Ground foreign matter detection method, device, equipment and medium based on radar chart

Abstract

The application discloses a radar chart-based ground foreign matter detection method, device, equipment and medium. The method comprises the following steps: acquiring a current radar image of a radar detection area; obtaining a current contour frame information library according to the current radar image; wherein the current contour frame information library comprises current contour frame information of at least one to-be-detected target; and performing foreign matter detection on the to-be-detected target according to the current contour frame information and a historical contour frame information library of the to-be-detected target; wherein the historical contour frame information library is determined according to the historical radar image. According to the technical scheme, accurate current contour frame information library can be obtained through analysis and processing of the current radar image, and then the current contour frame information of the to-be-detected target is compared with the historical contour frame information library, so that whether the to-be-detected target is a foreign matter can be accurately and quickly detected.

Description

Technical Field

[0001] This invention relates to the field of image detection technology, and in particular to a method, apparatus, device, and medium for detecting ground foreign objects based on radar images. Background Technology

[0002] Digital transportation is a crucial area for the development of the digital economy. As the transportation industry becomes increasingly intelligent, digitalized, and information-based, problems caused by foreign objects on the ground are receiving growing attention. For example, in transportation scenarios such as tunnels and highways, the presence of foreign objects can easily trigger a series of traffic accidents, significantly impacting traffic flow and causing serious safety issues. How to accurately and promptly identify and handle foreign objects has become a vital topic in the field of intelligent transportation safety.

[0003] The existing solutions for detecting foreign objects on roads utilize scanning radar to generate panoramic radar images. However, numerous image factors on roads can interfere with foreign object detection in the radar images, making it difficult to quickly and accurately detect the presence of foreign objects and potentially leading to false positives. Therefore, accurate detection of foreign objects is becoming increasingly important. Summary of the Invention

[0004] This invention provides a ground foreign object detection method, apparatus, device, and medium based on radar images to solve the problem of how to quickly detect foreign objects through radar images.

[0005] According to one aspect of the present invention, a ground foreign object detection method based on radar images is provided, the method comprising:

[0006] Acquire the current radar image of the radar detection area;

[0007] A current contour bounding box information database is obtained based on the current radar image; wherein, the current contour bounding box information database includes at least one current contour bounding box information of a target to be detected;

[0008] Foreign object detection is performed on the target based on the current outline bounding box information and the historical outline bounding box information database; wherein, the historical outline bounding box information database is determined based on the historical radar images.

[0009] According to another aspect of the present invention, a ground foreign object detection device based on radar charts is provided, the device comprising:

[0010] The image determination module is used to acquire the current radar image of the radar detection area;

[0011] The information database determination module is used to obtain a current contour bounding box information database based on the current radar image; wherein, the current contour bounding box information database includes at least one current contour bounding box information of a target to be detected;

[0012] The detection module is used to perform foreign object detection on the target based on the current outline bounding box information and the historical outline bounding box information database; wherein the historical outline bounding box information database is determined based on the historical radar images.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the ground foreign object detection method based on radar charts according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the ground foreign object detection method based on radar charts according to any embodiment of the present invention.

[0018] The technical solution of this invention accurately obtains a current contour border information library from the current radar image of the radar detection area. This library includes at least one current contour border information for a target to be detected. Foreign object detection is then performed on the target based on the current contour border information and a historical contour border information library, where the historical contour border information library is determined based on historical radar images. This technical solution obtains an accurate current contour border information library by analyzing and processing each pixel in the current radar image. The current contour border information of the target to be detected is then compared with the historical contour border information library to quickly and accurately detect the presence of foreign objects on the target.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a ground foreign object detection method based on radar charts according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a ground foreign object detection method based on radar images according to Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of a rectangular region selection method provided according to an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of a ground foreign object detection device based on a radar image, according to Embodiment 3 of the present invention.

[0025] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the radar image-based ground foreign object detection method according to an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart of a radar-based ground foreign object detection method according to Embodiment 1 of the present invention. This embodiment is applicable to the detection of foreign objects in scenarios with relatively fixed internal spatial environments (such as tunnels). The method can be executed by a radar-based ground foreign object detection device, which can be implemented in hardware and / or software. This radar-based ground foreign object detection device can be configured in the electronic equipment of the radar-based ground foreign object detection method. Figure 1 As shown, the method includes:

[0030] S110. Obtain the current radar image of the radar detection area.

[0031] The current radar image can be formed when a vehicle enters the radar detection area, the radar transmitter emits radio waves into the detection area, and the receiver receives the scattered echoes. The current radar image can be divided into several small squares, each called a pixel. By analyzing and processing the information of each pixel, the information features of each detection location point in the radar detection area corresponding to each pixel can be obtained, thereby determining the information of the target to be detected. For example, by analyzing and processing the position, color, and brightness information of each pixel in the current radar image, the situation of the target to be detected corresponding to the radar detection area can be accurately obtained.

[0032] S120. Obtain a current contour border information database based on the current radar image; wherein, the current contour border information database includes at least one current contour border information of a target to be detected.

[0033] The current contour bounding box information database can be a database used to store the current contour bounding box information of the target to be detected after analyzing and processing the current radar image. The current contour bounding box information is used to describe the bounding box information of the target to be detected in the current radar image. For example, the contour bounding box information can be the boundary information of the smallest rectangle that contains the contour and has a perpendicular boundary.

[0034] Specifically, by extracting the contour of the target to be detected in the current radar image, accurately obtaining the current contour border information of the target to be detected in the current radar image, and putting it into the current contour border information database, it can ensure that the detection of foreign objects on the target to be detected is more accurate.

[0035] S130. Foreign object detection is performed on the target to be detected based on the current outline bounding box information and the historical outline bounding box information database; wherein, the historical outline bounding box information database is determined based on the historical radar image.

[0036] The current outline bounding box information includes outline bounding box position information. The outline bounding box position information can be coordinate information representing the target's location. The historical outline bounding box information database includes at least one historical outline bounding box record, which includes at least outline bounding box position information and outline bounding box attribute information; the historical outline bounding box information database can be a database of historical outline bounding box information of the target to be detected obtained by analyzing and processing historical radar images. The historical radar image can be the previous frame of the current radar image. Foreign objects can be debris or other objects that may affect road traffic.

[0037] In a feasible embodiment, foreign object detection is performed on the target based on the current contour border information and the historical contour border information database, including the following steps A1-A4:

[0038] A1. Traverse the historical outline border information in the historical outline border information database, and determine the overlap between the historical outline border information and each current outline border information in the current outline border information database according to the outline border position information.

[0039] A2. Determine the target current contour border information that has the highest overlap with the historical contour border information in the current contour border information database.

[0040] A3. Update the outline and border attribute information of the historical outline and border information according to the overlap degree.

[0041] A4. Based on the updated outline border attribute information, perform foreign object detection on the target to be detected corresponding to the current outline border information of the target.

[0042] Among them, the outline border position information is the minimum circumscribed rectangle bounding box information.

[0043] Specifically, the historical outline border information in the historical outline border information database is traversed, and the overlap degree between the historical outline border information and each current outline border information in the current outline border information database is determined according to the outline border position information. The overlap degree can be determined according to the following formula:

[0044]

[0045] in, and The top-left and bottom-right corner positions of the rectangular bounding boxes representing historical outline border information are respectively provided. and The top-left and bottom-right corner positions of the rectangular bounding box that represent the current outline border information are respectively.

[0046] Based on the overlap between the determined historical contour border information and the current contour border information in the current contour border information database, the target current contour border information with the highest overlap with the historical contour border information in the current contour border information database is found. The contour border attribute information of the historical contour border information is updated according to the overlap, so that the historical contour border information database is more accurate. Foreign object detection of the target can be accurately performed based on the contour border attribute information in the historical contour border information database.

[0047] This technical solution uses a formula to accurately calculate the overlap between historical contour border information and current contour border information in the current contour border information database. It then identifies the current contour border information with the highest overlap as the target current contour border information corresponding to the historical contour border information. Based on the overlap, the contour border attribute information of the historical contour border information is updated, making the contour border attribute information of the historical contour border information more accurate in representing the target to be detected. Finally, based on the updated contour border attribute information, foreign object detection is performed on the target to be detected corresponding to the target current contour border information, achieving rapid and accurate detection of whether the target to be detected is a foreign object.

[0048] In a feasible embodiment, updating the outline border attribute information of the historical outline border information according to the overlap degree may include the following steps B1-B2:

[0049] B1. If the overlap is greater than or equal to a preset overlap threshold, then update the count of the number of consecutive static frames and set the count of the number of consecutive frames without target association to zero.

[0050] B2. If the overlap is less than a preset overlap threshold, then update the count of the number of consecutive unassociated frames and set the count of the number of consecutive stationary frames to zero.

[0051] The outline bounding box attribute information includes at least the number of consecutive target-free associated frames and the number of consecutive stationary frames. The number of consecutive target-free associated frames φ can refer to the number of consecutive radar image frames in which the target to be detected has not appeared, corresponding to the current outline bounding box information. The number of consecutive stationary frames τ is used to characterize the number of frames in which the target's position stops changing during movement, and can be used to determine the length of time the target has stopped moving. A preset overlap threshold T can be used to determine the minimum value that matches historical outline bounding box information with each current outline bounding box information in the current outline bounding box information database.

[0052] Specifically, the overlap between historical contour border information and current contour border information in the current contour border information database is obtained. If the overlap is greater than or equal to a preset overlap threshold, it means that the historical contour border information and the corresponding target current contour border information can represent the same target. In this case, the number of consecutive still frames is updated, i.e., τ = τ + 1, and the number of consecutive frames without target association is set to zero. If the overlap is less than the preset overlap threshold, it means that the target is no longer in the radar detection area at the current moment. In this case, the number of consecutive frames without target association is updated, i.e., φ = φ + 1, and the number of consecutive still frames is set to zero.

[0053] This technical solution uses the overlap degree and a preset overlap degree threshold to accurately update the outline and border attribute information of historical outline and border information, which is beneficial for subsequent accurate detection of whether the target is a foreign object.

[0054] In a feasible embodiment, foreign object detection is performed on the target to be detected corresponding to the current contour border information of the target based on the updated contour border attribute information, including:

[0055] If the updated number of consecutive still frames is greater than the preset threshold for the number of consecutive still frames, then the target to be detected corresponding to the target's current outline bounding box information is determined to be a foreign object, and the target's current outline bounding box information is deleted from the current outline bounding box information database.

[0056] Among them, the minimum number of consecutive static frames that the target has stopped is determined by the preset consecutive static frame threshold.

[0057] Specifically, after determining that the overlap is greater than or equal to a preset overlap threshold, the updated contour border attribute information of the target to be detected corresponding to the target's current contour border information in the historical contour border information database is extracted. It is then determined whether the updated consecutive still frames are greater than a preset consecutive still frame threshold. If the updated consecutive still frames are greater than the preset consecutive still frame threshold, it indicates that the target to be detected has stopped, and the target to be detected corresponding to the target's current contour border information is determined to be a foreign object. The target's current contour border information is then deleted from the current contour border information database. If the updated consecutive still frames are less than the preset consecutive still frame threshold, it indicates that the target to be detected has not yet stopped, and the contour border attribute information continues to be updated.

[0058] This technical solution achieves accurate and rapid determination of whether the target to be detected is a foreign object by performing foreign object detection on the target corresponding to the current contour border information based on the updated contour border attribute information.

[0059] In a feasible embodiment, after performing foreign object detection on the target to be detected corresponding to the current contour border information of the target based on the updated contour border attribute information, the method further includes:

[0060] If the updated number of consecutive frames without a target is greater than the preset threshold for the number of consecutive frames without a target, then the historical outline border information will be deleted from the historical outline border information database.

[0061] The preset threshold for the number of consecutive frames without target association is used to determine whether the target still exists in the radar detection area.

[0062] Specifically, after determining that the overlap is less than the preset overlap threshold, the updated contour border attribute information of the target to be detected corresponding to the current contour border information of the target in the historical contour border information database is extracted. If the number of consecutive frames without target association after the update is greater than the preset threshold for the number of consecutive frames without target association, it means that the object is no longer in the radar detection area and the historical contour border information of the target to be detected is invalid information. In this case, the historical contour border information should be deleted from the historical contour border information database.

[0063] This technical solution determines whether the historical outline bounding box information of the target to be detected is invalid by judging whether the number of consecutive unassociated frames after the update is greater than the preset threshold for the number of consecutive unassociated frames. If it is invalid, the historical outline bounding box information is deleted from the historical outline bounding box information database in a timely manner to ensure the accuracy of the historical outline bounding box information database.

[0064] In a feasible embodiment, after performing foreign object detection on the target to be detected corresponding to the current contour border information of the target based on the updated contour border attribute information, the method further includes:

[0065] Based on the remaining current outline border information in the current outline border information library, new historical outline border information is added to the historical outline border information library, and the outline border attribute information of the new historical outline border information is initialized.

[0066] Specifically, the current contour border information database is traversed. If the current contour border information still exists in the current contour border information database, it means that a new target has appeared in the radar detection area. In this case, the remaining current contour border information in the current contour border information database needs to be added to the historical contour border information database to ensure the richness of the historical contour border information database. The contour border attribute information of the new historical contour border information is initialized, i.e., τ=0, φ=0.

[0067] For example, the current contour border information library C includes three current contour border information items: C1, C2, and C3. The historical contour border information library S includes three historical contour border information items: S1, S2, and S3. After overlap calculation, C1 is determined to be the target current contour border information item corresponding to S1, C2 is the target current contour border information item corresponding to S2, and C3 is the target current contour border information item corresponding to S3. If the overlap between C1 and S1 is greater than a preset overlap threshold, the contour border attribute information of S1 is updated, and C1 is deleted from the current contour border information library C. If the overlap between C2 and S2 and C3 and S3 is less than a preset overlap threshold, the contour border attribute information of S2 and S3 is directly updated, and C2 and C3 are added to the historical contour border information library S.

[0068] This technical solution expands the historical outline border information database by adding new historical outline border information to the database of remaining current outline border information. This ensures the accuracy of the historical outline border information database and avoids misjudgment of foreign object detection due to missing information, thereby improving the accuracy of foreign object detection.

[0069] In a feasible embodiment, after determining that the target to be detected corresponding to the current contour bounding information of the target is a foreign object, the method further includes:

[0070] The location information of the foreign object is determined based on the outline position information in the current outline outline information of the target.

[0071] Specifically, the location information of the foreign object can be determined using the following formula:

[0072]

[0073] Where (x,y) represents the location information of the foreign object, and (r,c) represents the center location information of the minimum bounding rectangle. (r tl ,c tl ) and (r br ,c br ) represent the top-left and bottom-right corner positions of the minimum bounding rectangle, respectively. Δ represents the correspondence between pixels in the current radar image and the actual region, and P and Q represent the number of rows and columns in the current radar image, respectively.

[0074] This technical solution uses the position information of the outline of the target in the current outline outline information to accurately calculate the position information of the foreign object through a formula. It can promptly handle foreign objects on the road based on the position information of the foreign object, thus ensuring road driving safety.

[0075] The technical solution of this invention acquires the current radar image of the radar detection area and analyzes and processes the current radar image to accurately obtain the current contour border information database. The current contour border information database includes at least one current contour border information of the target to be detected. Then, based on the contour border position information, the overlap degree between the historical contour border information and each current contour border information in the current contour border information database is determined sequentially. The contour border attribute information of the historical contour border information is updated according to the overlap degree to ensure the accuracy of the historical contour border information database. Finally, foreign object detection is performed on the target to be detected based on the updated contour border attribute information to achieve rapid and accurate detection of whether there are foreign objects on the target to be detected.

[0076] Example 2

[0077] Figure 2 This is a flowchart of a ground foreign object detection method based on radar images according to Embodiment 2 of the present invention. This embodiment is a detailed description of obtaining the current contour bounding box information database based on the current radar image in the above embodiment. Figure 2 As shown, the method includes:

[0078] S210. Obtain the current radar image of the radar detection area, and separate the background and foreground in the current radar image to obtain the target radar image after background removal.

[0079] Specifically, the radar detection area is set in a tunnel scene, where the internal spatial environment is relatively fixed and does not change arbitrarily. Therefore, the background in the radar image is relatively simple. Furthermore, due to the influence of the tunnel's internal structure, the actual tunnel area to be detected in the current radar image is a rectangular region. For example, see the radar image obtained from a tunnel scene. Figure 3 In the image, circular area 1 represents the radar-detectable area, and rectangular area 2 represents the actual detection area where the tunnel is located. For example, a rectangular area is defined within the radar-detectable area. The portion outside this rectangular area is the relatively fixed tunnel background and will not significantly affect the detection of foreign objects on the tunnel surface. Therefore, the actual radar detection area is set to this rectangular area, and everything outside can be considered the background. This reduces unnecessary detection and calculation, speeding up the image processing. Specifically, based on the correspondence between pixels in the radar image and the actual area, the position of the tunnel surface area within the radar-detectable area is determined, resulting in the corresponding rectangular area as the final current radar image.

[0080] Furthermore, the background removal method can be used to remove the background from the current radar image, resulting in an accurate target radar image with the background removed. At the same time, using the background removal method to remove the background from the current radar image can significantly reduce the computational load and achieve simple, fast, and accurate background removal.

[0081] In a feasible embodiment, separating the background and foreground in the current radar image to obtain a target radar image after background removal may include the following steps C1-C3:

[0082] Step C1: Determine a preset number of previous radar images acquired in the radar detection area before acquiring the current radar image; the previous radar images include radar images acquired in the immediate vicinity before acquiring the current radar image or radar images acquired by closing off the radar detection area.

[0083] Step C2: Perform image accumulation and averaging on a preset number of previous radar images to obtain the accumulated average image corresponding to the previous radar image.

[0084] Step C3: Based on the cumulative average image, separate the background and foreground in the current radar image to obtain the target radar image after background removal.

[0085] The preset quantity can be determined based on actual needs, representing the number of radar images that need to be acquired by scanning the radar detection area before acquiring the current radar image. The previous radar image can be a collection of all radar images acquired by scanning the radar detection area within a recent timeframe before acquiring the current radar image; or it can be an image acquired by scanning the radar detection area under conditions where the radar detection area is closed off to prevent interference from vehicles or other factors. The radar in question is a microwave radar, such as a millimeter-wave radar.

[0086] Specifically, a preset number of previous radar images are obtained by scanning the radar detection area, and each image can be denoted as F. Then, the preset number of previous radar images are accumulated and averaged to obtain the accumulated average image F of the previous radar images. Next, the current radar image obtained by scanning the radar detection area at the current moment is obtained. Since the target to be detected in the current radar image does not appear in the previous radar image, the accumulated average image F of the previous radar image can be used as the background image of the radar image. Then, the background and foreground in the current radar image can be separated based on the accumulated average image of the previous radar image to obtain the target radar image after background removal.

[0087] This technical solution accumulates and averages a preset number of previous radar images, making the accumulated average image of the previous radar images more accurate. This allows for the separation of the background and foreground in the current radar image based on the accumulated average image of the previous radar images, resulting in an accurate target radar image after background removal. This facilitates more accurate acquisition of the location information of the target area to be detected in the current radar image.

[0088] In a feasible embodiment, separating the background and foreground in the current radar image based on the accumulated average image to obtain the target radar image after background removal may include the following steps D1-D3:

[0089] Step D1: Perform image difference processing on the cumulative average image of the current radar image and the previous radar image to obtain the image after image difference processing.

[0090] Step D2: By binarizing the image after image difference processing, the background and foreground in the current radar image are separated to obtain the target radar image after background removal.

[0091] Image difference processing can be performed by subtracting the values ​​of two similar images. Binarization processing can be performed so that each pixel in the image has only two possible values ​​or grayscale levels, that is, the grayscale value of any pixel in the image is 0 or 255, representing black and white respectively.

[0092] Specifically, the cumulative average image of the previous radar images is obtained by averaging the images from a preset number of previous radar images. Next, the current radar image F is acquired, and the cumulative average image of the current radar image and the previous radar image is subjected to image difference processing to obtain the image F after image difference processing. Δ , can be represented as:

[0093]

[0094] Where F is the grayscale value of the current radar image.

[0095] Next, the image F after image difference processing is analyzed. Δ Perform binarization processing, that is, F Δ The pixel value of each pixel in the image is converted to 0 or 255, and the pixel with a value of 0 is the background and the pixel with a value of 255 is the foreground. Therefore, the background and foreground in the current radar image can be separated based on the image difference after binarization, so as to obtain the target radar image after background removal.

[0096] The image F after image difference processing can be calculated using the following formula. Δ Perform binarization:

[0097]

[0098] Among them, f ij 'This represents the grayscale value of the corresponding pixel after the radar image has been binarized.' T is the grayscale value of the corresponding pixel in the radar image, and T is the preset grayscale value. The preset grayscale value can be the threshold value at which the grayscale value of the corresponding pixel in the radar image is converted to 0 or 255. When the grayscale value of the corresponding pixel in the radar image is greater than or equal to the preset grayscale value, the grayscale value of the corresponding pixel is converted to 255, and vice versa.

[0099] This technical solution performs image difference processing by averaging the current radar image with the previous radar image to obtain the image after image difference processing. Then, it performs binarization processing on the image after image difference processing to separate the background and foreground in the current radar image, thereby obtaining the target radar image after background removal. This achieves accurate separation of the background and foreground of the current radar image, making the target radar image after background removal more accurate, and enabling more accurate acquisition of the location information of the target area to be detected.

[0100] S220. Determine the location information of the target area to be detected included in the foreground of the target radar image.

[0101] The target region to be detected can be the smallest bounding rectangle region of the target in the radar image.

[0102] Specifically, only by accurately obtaining the location information of the target region to be detected included in the foreground of the target radar image can the current contour bounding information be accurately determined.

[0103] In a feasible embodiment, determining the location information of the target region to be detected included in the foreground of the target radar image may include the following steps E1-E3:

[0104] Step E1: Perform morphological processing on the target radar image to obtain the processed radar image; the target region to be detected in the foreground of the target radar image is segmented into different sub-regions due to foreground-background separation.

[0105] Step E2: Perform Gaussian smoothing on the processed radar image, and perform edge detection on the Gaussian smoothed radar image to obtain the edge detection map of the target radar image.

[0106] Step E3: Extract the outer boundary inflection points of the edge detection map to obtain the location information of the outer boundary inflection points of the target region to be detected in the foreground of the target radar image, which is used as the location information of the target region to be detected.

[0107] Specifically, during the formation of the target radar image, the target area to be detected may be divided into different sub-regions. Therefore, in order to eliminate internal holes and / or gaps between different sub-regions corresponding to the target area, morphological dilation is performed on the target radar image to obtain a dilated radar image. Since the area becomes larger after dilation, morphological erosion is performed on the dilated radar image to obtain an eroded radar image, which is used as the processed radar image. This allows the area to be restored to its pre-dilation state, making the processed radar image more accurately represent the target area. Because radar detection generates some noise, Gaussian smoothing is applied to the processed radar image to further eliminate some small noise points caused by radar detection, thus enhancing the image accuracy. Then, edge detection is performed on the Gaussian smoothed processed radar image to obtain the edge detection map of the target radar image. Finally, outer boundary inflection points are extracted from the edge detection map to obtain the position information of the outer boundary inflection points of the target area to be detected in the foreground of the target radar image, which serves as the position information of the target area to be detected. The outer boundary inflection point extraction method can be any method in the prior art and is not limited in this embodiment of the invention. The final determined location information of the target area to be detected can be represented as follows:

[0108]

[0109] Among them, D i This represents the set of coordinates of the outer boundary inflection points of the i-th target region. Represents the row and column geometric pixel coordinates of the m-th inflection point of the outer boundary of the i-th target region.

[0110] This technical solution obtains a processed radar image by performing morphological processing on the target radar image, making the processed radar image more accurate in representing the target area to be detected. In addition, the processed radar image is Gaussian smoothed to further eliminate some small noise points caused by radar detection, which further enhances the accuracy of the image. Then, edge detection is performed on the Gaussian smoothed radar image to obtain the edge detection map of the target radar image. Finally, the outer boundary inflection points are extracted from the edge detection map to obtain the position information of the outer boundary inflection points of the target area to be detected in the foreground of the target radar image. This information serves as the position information of the target area to be detected, which is beneficial for accurately obtaining the current contour bounding information in subsequent steps.

[0111] S230. Determine the minimum bounding rectangle of the target area to be detected as the current outline bounding box information based on the location information of the target area to be detected.

[0112] Specifically, the location information of the target region to be detected in the radar image is obtained, that is, the location information of the minimum bounding rectangle of the target region to be detected. The minimum bounding rectangle of the target region is calculated using this location information to obtain the bounding box information of the target region, which is then used as the current contour bounding box information. The current contour bounding box information can be represented as:

[0113]

[0114] Among them, C i This is represented as the i-th smallest bounding rectangle. and These represent the top-left and bottom-right corner positions of the minimum bounding rectangle of the i-th target to be detected, respectively.

[0115] S240. Construct a current contour border information database based on the current contour border information of all target regions to be detected in the target radar image.

[0116] Specifically, the current contour border information of all target regions to be detected in the target radar image is obtained, and the current contour border information of all target regions to be detected is stored in a database to build an accurate current contour border information database. This facilitates the subsequent updating of the historical contour border information database through the current contour border information database, thereby ensuring the accuracy of foreign object detection.

[0117] S250. Foreign object detection is performed on the target to be detected based on the current outline and bounding box information and the historical outline and bounding box information database.

[0118] The technical solution of this invention acquires the current radar image of the radar detection area and separates the background and foreground of the current radar image to obtain a target radar image after background removal. To eliminate internal holes, gaps in neighboring regions, and radar-induced noise in the target radar image, and to accurately obtain the target region to be detected in the foreground, morphological processing and Gaussian smoothing are performed on the target radar image. Simultaneously, edge detection is performed on the Gaussian-smoothed radar image to obtain an edge detection map of the target radar image, ensuring accurate determination of the target region to be detected in the target radar image. Finally, the outer boundary inflection points of the edge detection map are extracted to obtain the position information of the outer boundary inflection points of the target region to be detected in the foreground of the target radar image. This serves as the position information of the target region, facilitating accurate acquisition of the current contour border information. Furthermore, the current contour border information of all target regions to be detected is stored in an information database to accurately obtain the current contour border information database. Then, based on the current contour border information and the historical contour border information database, foreign object detection is performed on the target to achieve rapid and accurate detection of the presence of foreign objects.

[0119] Example 3

[0120] Figure 4 This is a schematic diagram of a ground foreign object detection device based on radar charts according to Embodiment 3 of the present invention. Figure 4 As shown, the device includes:

[0121] The image determination module 310 is used to acquire the current radar image of the radar detection area.

[0122] The information database determination module 320 is used to obtain a current contour border information database based on the current radar image; wherein, the current contour border information database includes at least one current contour border information of a target to be detected.

[0123] The detection module 330 is used to perform foreign object detection on the target to be detected based on the current outline border information and the historical outline border information database; wherein the historical outline border information database is determined based on the historical radar image.

[0124] The current outline border information includes outline border position information; the historical outline border information database includes at least one historical outline border information, which includes at least outline border position information and outline border attribute information.

[0125] Optional, detection module, specifically used for:

[0126] The historical contour border information in the historical contour border information database is traversed, and the overlap between the historical contour border information and each current contour border information in the current contour border information database is determined sequentially according to the contour border position information.

[0127] In the current contour border information database, determine the target current contour border information that has the highest overlap with the historical contour border information;

[0128] The outline and border attribute information of the historical outline and border information is updated based on the degree of overlap.

[0129] Foreign object detection is performed on the target to be detected corresponding to the current outline border information of the target based on the updated outline border attribute information.

[0130] Optionally, the detection module includes an information update unit, specifically used for:

[0131] If the overlap is greater than or equal to a preset overlap threshold, then the number of consecutive static frames is updated and the number of consecutive frames without target association is set to zero.

[0132] If the overlap is less than a preset overlap threshold, then the count of the number of consecutive unassociated frames is updated, and the count of the number of consecutive still frames is set to zero.

[0133] The outline bounding box attribute information includes at least the number of consecutive frames without target association and the number of consecutive still frames.

[0134] Optionally, the detection module includes a first judgment unit, specifically used for:

[0135] If the updated number of consecutive still frames is greater than the preset threshold for the number of consecutive still frames, then the target to be detected corresponding to the target's current outline bounding box information is determined to be a foreign object, and the target's current outline bounding box information is deleted from the current outline bounding box information database.

[0136] Optionally, the detection module includes a second judgment unit, specifically used for:

[0137] If the updated number of consecutive frames without a target is greater than the preset threshold for the number of consecutive frames without a target, then the historical outline border information will be deleted from the historical outline border information database.

[0138] Optionally, the detection module includes an information addition unit, specifically used for:

[0139] Based on the remaining current outline border information in the current outline border information library, new historical outline border information is added to the historical outline border information library, and the outline border attribute information of the new historical outline border information is initialized.

[0140] Among them, the outline border position information is the minimum circumscribed rectangle bounding box information.

[0141] Optionally, the detection module includes an overlap determination unit, specifically used for:

[0142] The degree of overlap is determined according to the following formula:

[0143]

[0144] in, and The top-left and bottom-right corner positions of the rectangular bounding boxes representing historical outline border information are respectively provided. and The top-left and bottom-right corner positions of the rectangular bounding box that represent the current outline border information are respectively.

[0145] Optionally, the detection module further includes a first position information determination unit, specifically used for:

[0146] The location information of the foreign object is determined based on the outline position information in the current outline outline information of the target.

[0147] Among them, the outline border position information is the minimum circumscribed rectangle bounding box information.

[0148] Optionally, the location information determination unit is specifically used for:

[0149] The location information of the foreign object is determined according to the following formula:

[0150]

[0151] Where (x,y) represents the location information of the foreign object, and (r,c) represents the center location information of the minimum bounding rectangle. (r tl ,c tl ) and (r br ,c br ) represent the top-left and bottom-right corner positions of the minimum bounding rectangle information, respectively. Δ represents the correspondence between pixels in the current radar image and the actual region, and P and Q represent the row and column numbers of the current radar image, respectively.

[0152] Optional, the information database determination module is specifically used for:

[0153] The background and foreground in the current radar image are separated to obtain a target radar image after background removal;

[0154] Determine the location information of the target region to be detected included in the foreground of the target radar image;

[0155] The minimum bounding rectangle of the target region to be detected is determined as the current outline bounding box information based on the location information of the target region to be detected.

[0156] A current contour border information database is constructed based on the current contour border information of all target regions to be detected in the target radar image.

[0157] Optionally, the information database determination module includes an image acquisition unit, specifically used for:

[0158] A preset number of previous radar images were acquired in the radar detection area before the current radar image was acquired; the previous radar images include radar images acquired in the immediate vicinity before the current radar image was acquired, or radar images acquired by closing off the radar detection area.

[0159] The image is accumulated and averaged for a preset number of previous radar images to obtain the accumulated average image corresponding to the previous radar image.

[0160] The background and foreground in the current radar image are separated based on the cumulative average image to obtain the target radar image after background removal.

[0161] Optionally, the image acquisition unit includes an image processing unit, specifically used for:

[0162] The image difference is obtained by performing image difference processing on the cumulative average image of the current radar image and the previous radar image.

[0163] By binarizing the image after image difference processing, the background and foreground in the current radar image are separated to obtain the target radar image after background removal.

[0164] Optionally, the information database determination module includes a second location information determination unit, specifically used for:

[0165] The target radar image is subjected to morphological processing to obtain a processed radar image; the target region to be detected in the foreground of the target radar image is segmented into different sub-regions due to foreground-background separation.

[0166] The processed radar image is Gaussian smoothed, and edge detection is performed on the Gaussian smoothed radar image to obtain the edge detection map of the target radar image.

[0167] The outer boundary inflection points of the edge detection map are extracted to obtain the location information of the outer boundary inflection points of the target region to be detected in the foreground of the target radar image, which is used as the location information of the target region to be detected.

[0168] The ground foreign object detection device based on radar charts provided in this embodiment of the invention can execute the ground foreign object detection method based on radar charts provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0169] The acquisition, storage, use, and processing of data in this application comply with relevant national laws and regulations and do not violate public order and good morals.

[0170] Example 4

[0171] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0172] Figure 5 A schematic diagram of an electronic device is shown that can be used to implement the radar-based ground foreign object detection method according to embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0173] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0174] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0175] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as radar image-based ground foreign object detection methods.

[0176] In some embodiments, the radar chart-based ground foreign object detection method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the radar chart-based ground foreign object detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the radar chart-based ground foreign object detection method by any other suitable means (e.g., by means of firmware).

[0177] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0179] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0180] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0181] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0182] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0183] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0184] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A ground foreign object detection method based on radar images, characterized in that, include: Acquire the current radar image of the radar detection area; A current contour bounding box information database is obtained based on the current radar image; wherein, the current contour bounding box information database includes at least one current contour bounding box information of a target to be detected; Foreign object detection is performed on the target based on the current outline bounding box information and the historical outline bounding box information database; wherein, the historical outline bounding box information database is determined based on historical radar images; The current outline border information includes outline border position information; the historical outline border information database includes at least one historical outline border information, and the historical outline border information includes at least outline border position information and outline border attribute information. Accordingly, foreign object detection is performed on the target based on the current outline bounding box information and the historical outline bounding box information database, including: The historical contour border information in the historical contour border information database is traversed, and the overlap between the historical contour border information and each current contour border information in the current contour border information database is determined sequentially according to the contour border position information. In the current contour border information database, determine the target current contour border information that has the highest overlap with the historical contour border information; The outline and border attribute information of the historical outline and border information is updated based on the degree of overlap. Foreign object detection is performed on the target to be detected corresponding to the current contour border information of the target based on the updated contour border attribute information; The outline bounding box attribute information includes at least the number of consecutive target-free associated frames and the number of consecutive stationary frames; the number of consecutive target-free associated frames refers to the number of radar image frames in which the target to be detected has not appeared consecutively, corresponding to the current outline bounding box information of the target; the number of consecutive stationary frames is used to characterize the number of frames in which the position of the target to be detected stops changing during the motion, and is used to determine the length of time the target to be detected stops moving. Accordingly, the outline border attribute information of the historical outline border information is updated based on the overlap degree, including: If the overlap is greater than or equal to a preset overlap threshold, then the number of consecutive static frames is updated and the number of consecutive frames without target association is set to zero. If the overlap is less than a preset overlap threshold, then update the count for the number of consecutive unassociated frames and set the count for the number of consecutive static frames to zero. Specifically, foreign object detection is performed on the target to be detected corresponding to the current contour border information of the target based on the updated contour border attribute information, including: If the updated number of consecutive still frames is greater than the preset number of consecutive still frames threshold, then the target to be detected corresponding to the target's current outline bounding box information is determined to be a foreign object, and the target's current outline bounding box information is deleted from the current outline bounding box information database; the preset number of consecutive still frames threshold is the minimum number of consecutive still frames used to determine that the target has stopped. The method further includes, after performing foreign object detection on the target corresponding to the current contour border information of the target based on the updated contour border attribute information: If the updated number of consecutive target-free associated frames is greater than the preset threshold for the number of consecutive target-free associated frames, then the historical outline border information is deleted from the historical outline border information database; the preset threshold for the number of consecutive target-free associated frames is the minimum number of consecutive target-free associated frames used to determine that the target does not exist in the radar detection area. The method further includes, after performing foreign object detection on the target corresponding to the current contour border information of the target based on the updated contour border attribute information: Based on the remaining current outline border information in the current outline border information library, new historical outline border information is added to the historical outline border information library, and the outline border attribute information of the new historical outline border information is initialized.

2. The method according to claim 1, characterized in that, The outline border position information is the minimum circumscribed rectangle bounding box information; Accordingly, based on the outline position information, the overlap between the historical outline outline information and each current outline outline information in the current outline outline information database is determined sequentially, including: The degree of overlap is determined according to the following formula: ； in, and The top-left and bottom-right corner positions of the rectangular bounding boxes representing historical outline border information are respectively provided. and The top-left and bottom-right corner positions of the rectangular bounding box that represent the current outline border information are respectively.

3. The method according to claim 1, characterized in that, After determining that the target to be detected corresponding to the current contour bounding information of the target is a foreign object, the method further includes: The location information of the foreign object is determined based on the outline position information in the current outline outline information of the target.

4. The method according to claim 3, characterized in that, The outline border position information is the minimum bounding rectangle bounding box information; Accordingly, determining the position information of the foreign object based on the outline position information in the target's current outline outline information includes: The location information of the foreign object is determined according to the following formula: ； in, Indicates the location information of the foreign object. This indicates the center position information of the minimum bounding rectangle. , and These represent the top-left and bottom-right corner positions of the minimum bounding rectangle, respectively. ∆ represents the correspondence between pixels in the current radar image and the actual region. P and Q represent the number of rows and columns in the current radar image, respectively.

5. The method according to claim 1, characterized in that, The current contour bounding box information database is obtained based on the current radar image, including: The background and foreground in the current radar image are separated to obtain a target radar image after background removal; Determine the location information of the target region to be detected included in the foreground of the target radar image; Based on the location information of the target area to be detected, the minimum bounding rectangle of the target area to be detected is determined as the current outline border information; A current contour border information database is constructed based on the current contour border information of all target regions to be detected in the target radar image.

6. The method according to claim 5, characterized in that, Separating the background and foreground in the current radar image to obtain a target radar image after background removal includes: A preset number of previous radar images were acquired in the radar detection area before the current radar image was acquired; the previous radar images include radar images acquired in the immediate vicinity before the current radar image was acquired, or radar images acquired by closing off the radar detection area. The image is accumulated and averaged for a preset number of previous radar images to obtain the accumulated average image corresponding to the previous radar image. The background and foreground in the current radar image are separated based on the cumulative average image to obtain the target radar image after background removal.

7. The method according to claim 6, characterized in that, Based on the cumulative average image, the background and foreground in the current radar image are separated to obtain the target radar image after background removal, including: The image difference is obtained by performing image difference processing on the cumulative average image of the current radar image and the previous radar image. By binarizing the image after image difference processing, the background and foreground in the current radar image are separated to obtain the target radar image after background removal.

8. The method according to claim 5, characterized in that, Determining the location information of the target region to be detected included in the foreground of the target radar image includes: The target radar image is subjected to morphological processing to obtain a processed radar image; the target region to be detected in the foreground of the target radar image is segmented into different sub-regions due to foreground-background separation. The processed radar image is Gaussian smoothed, and edge detection is performed on the Gaussian smoothed radar image to obtain the edge detection map of the target radar image. The outer boundary inflection points of the edge detection map are extracted to obtain the location information of the outer boundary inflection points of the target region to be detected in the foreground of the target radar image, which is used as the location information of the target region to be detected.

9. A ground foreign object detection device based on radar images, characterized in that, include: The image determination module is used to acquire the current radar image of the radar detection area; The information database determination module is used to obtain a current contour bounding box information database based on the current radar image; wherein, the current contour bounding box information database includes at least one current contour bounding box information of a target to be detected; The detection module is used to perform foreign object detection on the target based on the current outline bounding box information and the historical outline bounding box information database; wherein, the historical outline bounding box information database is determined based on historical radar images; The current outline border information includes outline border position information; the historical outline border information database includes at least one historical outline border information, which includes at least outline border position information and outline border attribute information. Specifically, the detection module is used to: traverse the historical contour border information in the historical contour border information database; determine the overlap degree between the historical contour border information and each current contour border information in the current contour border information database according to the contour border position information; determine the target current contour border information with the highest overlap degree with the historical contour border information in the current contour border information database; update the contour border attribute information of the historical contour border information according to the overlap degree; and perform foreign object detection on the target to be detected corresponding to the target current contour border information according to the updated contour border attribute information. The outline bounding box attribute information includes at least the number of consecutive target-free associated frames and the number of consecutive stationary frames; the number of consecutive target-free associated frames refers to the number of radar image frames in which the target to be detected has not appeared consecutively, corresponding to the current outline bounding box information of the target; the number of consecutive stationary frames is used to characterize the number of frames in which the position of the target to be detected stops changing during the motion, and is used to determine the length of time the target to be detected stops moving. The detection module includes an information update unit, specifically used for: updating the count of consecutive static frames and setting the count of consecutive frames without target association to zero if the overlap is greater than or equal to a preset overlap threshold; and updating the count of consecutive frames without target association and setting the count of consecutive static frames to zero if the overlap is less than the preset overlap threshold. The detection module includes a first judgment unit, specifically used for: if the updated number of consecutive still frames is greater than a preset number of consecutive still frames threshold, then determining that the target to be detected corresponding to the target's current outline border information is a foreign object, and deleting the target's current outline border information from the current outline border information database; the preset number of consecutive still frames threshold is the minimum number of consecutive still frames used to determine that the target has stopped. The detection module includes a second judgment unit, specifically used to: if the updated number of consecutive target-free associated frames is greater than a preset threshold for the number of consecutive target-free associated frames, then delete the historical outline border information from the historical outline border information database; the preset threshold for the number of consecutive target-free associated frames is the minimum number of consecutive target-free associated frames used to determine that the target does not exist in the radar detection area. The detection module includes an information addition unit, specifically used to: add new historical contour border information to the historical contour border information library based on the remaining current contour border information in the current contour border information library, and initialize the contour border attribute information of the new historical contour border information.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the ground foreign object detection method based on radar charts as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the ground foreign object detection method based on radar charts as described in any one of claims 1-8.

Images