Shielding detection method, device and equipment

Abstract

The embodiment of the invention provides a shielding detection method, device and equipment. The shielding detection method comprises the steps of obtaining a first image and at least one image division scheme; aiming at each image division scheme in the at least one image division scheme, dividing the first image based on the image division scheme to obtain a plurality of first image areas corresponding to the first image, and obtaining image feature parameters of each first image area in the plurality of first image areas; screening from the at least one image division scheme to obtain a target division scheme of which the image division scheme information meets a preset condition; and determining an image shielding ratio corresponding to the target division scheme, wherein the image shielding ratio is an equipment shielding ratio of the image acquisition equipment. According to the embodiment of the invention, the accuracy of shielding detection is improved.

Description

Technical Field

[0001] The present application belongs to the field of vehicle technology, and in particular, relates to an occlusion detection method, device and equipment. Background Art

[0002] In real life, with the rapid development of intelligent driving technology, on-board cameras are an indispensable part of vehicle perception and decision-making, and play an important role. However, in real road scenes, vehicles often encounter situations where on-board cameras are blocked. Occlusion of on-board cameras will lead to a decrease in the image quality of images collected by on-board cameras, and the loss or misinterpretation of key information in the images, which may affect the vehicle's perception of the environment and decision-making ability. Therefore, how to accurately detect whether the camera is blocked is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide an occlusion detection method, device and equipment, which improve the accuracy of camera occlusion detection.

[0004] In a first aspect, an embodiment of the present application provides an occlusion detection method, the method comprising:

[0005] Acquire a first image and at least one image segmentation scheme;

[0006] For each image division scheme of at least one image division scheme, divide the first image based on the image division scheme to obtain a plurality of first image regions corresponding to the first image, and obtain image feature parameters of each first image region among the plurality of first image regions;

[0007] From at least one image division scheme, screen and obtain a target division scheme whose image division scheme information satisfies a preset condition, wherein the image division scheme information is determined by an image feature parameter of each of a plurality of first image areas corresponding to each image division scheme, and the image division scheme information includes an image occlusion ratio;

[0008] The image occlusion ratio corresponding to the target division scheme is determined to be a device occlusion ratio of an image acquisition device, where the image acquisition device is a device used to acquire the first image.

[0009] In an optional implementation of the first aspect, the image feature parameter includes a first image feature parameter and a second image feature parameter, and the second image feature parameter includes at least one feature parameter;

[0010] Before selecting a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from at least one image segmentation scheme, the method further includes:

[0011] Determine a second image region among the plurality of first image regions corresponding to the first image where the first image characteristic parameter is greater than a preset parameter threshold;

[0012] determining an image occlusion ratio of the first image based on a ratio between the first number of regions of the second image region and the second number of regions of the first image region;

[0013] For each of the plurality of first image regions, determining a characteristic variance of a target characteristic parameter corresponding to the image region to obtain a plurality of characteristic variances, determining an average of the plurality of characteristic variances as a characteristic variance average of the target characteristic parameter to obtain at least one characteristic variance average, and performing a first preset weight on the at least one characteristic variance average to obtain a target value, wherein the target characteristic parameter is any one of the at least one characteristic parameter corresponding to the second image characteristic parameter;

[0014] The image occlusion ratio and the target value are determined as image partitioning scheme information.

[0015] From at least one image segmentation scheme, a target segmentation scheme whose image segmentation scheme information satisfies a preset condition is screened and obtained, including:

[0016] From at least one image division scheme, a target division scheme is screened out, in which the image occlusion ratio is greater than a first preset ratio threshold and the target value is the smallest.

[0017] In an optional implementation of the first aspect, determining the image occlusion ratio of the first image based on a ratio between the number of first regions of the second image region and the number of second regions of the first image region includes:

[0018] Determine a ratio between the first number of regions of the second image region and the second number of regions of the first image region as an initial image occlusion ratio;

[0019] When the occlusion ratio of the initial image is greater than a second preset ratio threshold, a plurality of consecutive frames of second images are acquired, and an occluded image region corresponding to each frame of the second image is determined, and image acquisition times of the plurality of consecutive frames of the second images are all earlier than image acquisition times of the first image;

[0020] For each image area in the multiple image areas included in the second image area, based on the blocked image area corresponding to each frame of the second image, determine the blockage ratio of the image area; determine the image area in the multiple image areas whose blockage ratio is greater than the preset blockage ratio as the third image area;

[0021] A ratio between the number of third regions of the third image region and the number of second regions of the first image region is determined as an image occlusion ratio of the first image.

[0022] In an optional implementation of the first aspect, the first image feature parameter includes at least one of an edge feature parameter and a texture feature parameter;

[0023] Before determining a second image region in which a first image feature parameter is greater than a preset parameter threshold value among a plurality of first image regions corresponding to the first image, the method further includes:

[0024] Performing edge detection on the first image using an edge detection algorithm to obtain edge feature parameters of the first image;

[0025] and / or,

[0026] The first image is processed using a gray level co-occurrence matrix to extract texture feature parameters of the first image.

[0027] In an optional implementation of the first aspect, the first image is a grayscale image; acquiring the first image includes:

[0028] Acquire a second image, where the second image is a plurality of pixels and color information corresponding to each of the plurality of pixels;

[0029] Based on the color information corresponding to each pixel in the plurality of pixels, a grayscale conversion function is used to perform grayscale conversion processing on the color image to obtain a first image.

[0030] In an optional implementation of the first aspect, obtaining at least one image segmentation scheme includes:

[0031] Obtaining image division constraint conditions, the image division constraint conditions including the range of the number of area divisions of the image in the image width direction and the range of the number of area divisions of the image in the image height direction;

[0032] At least one image partitioning scheme is generated based on image partitioning constraints using an image segmentation method.

[0033] In an optional implementation of the first aspect, after determining the occlusion detection information of the image acquisition device based on the image occlusion ratio corresponding to the target division scheme, the method further includes:

[0034] Based on the preset corresponding relationship between the device occlusion ratio and the warning level, the device occlusion ratio is matched to obtain the first warning level of the image acquisition device.

[0035] In an optional implementation of the first aspect,

[0036] The method also includes:

[0037] respectively determining region status information of a plurality of first image regions;

[0038] Based on the preset area weights, weighted summation is performed on the area status information of the plurality of first images to obtain an image occlusion degree of the first image, and the image occlusion degree of the first image is determined to be a device occlusion degree of the image acquisition device;

[0039] Based on the preset corresponding relationship between the device occlusion degree and the warning level, the device occlusion degree is matched to obtain the second warning level of the image acquisition device.

[0040] In a second aspect, an embodiment of the present application provides an occlusion detection device, the device comprising:

[0041] An acquisition module, used for acquiring a first image and at least one image division scheme;

[0042] a division module, configured to divide the first image based on the image division scheme for each of at least one image division scheme, obtain a plurality of first image regions corresponding to the first image, and obtain image feature parameters of each of the plurality of first image regions;

[0043] A screening module, configured to screen out a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from at least one image segmentation scheme, wherein the image segmentation scheme information is determined by an image feature parameter of each of a plurality of first image areas corresponding to each image segmentation scheme, and the image segmentation scheme information includes an image occlusion ratio;

[0044] The determination module is used to determine the image occlusion ratio corresponding to the target division scheme, which is the device occlusion ratio of the image acquisition device, and the image acquisition device is a device used to acquire the first image.

[0045] In a third aspect, an electronic device is provided, comprising: a memory for storing computer program instructions; and a processor for reading and running the computer program instructions stored in the memory to execute the occlusion detection method provided by any optional implementation of the first to third aspects.

[0046] In a fourth aspect, a computer storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the occlusion detection method provided by any optional implementation of the first to third aspects is implemented.

[0047] In a fifth aspect, a computer program product is provided. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the occlusion detection method provided by any optional implementation of the first to third aspects.

[0048] In an embodiment of the present application, a first image and at least one image division scheme can be obtained, and then for each image division scheme in at least one image division scheme, the first image can be divided based on the image division scheme to obtain a plurality of first image regions corresponding to the first image, and the image feature parameters of each first image region in the plurality of first image regions can be obtained. Based on this, a target division scheme whose image division scheme information meets a preset condition can be screened from at least one image division scheme, wherein the image division scheme information is determined by the image feature parameters of each first image region in the plurality of first image regions corresponding to each image division scheme. Since the image division scheme information involved above may include an image occlusion ratio, the image occlusion ratio corresponding to the target division scheme can be determined, which is the device occlusion ratio of the image acquisition device, and the image acquisition device is a device for acquiring the first image. In this way, the currently acquired image can be processed based on each image division scheme in the plurality of image division schemes, and a target division scheme with higher accuracy can be determined from the plurality of image division schemes according to the processing results, so as to determine the occlusion detection information of the image acquisition device, thereby improving the accuracy of occlusion detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0050] Figure 1 It is a flowchart of an occlusion detection method provided in an embodiment of the present application;

[0051] Figure 2 This is a flow chart of an occlusion detection method provided in an embodiment of the present application.

[0052] Figure 3 This is one of the application schematic diagrams of an occlusion detection method provided in an embodiment of the present application.

[0053] Figure 4 This is the second application schematic diagram of an occlusion detection method provided in an embodiment of the present application;

[0054] Figure 5 This is the third application schematic diagram of an occlusion detection method provided in an embodiment of the present application;

[0055] Figure 6 is a structural schematic diagram of an occlusion detection device provided in an embodiment of the present application;

[0056] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0058] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0059] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0060] In real life, with the rapid development of intelligent driving technology, on-board cameras are an indispensable part of vehicle perception and decision-making, and play an important role. However, in real road scenes, vehicles often encounter situations where on-board cameras are blocked. The occlusion of on-board cameras will lead to a decrease in the image quality of the images collected by the on-board cameras, and the loss or misinterpretation of key information in the images, which may affect the vehicle's perception of the environment and decision-making ability. Therefore, how to accurately detect whether the camera is blocked is a technical problem that needs to be solved urgently.

[0061] However, in order to solve the above problems, the technical solutions in the prior art mainly focus on image processing, feature extraction and machine learning, etc. Among them, some methods use simple and practical features such as color, texture, or shape for occlusion detection, but these methods are often sensitive to lighting conditions and scene changes, prone to misjudgment, and lack judgment on the degree of camera occlusion and warning level.

[0062] In order to solve the above problems, the embodiments of the present application provide an occlusion detection method, device and equipment, which can obtain a first image and at least one image division scheme, and then for each image division scheme in the at least one image division scheme, the first image can be divided based on the image division scheme to obtain multiple first image areas corresponding to the first image, and the image feature parameters of each first image area in the multiple first image areas can be obtained. Based on this, a target division scheme whose image division scheme information meets the preset conditions can be screened from the at least one image division scheme, wherein the image division scheme information is determined by the image feature parameters of each first image area in the multiple first image areas corresponding to each image division scheme. Since the above-mentioned image division scheme information may include an image occlusion ratio, the image occlusion ratio corresponding to the target division scheme can be determined, which is the device occlusion ratio of the image acquisition device, and the image acquisition device is a device for acquiring the first image. In this way, the currently acquired image can be processed based on each image division scheme in the multiple image division schemes, and a target division scheme with higher accuracy can be determined from the multiple image division schemes according to the processing results, so as to determine the occlusion detection information of the image acquisition device, thereby improving the accuracy of occlusion detection.

[0063] Based on this, it needs to be explained first that the occlusion detection method provided in the embodiment of the present application can be executed by an occlusion detection device, or a control module in the occlusion detection device for executing the above-mentioned camera occlusion driving method. In the embodiment of the present application, the occlusion detection method provided in the embodiment of the present application is explained by taking the occlusion detection device executing the occlusion detection method as an example.

[0064] The following describes in detail the occlusion detection method provided in the embodiment of the present application through specific embodiments in conjunction with the accompanying drawings.

[0065] Figure 1 It is a flow chart of a camera occlusion detection system provided in an embodiment of the present application.

[0066] like Figure 1 As shown, the execution subject of the method may be an occlusion detection device, and the method may specifically include the following steps:

[0067] S101: Acquire a first image and at least one image division scheme.

[0068] In some embodiments, at least one of the above-mentioned image division schemes may be preset based on actual experience, or may be generated based on a preset algorithm or processing method. For example, the image division scheme may be as follows: Figure 3 As shown, the image is divided into 5×5, and no further restrictions are made here.

[0069] S102, for each image division scheme of at least one image division scheme, divide the first image based on the image division scheme to obtain multiple first image regions corresponding to the first image, and obtain image feature parameters of each first image region among the multiple first image regions.

[0070] The occlusion detection device can divide the first image based on each image division scheme in at least one image division scheme, obtain multiple first image areas corresponding to the first image, and obtain image feature parameters of each first image area in the multiple first images.

[0071] S103: Filter and obtain, from at least one image division scheme, a target division scheme whose image division scheme information satisfies a preset condition.

[0072] In some embodiments, the image division scheme information involved above is determined by the image feature parameters of each first image area in the plurality of first image areas corresponding to each image division scheme. The image division scheme information may include an image occlusion ratio.

[0073] Specifically, the occlusion detection device may first determine the image division scheme information corresponding to each image division scheme based on the image feature parameters of each of the multiple first image areas corresponding to each image division scheme, and then screen out a target division scheme whose image division scheme information meets the preset conditions from at least one image division scheme. The preset conditions may be conditions pre-set based on actual experience or circumstances, and are not limited in detail here.

[0074] S104, determining the image occlusion ratio corresponding to the target division scheme, which is the device occlusion ratio of the image acquisition device.

[0075] The image acquisition device mentioned above is a device for acquiring the first image. In addition, the image acquisition device mentioned above may include a camera, a webcam, and other devices, which are not limited here.

[0076] Specifically, after determining the target division scheme, the occlusion detection device can determine the image occlusion ratio corresponding to the target division scheme, which is the occlusion detection information of the image device that captures the first image. Since the image division scheme information can include the image occlusion ratio, the occlusion detection device can determine the image occlusion ratio corresponding to the target division scheme, which is the occlusion detection information of the image device that captures the first image.

[0077] It should be noted that since at least one image division scheme involved in the embodiments of the present application may include a pre-set image division scheme and may also include an image division scheme generated based on an algorithm, in one example, in the embodiments of the present application, multiple consecutive image frames can be divided separately based on the pre-set image division scheme and subsequently processed. If the multiple consecutive image frames are determined to have occlusion, the image division scheme generated by the algorithm can be used to divide the images and perform subsequent processing to achieve further occlusion detection of the images.

[0078] In an embodiment of the present application, a first image and at least one image division scheme can be obtained, and then for each image division scheme in at least one image division scheme, the first image can be divided based on the image division scheme to obtain a plurality of first image regions corresponding to the first image, and the image feature parameters of each first image region in the plurality of first image regions can be obtained. Based on this, a target division scheme whose image division scheme information meets a preset condition can be screened from at least one image division scheme, wherein the image division scheme information is determined by the image feature parameters of each first image region in the plurality of first image regions corresponding to each image division scheme. Since the image division scheme information involved above may include an image occlusion ratio, the image occlusion ratio corresponding to the target division scheme can be determined, which is the device occlusion ratio of the image acquisition device, and the image acquisition device is a device for acquiring the first image. In this way, the currently acquired image can be processed based on each image division scheme in the plurality of image division schemes, and a target division scheme with higher accuracy can be determined from the plurality of image division schemes according to the processing results, so as to determine the occlusion detection information of the image acquisition device, thereby improving the accuracy of occlusion detection.

[0079] In one embodiment, the image feature parameters involved include a first image feature parameter and a second image feature parameter, and the second image feature parameter includes at least one feature parameter. Based on this, before selecting a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from at least one image segmentation scheme, such as Figure 2 As shown, the above-mentioned occlusion detection method may include the following steps:

[0080] S201, determining a second image region among a plurality of first image regions corresponding to a first image where a first image characteristic parameter is greater than a preset parameter threshold.

[0081] Specifically, after the occlusion detection device obtains the characteristic parameters of each image area in the multiple image areas, since the image characteristic parameters may include the first image characteristic parameter and the second image characteristic parameter, based on this, the occlusion detection device can determine the second image area whose first image characteristic parameter is greater than the preset parameter threshold among the multiple first image areas corresponding to the first image. The preset parameter threshold may be a threshold pre-set based on actual experience or circumstances, and is not further limited here.

[0082] S202: Determine an image occlusion ratio of the first image based on a ratio between the first number of regions of the second image and the second number of regions of the first image.

[0083] The first area number may be the area number of the second image area, and the second area number may be the area number of the first image area.

[0084] Specifically, the occlusion detection device can determine the image occlusion ratio of the first image based on the ratio between the first number of regions of the second image region and the second number of regions of the first image region. Exemplarily, the occlusion detection device can determine the ratio between the first number of regions of the second image region and the second number of regions of the first image region as the image occlusion ratio of the first image.

[0085] S203, for each image area among the multiple first image areas, determine the characteristic variance of the target feature parameter corresponding to the image area to obtain multiple characteristic variances, and determine the average value of the multiple characteristic variances as the characteristic variance average value of the target feature parameter to obtain at least one characteristic variance average value, and obtain the target value based on the first preset weight for at least one characteristic variance average value.

[0086] The target characteristic parameter is any one of the at least one characteristic parameter corresponding to the second image characteristic parameter. In addition, it should be noted that the at least one characteristic parameter involved may include parameters such as image brightness and image gradient, which are not specifically limited here.

[0087] Specifically, the occlusion detection device can determine the characteristic variance of the target characteristic parameter corresponding to each image area in the multiple first image areas, so that multiple characteristic variances can be obtained, and then the average value of the multiple characteristic variances can be determined as the characteristic variance average value of the above-mentioned target characteristic parameter, and then the characteristic variance average value corresponding to at least one characteristic parameter can be obtained. Based on this, the occlusion detection device can perform weighted summation of the characteristic variance average values ​​corresponding to at least one characteristic parameter based on the first preset weight to obtain the target value. Among them, the first preset weight can be pre-set based on actual experience, and no excessive restrictions are made here.

[0088] S204, determining the image occlusion ratio and the target value as image division scheme information. Based on this, the above-mentioned method of screening out a target division scheme whose image division scheme information meets a preset condition from at least one image division scheme includes:

[0089] From at least one image division scheme, a target division scheme is screened out, in which the image occlusion ratio is greater than a first preset ratio threshold and the target value is the smallest.

[0090] Specifically, after obtaining the image occlusion ratio and target value corresponding to each image segmentation scheme, the occlusion detection device can screen out a target segmentation scheme whose image occlusion ratio is greater than a first preset ratio threshold and whose target value is the smallest from at least one image segmentation scheme. The first preset ratio can be pre-set based on actual experience or circumstances, and is not limited in detail here.

[0091] In this embodiment, by calculating the image division scheme information corresponding to each image division scheme, a target division scheme with higher accuracy can be selected from at least one image division scheme based on the image division scheme information, thereby facilitating the subsequent accurate determination of the occlusion detection information of the image acquisition device.

[0092] In one embodiment, the above-mentioned step of determining the image occlusion ratio of the first image based on the ratio between the number of first areas of the second image area and the number of second areas of the first image area may include the following steps:

[0093] Determine a ratio between the first number of regions of the second image region and the second number of regions of the first image region as an initial image occlusion ratio;

[0094] When the occlusion ratio of the initial image is greater than a second preset ratio threshold, a plurality of consecutive frames of second images are acquired, and an occluded image region corresponding to each frame of the second image is determined, and image acquisition times of the plurality of consecutive frames of the second images are all earlier than image acquisition times of the first image;

[0095] For each image area in the multiple image areas included in the second image area, based on the blocked image area corresponding to each frame of the second image, determine the blockage ratio of the image area; determine the image area in the multiple image areas whose blockage ratio is greater than the preset blockage ratio as the third image area;

[0096] A ratio between the number of third regions of the third image region and the number of second regions of the first image region is determined as an image occlusion ratio of the first image.

[0097] The second preset ratio threshold may be pre-set based on actual experience or circumstances, and is not limited here. In addition, the image acquisition time of the continuous multiple frames of the second image involved above is earlier than the image acquisition time of the first image. The preset occlusion ratio may be pre-set based on actual experience or circumstances, and is not limited here.

[0098] Specifically, the occlusion detection device can determine the ratio between the first number of areas in the second image area and the second number of areas in the first image area as the initial image occlusion ratio; and then, when the initial image occlusion ratio is greater than the second preset ratio threshold, a plurality of consecutive second image frames can be acquired, and the occluded image area corresponding to each frame of the second image can be determined, and then, for each image area in the plurality of image areas included in the second image area, based on the occluded image area corresponding to each frame of the second image, the occlusion ratio of the image area can be determined, so that the image area in the plurality of image areas whose occlusion ratio is greater than the preset occlusion ratio can be determined as the third image area, and then the ratio between the third number of areas in the third image area and the second number of areas in the first image area can be determined as the image occlusion ratio of the first image. In one example, as Figure 3 As shown, it is assumed that the second region of the first image includes the region <2> ,area <6> ,area <13> ,area <20> and Region <23> , the image occlusion ratio of the first image is 20%, which is greater than the second preset ratio threshold, then 5 consecutive frames of second images are obtained in the historical time to further judge the image occlusion ratio of the first image, if the occluded areas in 4 of the 5 frames of the second image include the area <2> ,area <6> and Region <13> , that is to say, the area <2> ,area <6> ,area <13> The occlusion ratio is 80%, which is greater than the preset occlusion ratio, then the area is determined <2> ,area <6> and Region <13> The third image area is a third image area, and then based on the ratio between the number of third areas of the third image area and the number of second areas of the first image area, a final image occlusion ratio of the first image can be obtained.

[0099] In this embodiment, the occlusion detection can be further performed on the current frame image in combination with the occlusion detection results of multiple frames of images within a historical time period. This can not only reduce noise interference but also improve the accuracy of occlusion detection.

[0100] In some embodiments, the first image feature parameter involved may include at least one of an edge feature parameter and a texture feature parameter. Based on this, before determining a second image region in which the first image feature parameter of the plurality of first image regions corresponding to the first image is greater than a preset parameter threshold, the occlusion detection method involved may further include the following steps:

[0101] Performing edge detection on the image using an edge detection algorithm to obtain edge feature parameters of the first image;

[0102] and / or,

[0103] The image is processed using the gray level co-occurrence matrix to extract the texture feature parameters of the image.

[0104] The edge detection algorithm involved above may be an edge detection algorithm preset based on actual experience or circumstances. For example, the algorithm may be a Canny algorithm, and the gray level co-occurrence matrix involved above may be a Gray Level Co-occurrence Matrix (GLCM).

[0105] Specifically, since the first image feature parameters involved above may include at least one of edge feature parameters and texture feature parameters, based on this, the occlusion detection device can use an edge detection algorithm to perform edge detection on the first image to obtain edge feature parameters of the first image, and / or, the occlusion detection device can also use a gray level co-occurrence matrix to process the first image to extract texture feature parameters of the first image.

[0106] In some embodiments, the edge feature parameters involved include gradient mean and / or gradient variance; the texture feature parameters include contrast and / or energy. Based on this, it should be noted that since the edge feature parameters involved may include gradient mean and gradient variance, the texture feature parameters may include contrast and energy. Accordingly, the preset parameter thresholds involved may include a preset gradient mean threshold, a preset gradient variance threshold, a preset contrast threshold, and a preset energy threshold.

[0107] It should also be noted that the occlusion detection method provided in the embodiment of the present application can also generate weights for each area by constructing a data set including occluded images and unoccluded images, and then perform statistical analysis on the distribution of the data set to determine the various thresholds for occlusion detection. For example, the initial value of the preset texture feature parameter threshold involved above can be set to the sum of the mean of the texture feature parameter in the data set and twice the standard deviation of the texture feature parameter.

[0108] In one example, the process for calculating the gradient mean and the gradient variance can be shown in the following formulas (1) and (2):

[0109]

[0110] Among them, n is the number of pixels in each area, and g is the gradient value of each pixel.

[0111]

[0112] In addition, the process for calculating contrast and / or energy can be shown in the following formulas (3) and (4):

[0113] Contrast=∑ i,j (ij) 2 *P(i,j) (3)

[0114] Energy=∑ i,j (P(i,j)) 2 (4)

[0115] Among them, (ij) is a gray level pair, P(i,j) is the normalized value of the corresponding element in the gray level co-occurrence matrix GLCM, Contrast is the contrast, and Energy is the energy.

[0116] In this embodiment, it can be taken into account that the texture feature parameters and edge feature parameters of the image during normal use of the image acquisition device are relatively rich, while the texture feature parameters and edge feature parameters of the image under occlusion of the image acquisition device are relatively simple. Based on this, an edge detection algorithm can be used to perform edge detection on the image to highlight the edge features of the image, and the texture features of the image can be extracted using a grayscale co-occurrence matrix, so that the second image area can be subsequently determined from multiple first image areas based on the above-mentioned edge feature parameters and / or texture feature parameters, thereby improving the accuracy of subsequent occlusion detection.

[0117] In some embodiments, the first image mentioned above may be a grayscale image. Based on this, the step of acquiring the first image mentioned above may specifically include the following steps:

[0118] Based on color information corresponding to each pixel in the plurality of pixels, a grayscale conversion function is used to perform grayscale conversion processing on the second image to obtain the first image.

[0119] The second image mentioned above may be color information. In some embodiments, the second image mentioned above may include multiple pixels and color information corresponding to each pixel. It should be noted that the color information may be RGB color mode (RGB color mode, RGB) information. In addition, the grayscale conversion function mentioned above may be a function pre-set based on actual experience or circumstances, and is used to convert a color image into grayscale, which is not specifically limited here.

[0120] Specifically, the occlusion detection device can obtain the second image. Since the second image may include multiple pixels and color information corresponding to each pixel, the occlusion detection device can perform grayscale conversion processing on the color information corresponding to each pixel in the second image based on the grayscale conversion function to obtain the first image.

[0121] In an example, the grayscale conversion function involved above can be shown as formula (5), which is specifically as follows:

[0122] Grayscale(x,y)=a*R(x,y)+b*G(x,y)+c*B(x,y) (5)

[0123] Among them, Grayscale(x,y) is the grayscale value of the pixel at the position (x,y), R(x,y), G(x,y), and B(x,y) are the red, green, and blue component values ​​of the pixel at the position (x,y) of the color image. In addition, a, b, and c mentioned above are adjustment coefficients of the red, green, and blue component values, respectively. In an example, a can be 0.2989, b can be 0.5870, and c can be 0.1140.

[0124] In this embodiment, after acquiring the second image, the acquired second image can be gray-scale converted to obtain the first image. In this way, not only the computational complexity can be reduced, but also the structural information of the image can be focused on. In this way, the accuracy of occlusion detection can be improved in the future.

[0125] In addition, since traditional image segmentation methods usually rely on predefined rules and static segmentation schemes, which are generated by analyzing data sets, such divisions are often fixed and relatively rigid, such as 5*5, 4*4, 3*4, etc. However, in actual application scenarios, the location and proportion of occlusion are diverse and have great uncertainty, so a single and fixed segmentation scheme often cannot adapt to various situations, thus affecting the accuracy of occlusion degree judgment. Figure 4 shown.

[0126] Therefore, in order to improve the accuracy of occlusion detection, in one embodiment, the above-mentioned step of obtaining at least one image division scheme may specifically include the following steps:

[0127] Obtain image partitioning constraints;

[0128] At least one image partitioning scheme is generated based on image partitioning constraints using an image segmentation method.

[0129] In some embodiments, the image division constraint mentioned above may include the range of the number of regions divided in the image width direction and the range of the number of regions divided in the image height direction. That is, the image division constraint specifies the limit of the number of regions divided in the image width and height directions. For example, the image division constraint may set the number of regions divided in the image width and height directions to be between 3 and 7. Specifically, no specific limitation is made here.

[0130] In addition, the preset processing methods mentioned above may be permutation and combination methods, or heuristic algorithms, etc., and the specifics are not limited too much here.

[0131] In this embodiment, the occlusion detection device can obtain the image division constraint conditions, and then can generate at least one image division scheme based on the image division constraint conditions by using the image segmentation method. In this way, it is convenient to determine the target image division scheme with higher accuracy from at least one image division scheme, that is, to determine the image division scheme that best suits the current situation from at least one image division scheme, so that the algorithm can cope with the challenges of different occlusion positions, sizes and shapes, thereby significantly improving the accuracy and robustness of occlusion degree judgment. In addition, compared with the traditional static scheme, it reduces the cumbersomeness of manually setting segmentation rules and schemes, and is more intelligent.

[0132] In one embodiment, after the above-mentioned step of determining the image occlusion ratio corresponding to the target division scheme as the device occlusion ratio of the image acquisition device, the above-mentioned occlusion detection method may specifically include the following steps:

[0133] Based on the preset corresponding relationship between the device occlusion ratio and the warning level, the device occlusion ratio is matched to obtain the first warning level of the image acquisition device.

[0134] The correspondence between the preset device occlusion ratio and the warning level may be preset based on actual experience or circumstances, and is not further limited here.

[0135] Specifically, after obtaining the device occlusion ratio of the image acquisition device, the occlusion detection device can match the device occlusion ratio of the image acquisition device based on the corresponding relationship between the preset device occlusion ratio and the occlusion level to obtain the first warning level of the image acquisition device.

[0136] In this embodiment, the occlusion detection device can make warnings and decisions to varying degrees according to actual conditions, and effectively deal with the risks and challenges caused by occlusion.

[0137] In addition, in order to further evaluate the importance and sensitivity of the occlusion state to different functional modules, the embodiment of the present application constructs the weight of each image area after gridding, and assigns a corresponding weight to each image area according to the requirements and priorities of different functional modules to reflect its importance to the system function. Based on this, in one embodiment, the occlusion detection method involved above may also include the following steps:

[0138] respectively determining region status information of a plurality of first image regions;

[0139] Based on the preset area weights, weighted summation is performed on the area status information of the plurality of first images to obtain an image occlusion degree of the first image, and the image occlusion degree of the first image is determined to be a device occlusion degree of the image acquisition device;

[0140] Based on the preset corresponding relationship between the device occlusion degree and the warning level, the device occlusion degree is matched to obtain the second warning level of the image acquisition device.

[0141] Among them, the area status information can be the occluded state of the first image area or the unoccluded state of the first image area. In addition, the preset area weights involved above can be pre-set based on actual experience or circumstances, and are not limited too much here. It should also be noted that the correspondence between the preset device occlusion degree and the warning level involved above is pre-set based on actual experience or circumstances, and is not limited too much here.

[0142] Specifically, the occlusion detection device can respectively determine the regional status information of multiple first image areas, and then, based on the preset regional weights, perform weighted summation on the regional status information of multiple first images to obtain the image occlusion degree of the first images, and then determine the image occlusion degree of the first image as the device occlusion degree of the image acquisition device, and then, based on the corresponding relationship between the preset device occlusion degree and the warning level, match the device occlusion degree to obtain the second warning level of the image acquisition device.

[0143] The weighted process can be calculated by the following formula: O = ΣW(i,j)*H(i,j), where H(i,j) represents the occlusion state of the region in the i-th row and j-th column, and W(i,j) represents the weight value of the region in the i-th row and j-th column.

[0144]

[0145] Based on this, the occlusion detection device can determine the device occlusion degree of the image acquisition device according to the image occlusion degree of the first image, and then can combine the predefined rules and thresholds to output different warning levels so that the occlusion detection device can take corresponding warning and control strategies. For example, if the device occlusion degree exceeds threshold A, the second warning level of the image acquisition device is determined to be the first level, that is, it is determined that the functional module of the image acquisition device is completely ineffective; if the device occlusion degree is between threshold B and threshold A, the second warning level of the image acquisition device is determined to be the second level, that is, it is determined that the functional module of the image acquisition device is disturbed and the accuracy is impaired; if the device occlusion degree is lower than threshold B, the second warning level of the image acquisition device is determined to be the third level, that is, it is determined that the image acquisition device can work normally.

[0146] In one example, considering that the middle and lower areas of the image have a greater impact on the normal operation of the functional module, once blocked, it is likely to cause functional misjudgment or even failure, so it should be given a larger weight, while the edge position, especially the top position, has basically no effect on the function, and even if blocked, it does not affect the execution of the function, so it should be given a smaller weight. The specific weight distribution can be as follows Figure 5 (a) and Figure 5 (b). In yet another example, Figure 5 (c) and Figure 5 (d) is a weight of the traffic participant detection module in intelligent driving, which focuses more on the central area of ​​the image. With the help of weights, the system can respond more flexibly when the camera is blocked and accurately feedback to the corresponding functional module. In this way, the final weight of each functional module can be generated based on the size of each grid falling in each area of ​​the preset functional module mask: the grid with the highest area in each area of ​​the preset mask is the weight of the current grid.

[0147] In this embodiment, the needs and priorities of different image areas are taken into consideration, corresponding weights are generated, and the degree of occlusion of the entire image is calculated in combination with the regional status information of the image area. This enables the occlusion detection device to make different degrees of warnings and decisions based on actual conditions, and effectively respond to the risks and challenges caused by occlusion.

[0148] Based on the same inventive concept, the present application also provides an occlusion detection device. The occlusion detection device can be applied to a planning device, specifically in combination with Figure 6 The occlusion detection device provided in the embodiment of the present application is described in detail.

[0149] Figure 6 It is a structural schematic diagram of an occlusion detection device provided in an embodiment of the present application.

[0150] like Figure 6As shown, the occlusion detection device 600 may include: an acquisition module 610 , a division module 620 , a screening module 630 and a determination module 640 .

[0151] An acquisition module 610, configured to acquire a first image and at least one image division scheme;

[0152] a division module 620, configured to divide the first image based on the image division scheme for each of the at least one image division schemes, obtain a plurality of first image regions corresponding to the first image, and obtain an image feature parameter of each of the plurality of first image regions;

[0153] A screening module 630 is used to screen out a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from at least one image segmentation scheme, wherein the image segmentation scheme information is determined by an image feature parameter of each of a plurality of first image areas corresponding to each image segmentation scheme, and the image segmentation scheme information includes an image occlusion ratio;

[0154] The determination module 640 is used to determine the image occlusion ratio corresponding to the target division scheme, which is the occlusion detection information of the image acquisition device, and the image acquisition device is a device used to acquire the first image.

[0155] In one embodiment, the image feature parameters include a first image feature parameter and a second image feature parameter, and the second image feature parameter includes at least one feature parameter; based on this, the above-mentioned occlusion detection device also includes a weighted summation module.

[0156] The determination module is further used to determine a second image region whose first image feature parameter is greater than a preset parameter threshold among the multiple first image regions corresponding to the first image;

[0157] The determination module is further used to determine the image occlusion ratio of the first image based on the ratio between the first area number of the second image area and the second area number of the first image area;

[0158] The weighted summation module is further used to determine, for each image area of ​​the multiple first image areas, a feature variance of a target feature parameter corresponding to the image area to obtain multiple feature variances, and determine an average value of the multiple feature variances as a feature variance average value of the target feature parameter to obtain at least one feature variance average value, and perform weighted summation of at least one feature variance average value based on a first preset weight to obtain a target value, where the target feature parameter is any one of the at least one feature parameter corresponding to the second image feature parameter;

[0159] The determination module is further used to determine the image occlusion ratio and the target value as the image division scheme information.

[0160] In one embodiment, the determination module is specifically used to:

[0161] Determine a ratio between the first number of regions of the second image region and the second number of regions of the first image region as an initial image occlusion ratio;

[0162] When the occlusion ratio of the initial image is greater than a second preset ratio threshold, a plurality of consecutive frames of second images are acquired, and an occluded image region corresponding to each frame of the second image is determined, and image acquisition times of the plurality of consecutive frames of the second images are all earlier than image acquisition times of the first image;

[0163] For each image area in the multiple image areas included in the second image area, based on the blocked image area corresponding to each frame of the second image, determine the blockage ratio of the image area; determine the image area in the multiple image areas whose blockage ratio is greater than the preset blockage ratio as the third image area;

[0164] A ratio between the number of third regions of the third image region and the number of second regions of the first image region is determined as an image occlusion ratio of the first image.

[0165] In one embodiment, the first image feature parameter includes at least one of an edge feature parameter and a texture feature parameter; the above-mentioned occlusion detection device includes an edge detection module and an extraction module.

[0166] An edge detection module, used to perform edge detection on the first image using an edge detection algorithm to obtain edge feature parameters of the first image;

[0167] The extraction module is used to process the first image using the gray level co-occurrence matrix to extract texture feature parameters of the first image.

[0168] In one embodiment, the first image is a grayscale image; the acquisition module is specifically used to:

[0169] Acquire a second image, where the second image includes a plurality of pixels and color information corresponding to each of the plurality of pixels;

[0170] Based on color information corresponding to each pixel in the plurality of pixels, a grayscale conversion function is used to perform grayscale conversion processing on the second image to obtain the first image.

[0171] In one embodiment, the acquisition module is specifically used for:

[0172] Obtaining image division constraint conditions, the image division constraint conditions including the range of the number of area divisions of the image in the image width direction and the range of the number of area divisions of the image in the image height direction;

[0173] At least one image partitioning scheme is generated based on image partitioning constraints using an image segmentation method.

[0174] In one embodiment, the aforementioned occlusion detection device further includes a matching module.

[0175] The matching module is used to match the device occlusion ratio based on the preset corresponding relationship between the device occlusion ratio and the warning level to obtain the first warning level of the image acquisition device.

[0176] In one embodiment, the determination module is further used to respectively determine the region status information of the plurality of first image regions;

[0177] A weighted summation module, configured to perform weighted summation on the regional status information of the plurality of first images based on preset regional weights to obtain an image occlusion degree of the first images, and determine the image occlusion degree of the first images as a device occlusion degree of the image acquisition device;

[0178] A matching module is used to match the device occlusion degree based on the correspondence between the preset device occlusion degree and the warning level to obtain the second warning level of the image acquisition device. In an embodiment of the present application, a first image and at least one image division scheme can be obtained, and then for each image division scheme in the at least one image division scheme, the first image can be divided based on the image division scheme to obtain multiple first image areas corresponding to the first image, and the image feature parameters of each first image area in the multiple first image areas can be obtained. Based on this, a target division scheme whose image division scheme information meets the preset conditions can be screened from at least one image division scheme, wherein the image division scheme information is determined by the image feature parameters of each first image area in the multiple first image areas corresponding to each image division scheme. Since the above-mentioned image division scheme information may include an image occlusion ratio, the image occlusion ratio corresponding to the target division scheme can be determined, which is the device occlusion ratio of the image acquisition device, and the image acquisition device is a device for acquiring the first image. In this way, the currently acquired image can be processed based on each of the multiple image division schemes, and a target division scheme with higher accuracy can be determined from the multiple image division schemes according to the processing results, so as to determine the occlusion detection information of the image acquisition device, thereby improving the accuracy of occlusion detection.

[0179] Each module in the occlusion detection device provided in the embodiment of the present application can be implemented Figure 1 or Figure 2 The method steps of the embodiment shown in the figure can achieve the corresponding technical effects, and for the sake of brevity, they will not be repeated here.

[0180] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0181] The electronic device may include a processor 701 and a memory 702 storing computer program instructions.

[0182] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0183] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 702 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0184] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0185] The processor 701 implements any one of the occlusion detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 702 .

[0186] In one example, the electronic device may further include a communication interface 703 and a bus 710. Figure 7 into mutual communication.

[0187] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0188] Bus 710 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0189] In addition, in combination with the occlusion detection method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the occlusion detection method provided in the embodiment of the present application is implemented.

[0190] An embodiment of the present application also provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the occlusion detection method provided in the embodiment of the present application.

[0191] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0192] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0193] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0194] Aspects of the present disclosure are described above with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable occlusion detection device to produce a machine so that these instructions executed by the processor of the computer or other programmable occlusion detection device enable the implementation of the functions / actions specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0195] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for detecting occlusion, characterized in that: The method comprises: Acquire a first image and at least one image segmentation scheme; For each image division scheme of the at least one image division scheme, dividing the first image based on the image division scheme to obtain a plurality of first image regions corresponding to the first image, and acquiring image feature parameters of each first image region among the plurality of first image regions; From the at least one image division scheme, a target division scheme whose image division scheme information satisfies a preset condition is screened and obtained, wherein the image division scheme information is determined by an image feature parameter of each of a plurality of first image areas corresponding to each of the image division schemes, and the image division scheme information includes an image occlusion ratio; An image occlusion ratio corresponding to the target division scheme is determined as a device occlusion ratio of an image acquisition device, where the image acquisition device is a device used to acquire the first image.

2. The method according to claim 1, characterized in that: The image feature parameters include a first image feature parameter and a second image feature parameter, wherein the second image feature parameter includes at least one feature parameter; Before screening out a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from the at least one image segmentation scheme, the method further includes: Determine a second image region among the plurality of first image regions corresponding to the first image where the first image feature parameter is greater than a preset parameter threshold; determining an image occlusion ratio of the first image based on a ratio between a first number of regions of the second image region and a second number of regions of the first image region; For each of the multiple first image regions, determine a feature variance of a target feature parameter corresponding to the image region to obtain multiple feature variances, determine an average of the multiple feature variances as a feature variance average of the target feature parameter to obtain at least one feature variance average, and perform weighted summation of the at least one feature variance average based on a first preset weight to obtain a target value, wherein the target feature parameter is any one of the at least one feature parameter corresponding to the second image feature parameter; Determine the image occlusion ratio and the target value as the image division scheme information; The step of screening out a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from the at least one image segmentation scheme comprises: From the at least one image division scheme, a target division scheme is screened out, in which the image occlusion ratio is greater than a first preset ratio threshold and the target value is the smallest.

3. The method according to claim 2, characterized in that The determining the image occlusion ratio of the first image based on the ratio between the first number of regions of the second image region and the second number of regions of the first image region comprises: Determine a ratio between the first number of regions of the second image region and the second number of regions of the first image region as an initial image occlusion ratio; When the occlusion ratio of the initial image is greater than a second preset ratio threshold, acquiring a plurality of consecutive frames of second images, and determining an occluded image region corresponding to each frame of the second image, wherein image acquisition times of the plurality of consecutive frames of second images are earlier than image acquisition times of the first image; For each image area among the multiple image areas included in the second image area, based on the blocked image area corresponding to each frame of the second image, determine the blockage ratio of the image area; determine an image area among the multiple image areas whose blockage ratio is greater than a preset blockage ratio as a third image area; A ratio between the number of third regions of the third image region and the number of second regions of the first image region is determined as an image occlusion ratio of the first image.

4. The method according to claim 2, characterized in that: The first image feature parameter includes at least one of an edge feature parameter and a texture feature parameter; Before determining a second image region in which a first image feature parameter is greater than a preset parameter threshold value among a plurality of first image regions corresponding to the first image, the method further includes: Performing edge detection on the first image using an edge detection algorithm to obtain edge feature parameters of the first image; and / or, The first image is processed using a gray level co-occurrence matrix to extract texture feature parameters of the first image.

5. The method according to claim 1, characterized in that: The first image is a grayscale image; and obtaining the first image includes: Acquire a second image, where the second image includes a plurality of pixels and color information corresponding to each of the plurality of pixels; Based on the color information corresponding to each pixel in the multiple pixels, a grayscale conversion function is used to perform grayscale conversion processing on the second image to obtain the first image.

6. The method according to claim 1, characterized in that Obtain at least one image partitioning scheme, including: Obtaining image division constraint conditions, wherein the image division constraint conditions include a range of the number of area divisions of the image in the image width direction and a range of the number of area divisions of the image in the image height direction; At least one image partitioning scheme is generated based on the image partitioning constraint conditions using an image partitioning method.

7. The method according to claim 1, characterized in that After determining that the image occlusion ratio corresponding to the target division scheme is a device occlusion ratio of the image acquisition device, the method further includes: Based on a preset correspondence between a device occlusion ratio and a warning level, the device occlusion ratio is matched to obtain a first warning level of the image acquisition device.

8. The method according to claim 1, characterized in that: The method further comprises: respectively determining region status information of a plurality of first image regions; Based on preset area weights, performing weighted summation on the area status information of the plurality of first images to obtain an image occlusion degree of the first images, and determining the image occlusion degree of the first images as a device occlusion degree of the image acquisition device; Based on a preset correspondence between the device occlusion degree and the warning level, the device occlusion degree is matched to obtain a second warning level of the image acquisition device.

9. An occlusion detection device, characterized in that: Applied to planning equipment, the device comprises: An acquisition module, used for acquiring a first image and at least one image division scheme; a division module, configured to divide the first image based on each of the at least one image division schemes to obtain a plurality of first image regions corresponding to the first image, and obtain image feature parameters of each of the plurality of first image regions; A screening module, configured to screen out a target segmentation scheme whose image segmentation scheme information satisfies a preset condition from the at least one image segmentation scheme, wherein the image segmentation scheme information is determined by an image feature parameter of each of a plurality of first image areas corresponding to each of the image segmentation schemes, and the image segmentation scheme information includes an image occlusion ratio; The determination module is used to determine the image occlusion ratio corresponding to the target division scheme, which is the device occlusion ratio of the image acquisition device, and the image acquisition device is the device used to acquire the first image.

10. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the occlusion detection method according to claims 1-8.

Images