areas according to the coordinates of the corner points of the projection area;

[0139] The processing unit 502 is further configured to obtain feature information of each of the sub-regions, and obtain a test result of whether the projector is qualified according to the feature information of each of the sub-regions.

[0140] In one embodiment, the acquisition unit 501 is further used to acquire the intrinsic parameter matrix and the distortion coefficient of the camera, and use the intrinsic parameter matrix and the distortion coefficient to perform distortion correction on the second image to obtain a corrected second image; the second image is obtained by photographing the camera after the preset calibration image is projected onto a projection plane by the projector;

[0141] The processing unit 502 is further configured to calculate a mapping matrix according to the corner point coordinates of the corrected second image in the camera image coordinate system and the corner point coordinates of the preset calibration image in the display screen coordinate system;

[0142] The acquisition unit 501 is further configured to acquire the coordinates of the corner points of the projection area in the first image in the display screen coordinate system according to the mapping matrix.

[0143] In one embodiment, the processing unit 502 is further configured to calculate the optical signal strength of each of the sub-areas;

[0144] The device further includes: a determination unit; the determination unit is configured to determine that the projector is qualified if the light signal intensity of each of the sub-areas is not greater than a first preset threshold;

[0145] The determining unit is further configured to determine that the projector is unqualified if there is any sub-area where the light signal intensity is greater than the first preset threshold.

[0146] In one embodiment, the device further includes: an image division unit; the image division unit is used to divide the first image according to the boundary of each sub-region to obtain a plurality of sub-region images;

[0147] The processing unit 502 is further used to input each of the sub-region images into a classification model, and output a category to which each of the sub-regions belongs;

[0148] The determining unit is further configured to determine that the projector is qualified if the category to which each of the sub-areas belongs indicates that there is no light leakage;

[0149] The determining unit is further configured to determine that the projector is unqualified if any of the sub-areas has a category characterizing light leakage;

[0150] The classification model includes a feature extraction sub-model and a classification sub-model.

[0151] The feature extraction sub-model includes a convolution layer and a pooling layer, wherein the convolution layer is used to obtain a feature map corresponding to each sub-region according to each sub-region image; the pooling layer is used to perform a pooling operation on the feature map corresponding to each sub-region to reduce the dimension of the feature map corresponding to each sub-region;

[0152] The classification sub-model includes a fully connected layer and an output layer. The fully connected layer is used to perform fully connected processing on the feature map of each sub-region after dimensionality reduction; the output layer is used to standardize the feature vector of each sub-region after full connection processing through a Softmax function to obtain the probability distribution of each sub-region for each category, and determine that the category corresponding to the maximum value of the probability distribution is the category to which the sub-region belongs.

[0153] In one embodiment, the processing unit 502 is further configured to apply Gaussian blur processing to each of the sub-regions to obtain a low-frequency signal of each of the sub-regions and a high-frequency signal of each of the sub-regions;

[0154] The processing unit 502 is further configured to calculate an average value of the low-frequency signal of each of the sub-regions, and determine a minimum average value and a maximum average value among the average values ​​of the low-frequency signals of the sub-regions;

[0155] The determination unit is further configured to determine that the projector is unqualified if the difference between the maximum average value and the minimum average value is greater than a second preset threshold.

[0156] In one embodiment, the processing unit 502 is further configured to count the number of high-frequency signals in each of the sub-regions if the difference between the maximum average value and the minimum average value is less than a second preset threshold;

[0157] The determining unit is further configured to determine that the projector is unqualified if the number of high-frequency signals in any of the sub-areas is greater than a third preset threshold, and otherwise determine that the projector is qualified.

[0158] In one embodiment, the processing unit 502 is further configured to obtain a light leakage marking result of each sub-region according to the light signal intensity of each sub-region;

[0159] The device also includes: an uploading unit; the uploading unit is used to upload the light leakage marking result of each sub-area and the detection result of whether the projector is qualified to the host computer.

[0160] In actual application, the processing unit can be realized by the processor of the host computer in the projector detection system combined with the communication interface, and the acquisition unit, determination unit, image division unit and upload unit can be realized by the communication interface in the projector detection device.

[0161] It should be noted that: the above embodiment provides a projector detection device, and only uses the division of the above program modules as an example to illustrate when performing projector detection. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the projector detection device and the projector detection method embodiment provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0162] Based on the hardware implementation of the above program module, and in order to implement a projector detection method provided in an embodiment of the present application, an embodiment of the present application further provides a projector detection system, and the projector detection system includes:

[0163] A projector, a camera and a host computer, wherein the projector, the camera and the host computer are electrically connected;

[0164] The projector is used to project a preset image onto the projection plane; the projector is provided with an optical machine for generating and controlling the light source required by the projector;

[0165] The camera is used to image the projection plane to obtain image data;

[0166] The host computer includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, any one of the projector detection methods described above is implemented.

[0167] The projector and camera can be mounted on the projector stage, please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of a projector stage. The stage is set in front of the projection plane. The projection plane is usually a white wall or whiteboard, which is used to evenly reflect the light emitted by the projector for projector detection. The projector to be detected is placed in the hollow position of the stage. The projector is placed in the middle of the stage to facilitate the camera to capture the image projected by the projector from the best angle to ensure the accuracy of the detection result. The placement position of the projector can be adjusted to accommodate projectors of different sizes and models to ensure compatibility and flexibility. A camera is set above the stage, which is responsible for capturing the image projected by the projector onto the plane. Furthermore, it can also be connected to the host computer, and the host computer can be used to control the projector to project the image onto the projection plane, and control the camera to capture the projection plane after the projected image is captured.

[0168] In the embodiment of the present application, the memory of the host computer is used to store various types of data to support the operation of the projector detection system. Examples of such data include: any computer program used to operate on the projector detection system.

[0169] It is understandable that when the processor in the projector detection system described above executes the computer program, it can also implement the functions of the various units in the above-mentioned corresponding device embodiments, which will not be repeated here. Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory, and executed by the processor to complete the various embodiments of the present application. One or more modules / units can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the projector detection system. For example, the computer program can be divided into the various units in the above-mentioned projector detection system, and each unit can implement the specific functions described in the above-mentioned corresponding projector detection system.

[0170] The host computer in the projector detection system can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The host computer may include but is not limited to a processor and a memory. Those skilled in the art will understand that the processor and the memory are merely examples of the host computer and do not constitute a limitation on the host computer. The host computer may include more or fewer components, or a combination of certain components, or different components. For example, the host computer may also include a network access device, a bus, etc.

[0171] The processor can be a central processing unit (CPU), or 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. A general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the host computer, and uses various interfaces and lines to connect various parts of the entire host computer.

[0172] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the projector detection system by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc.; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC, Smart Media Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0173] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed on a computer, the computer executes any one of the steps of the projector detection method described above.

[0174] An embodiment of the present application also provides a computer program product having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, it is used to implement the projector detection method described in the first aspect of the embodiment of the present application or any specific implementation method of the first aspect.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0176] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0179] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a projector detection system (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

Claims

1. A projector detection method, characterized in that: include: Acquire a first image of a projection plane captured by a camera; the projection plane includes a projection area and a non-projection area where an image is projected by a projector; Obtaining the coordinates of the corner points of the projection area in the first image; Dividing the non-projection area into a plurality of sub-areas according to the coordinates of the corner points of the projection area; Acquire characteristic information of each of the sub-areas, and obtain a test result of whether the projector is qualified according to the characteristic information of each of the sub-areas.

2. The projector detection method according to claim 1, characterized in that: The acquiring the coordinates of the corner points of the projection area in the first image comprises: Acquire the intrinsic parameter matrix and distortion coefficient of the camera, and use the intrinsic parameter matrix and the distortion coefficient to perform distortion correction on the second image to obtain a corrected second image; the second image is obtained by photographing the camera after projecting a preset calibration image onto a projection plane using the projector; Calculating a mapping matrix according to the coordinates of the corner points of the corrected second image in the camera image coordinate system and the coordinates of the corner points of the preset calibration image in the display screen coordinate system; According to the mapping matrix, the coordinates of the corner points of the projection area in the first image in the display screen coordinate system are obtained.

3. The projector detection method according to claim 1, characterized in that: The characteristic information of the sub-region includes the light signal intensity of the sub-region; the acquiring the characteristic information of each sub-region and obtaining the test result of whether the projector is qualified according to the characteristic information of each sub-region includes: Calculating the optical signal intensity of each of the sub-areas; If the light signal intensity of each of the sub-areas is not greater than the first preset threshold, determining that the projector is qualified; If the light signal intensity of any of the sub-areas is greater than the first preset threshold, it is determined that the projector is unqualified.

4. The projector detection method according to claim 1, characterized in that: The feature information of the sub-region includes a feature map extracted in the sub-region by a classification model; the acquiring the feature information of each sub-region and obtaining a test result of whether the projector is qualified according to the feature information of each sub-region includes: Dividing the first image according to the boundary of each sub-region to obtain a plurality of sub-region images; Input each sub-region image into a classification model, and output the category to which each sub-region belongs; If the category to which each of the sub-areas belongs indicates that there is no light leakage, then the projector is determined to be qualified; If any of the sub-areas has a category representation indicating light leakage, determining that the projector is unqualified; The classification model includes a feature extraction sub-model and a classification sub-model. The feature extraction sub-model includes a convolution layer and a pooling layer, wherein the convolution layer is used to obtain a feature map corresponding to each sub-region according to each sub-region image; the pooling layer is used to perform a pooling operation on the feature map corresponding to each sub-region to reduce the dimension of the feature map corresponding to each sub-region; The classification sub-model includes a fully connected layer and an output layer. The fully connected layer is used to perform fully connected processing on the feature map of each sub-region after dimensionality reduction; the output layer is used to standardize the feature vector of each sub-region after full connection processing through a Softmax function to obtain the probability distribution of each sub-region for each category, and determine that the category corresponding to the maximum value of the probability distribution is the category to which the sub-region belongs.

5. The projector detection method according to claim 1, characterized in that: The characteristic information of the sub-region includes a low-frequency signal and a high-frequency signal of the sub-region; the acquiring the characteristic information of each sub-region and obtaining a test result of whether the projector is qualified according to the characteristic information of each sub-region includes: Applying Gaussian blur processing to each of the sub-regions to obtain a low-frequency signal and a high-frequency signal of each of the sub-regions; Calculating an average value of the low-frequency signal of each of the sub-regions, and determining a minimum average value and a maximum average value among the average values ​​of the low-frequency signals of the sub-regions; If the difference between the maximum average value and the minimum average value is greater than a second preset threshold, it is determined that the projector is unqualified.

6. The projector detection method according to claim 5, characterized in that: The method further comprises: If the difference between the maximum average value and the minimum average value is less than a second preset threshold, counting the number of high-frequency signals in each of the sub-areas; If the number of high-frequency signals in any of the sub-areas is greater than a third preset threshold, the projector is determined to be unqualified; otherwise, the projector is determined to be qualified.

7. The projector detection method according to claim 1, characterized in that: The method further comprises: Obtaining a light leakage marking result of each sub-region according to the light signal intensity of each sub-region; The light leakage marking result of each sub-area and the detection result of whether the projector is qualified are uploaded to the host computer.

8. A projector detection device, characterized in that: include: An acquisition unit, configured to acquire a first image of a projection plane captured by a camera; the projection plane includes a projection area and a non-projection area where an image is projected by a projector; The acquisition unit is further used to acquire the coordinates of the corner points of the projection area in the first image; A processing unit, configured to divide the non-projection area into a plurality of sub-areas according to the coordinates of the corner points of the projection area; The processing unit is further used to obtain feature information of each of the sub-areas, and obtain a test result of whether the projector is qualified according to the feature information of each of the sub-areas.

9. A projector detection system, characterized in that: It includes a projector, a camera and a host computer, wherein the projector, the camera and the host computer are electrically connected; The projector is used to project a preset image onto the projection plane; the projector is provided with an optical machine for generating and controlling the light source required by the projector; The camera is used to image the projection plane to obtain image data; The host computer includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the projector detection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is run on a projector detection system, the projector detection method according to any one of claims 1 to 7 is executed.

Images