A FOD detection method, device and equipment based on laser scanning and a storage medium

Abstract

The application discloses a kind of FOD detection method, device, electronic equipment and storage medium based on laser scanning, method includes: division is multiple substructure light image area;According to the preset difference calculation method, the laser candidate point of substructure light image area is determined;Obtain laser candidate point image and determine laser line reference position based on laser candidate point image;According to the laser line reference position, respectively determine each column first laser point in structured light image, and according to each first laser point, determine the laser line of previous frame structured light image;According to the first laser point position of previous frame structured light image as center, determine the laser line of next frame structured light image;According to the preset triangular conversion relationship, the height information of target object is determined, and whether the target object is foreign matter is determined according to height information.The application reduces the possibility of line error caused by light, and improves the extraction speed of laser line.

Description

Technical Field

[0001] This invention relates to the fields of image processing and automated detection technology, specifically to a laser scanning-based FOD detection method, device, electronic device, and storage medium. Background Technology

[0002] In today's technological and economic development, the detection of FOD (Foreign Object Debris) on airport runways is receiving increasing attention. FOD, typically foreign objects left on the runway, pose a threat to the safe takeoff and landing of aircraft, such as metal parts, gravel, paper products, or plants and animals. Traditional methods of detecting airport FOD relying on manual inspections are inefficient, costly, highly susceptible to environmental influences, and prone to omissions. With the widespread application of machine vision in industry, industrial production is progressing towards informatization and intelligentization. Combining machine vision with image processing technology provides strong technical support for airport FOD detection.

[0003] However, existing technologies for detecting FOD are easily affected by external light, resulting in inaccurate detection results; and the detection speed is also low. Summary of the Invention

[0004] The purpose of this invention is to overcome the above-mentioned technical deficiencies and provide a FOD detection method, device, electronic device and storage medium based on laser scanning, so as to solve the technical problem that FOD detection is easily affected by external light intensity in the prior art.

[0005] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a FOD detection method based on laser scanning, comprising the following steps:

[0007] The multi-frame continuous structured light image of the airport runway surface is divided into multiple sub-structured light image regions;

[0008] Based on a preset differential calculation method, laser candidate points for each sub-structured light image region of each frame of structured light image are determined;

[0009] The laser candidate points are mapped onto an image of the same size to obtain a laser candidate point image, and the laser line reference position is determined based on the laser candidate point image.

[0010] Based on the laser line reference position, the positions of the laser candidate points closest to the laser line reference position in each column of the structured light image are determined and marked as the first laser points. Based on each of the first laser points, the laser lines of the structured light images in the first few frames are determined.

[0011] Based on the position of the first laser point in the previous frame of the structured light image, determine the extraction range of the second laser point in the next frame of the structured light image and extract the second laser point to determine the laser line in the next frame of the structured light image.

[0012] Based on a preset triangulation relationship, the distance between the laser line and the baseline in each frame of the structured light image is converted into the height information of the target object, and the target object is determined to be a foreign object based on the height information.

[0013] In some embodiments, determining the laser candidate points of each sub-structured light image region of each frame of structured light image according to a preset differential calculation method includes:

[0014] A preset binarization method is used to perform grayscale processing on the structured light image to obtain a grayscale structured light image within a set pixel grayscale range, and the grayscale structured light image is divided into multiple sub-structured light image regions.

[0015] According to the preset differential calculation method, the pixels of each of the substructured light image regions are differentially divided backward according to the preset differential module to obtain multiple differential pixels.

[0016] The difference curve is determined based on multiple difference pixels in each of the substructured light image regions;

[0017] Based on the range of laser points determined by the difference curve, laser candidate points are determined.

[0018] In some embodiments, determining the laser line reference position based on the laser candidate point image includes:

[0019] The pixel values ​​of each row in the laser candidate point image are accumulated to obtain multiple accumulated pixel values;

[0020] Iterate through the multiple accumulated pixel values ​​to determine the maximum accumulated pixel value;

[0021] The reference position of the laser line is determined based on the row number corresponding to the maximum accumulated pixel value.

[0022] In some embodiments, determining the laser line of the structured light image in the next frame based on the position of the first laser point in the previous frame of the structured light image includes:

[0023] Mark the position of the first laser point in each column of the structured light image in the previous frame;

[0024] Based on the position of the first laser point in each column of the previous frame structured light image, determine the laser point acquisition range of the corresponding column in the next frame structured light image;

[0025] Based on the laser point acquisition range, a preset differential method is used to acquire the second laser point in the corresponding column of the next frame of structured light image;

[0026] The range of laser lines in the structured light image of the next frame is determined based on the second laser point in each column.

[0027] In some embodiments, converting the distance between the laser line and the baseline in each frame of the structured light image into the height information of the target object according to a preset triangulation relationship includes:

[0028] Based on the angle between the laser installation direction and the horizontal plane, the ratio between the actual shooting distance of the camera and the pixels of the structured light image, and the degree of influence of the camera laser line calibration value on each column of the structured light image, the two-dimensional coordinates of the triangulation points of each column of the structured light image are determined.

[0029] Based on the two-dimensional coordinates, the height information of the target object is determined.

[0030] In some embodiments, before determining whether the target object is a foreign object based on the height information, the method further includes:

[0031] Based on the height information of each frame of the structured light image, multiple frames of the structured light images are accumulated row by row to obtain the three-dimensional solid point cloud of the target object.

[0032] In some embodiments, determining whether the target object is a foreign object based on the height information includes:

[0033] The height information is compared with a preset height threshold to obtain the comparison result;

[0034] Based on the comparison results, it is determined whether the target object is a foreign object.

[0035] Secondly, the present invention also provides a FOD detection device based on laser scanning, comprising:

[0036] The sub-region determination module is used to divide the first few frames of the multi-frame continuous airport runway surface structured light image into multiple sub-structured light image regions.

[0037] The laser candidate point determination module is used to determine the laser candidate points of each sub-structured light image region of each frame of structured light image according to a preset differential calculation method.

[0038] The laser line reference position determination module is used to map the laser candidate points onto an image of the same size, obtain a laser candidate point image, and determine the laser line reference position based on the laser candidate point image;

[0039] The first structured light image laser line determination module is used to determine the position of the laser candidate point closest to the laser line reference position in each column of the structured light image according to the laser line reference position and mark it as the first laser point, and determine the laser line of the structured light image in the first few frames according to each first laser point;

[0040] The second structured light image laser line determination module is used to determine the extraction range of the second laser point of the structured light image in the next frame and extract the second laser point based on the position of the first laser point of the previous frame of the structured light image, thereby determining the laser line of the structured light image in the next frame.

[0041] The FOD detection module based on laser scanning is used to convert the distance between the laser line and the baseline in each frame of the structured light image into the height information of the target object according to a preset triangulation relationship, and to determine whether the target object is a foreign object based on the height information.

[0042] Thirdly, the present invention also provides an electronic device, comprising: a processor and a memory;

[0043] The memory stores a computer-readable program that can be executed by the processor;

[0044] When the processor executes the computer-readable program, it implements the steps in the laser scanning-based FOD detection method as described above.

[0045] Fourthly, the present invention also provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in the laser scanning-based FOD detection method as described above.

[0046] Compared with existing technologies, the FOD detection method, device, electronic equipment, and storage medium based on laser scanning provided by this invention first divides the structured light image into multiple sub-structured light image regions and extracts the laser points that may exist within each sub-structured light image region. Although potential illumination interference may be extracted during the extraction process of each sub-structured light image region, the laser candidate point closest to the laser line reference position in the structured light image is found as the final determined first laser point, thereby reducing the possibility of line lifting errors caused by illumination. Subsequently, taking advantage of the continuous and non-abrupt characteristics of laser line changes, the position of the first laser point extracted from the previous frame of the structured light image is recorded, and this position is used in the laser point extraction calculation of the next frame of the structured light image. By comparing frame by frame, the calculation range is narrowed, thereby reducing unnecessary calculations and improving the overall line lifting speed. At the same time, by using an infrared laser to detect road FOD and acquiring target images through an infrared camera, FOD detection can be achieved in all weather conditions and under various illumination environments. Attached Figure Description

[0047] Figure 1 This is a flowchart of an embodiment of the FOD detection method based on laser scanning provided by the present invention;

[0048] Figure 2 This is a flowchart of an embodiment of step S102 in the FOD detection method based on laser scanning provided by the present invention;

[0049] Figure 3 This is a flowchart of an embodiment of step S103 in the FOD detection method based on laser scanning provided by the present invention;

[0050] Figure 4 This is a flowchart of an embodiment of step S105 in the FOD detection method based on laser scanning provided by the present invention;

[0051] Figure 5 This is a schematic diagram of an embodiment of the FOD detection device based on laser scanning provided by the present invention;

[0052] Figure 6 This is a schematic diagram of the operating environment of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0054] This invention includes an infrared laser, an infrared industrial camera, a high-performance computer, and a data acquisition system bracket. The camera is mounted vertically downwards, and the laser and camera are mounted at a β angle. The infrared laser illuminates the FOD surface, and the camera acquires the imaging results via a callback, which are then transmitted to a computer application via a serial cable. The application uses multi-threading to process the data in real time. The processing results are analyzed and compared, and the detection results are output on the terminal.

[0055] It should be noted that in this embodiment, an infrared laser is mounted on a vehicle and projected onto the airport runway surface at a certain angle, while the infrared camera and gyroscope module are activated. Subsequently, the equipment parameters are adjusted, including the angle between the laser and the camera, ensuring that the laser emitted by the laser is imaged at the center of the infrared camera. Simultaneously, the laser power is adjusted, and the camera is calibrated. Specifically, the method for adjusting the equipment parameters involves adjusting the relative positions of each laser so that the infrared laser beams emitted by each laser are arranged in a straight horizontal line on the road surface, increasing the detection range for road surface treatments. Then, the installation angle of each laser is adjusted so that the emitted laser line illuminates the surface of foreign objects at a certain angle, making it easier for the camera to detect them. Simultaneously, the wavelength of the laser emitted by the laser is adjusted based on the solar energy distribution map and spectral distribution curve, and according to environmental factors such as the intensity of external light, so that interference caused by external light minimizes its impact on the camera's acquisition of the laser line. Finally, the camera is calibrated to determine the position of the baseline. Simultaneously, the camera's placement height was adjusted to provide a wider field of view and detection range, ensuring that the laser emitted by the laser was positioned precisely in the center of the camera. Finally, laser images of the airport runway surface were acquired, and structured light images of the runway surface were captured continuously for multiple frames using an infrared camera, while simultaneously recording the vehicle's speed during the acquisition process.

[0056] Figure 1 This is a flowchart of the FOD detection method based on laser scanning provided in an embodiment of the present invention. Please refer to [link / reference]. Figure 1 The FOD detection method based on laser scanning includes the following steps:

[0057] S101. Divide multiple consecutive frames of structured light images of the airport runway surface into multiple sub-structured light image regions.

[0058] S102. Based on the preset differential calculation method, determine the laser candidate points of each sub-structured light image region of each frame of structured light image;

[0059] S103. Map the laser candidate points onto an image of the same size to obtain a laser candidate point image and determine the laser line reference position based on the laser candidate point image;

[0060] S104. Based on the laser line reference position, determine the position of the laser candidate point closest to the laser line reference position in each column of the structured light image and mark it as the first laser point. Based on each first laser point, determine the laser lines of the structured light image in the first few frames.

[0061] S105. Based on the position of the first laser point in the previous frame of the structured light image, determine the extraction range of the second laser point in the next frame of the structured light image and extract the second laser point to determine the laser line in the next frame of the structured light image.

[0062] S106. According to the preset triangulation relationship, the distance between the laser line and the baseline of each frame of the structured light image is converted into the height information of the target object, and the target object is determined to be a foreign object based on the height information.

[0063] In this embodiment, the structured light image is first divided into multiple sub-structured light image regions, and laser points that may exist within these regions are extracted. Although potential illumination interference may be detected during the extraction process, the laser candidate point closest to the laser line reference position in the structured light image is identified as the final determined first laser point, thus reducing the possibility of line-lifting errors caused by illumination. Subsequently, taking advantage of the continuous and non-abrupt nature of laser line changes, the position of the first laser point extracted from the previous frame of the structured light image is recorded. This position is then used in the laser point extraction calculation of the next frame of the structured light image. By comparing each frame, the calculation range is narrowed, thereby reducing unnecessary calculations and improving the overall line-lifting speed. Simultaneously, an infrared laser is used to detect road FOD, and an infrared camera is used to acquire target images, enabling FOD detection under various lighting conditions in all weather conditions.

[0064] In some embodiments, please refer to Figure 2 The step of determining the laser candidate points of each sub-structured light image region of each frame of structured light image according to a preset differential calculation method includes:

[0065] S201. Using a preset binarization method, the structured light image is processed to obtain a grayscale structured light image within a set pixel grayscale range, and the grayscale structured light image is divided into multiple sub-structured light image regions.

[0066] S202. According to the preset differential calculation method, the pixels of each of the substructured light image regions are subjected to backward differential calculation according to the preset differential module to obtain multiple differential pixels.

[0067] S203. Determine the difference curve based on the multiple difference pixels of each of the substructured light image regions;

[0068] S204. Based on the range of laser points determined by the difference curve, determine the candidate laser points.

[0069] In this embodiment, the entire structured light image of size h*w is binarized so that the pixel grayscale value is between 0 and 255. The image is divided into 5 regions by rows, each region being h*w / 5 in size, with the center lines of two regions located at the boundaries of the other three adjacent regions. Further, for each region's pixels, backward differencing is performed using a difference template of 10 pixels. For the current point P(i,m), calculation is performed according to the template (10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), and the calculation formula is: f(i,m) = 10*P(i,m) - ∑ i+10 P(i,m); For all points f(i,m) in each region of each column after difference calculation, form a one-dimensional array F in the direction of increasing i. m That is, the difference curve, and perform curvature transformation on the curve to find the maximum peak value f. max and the maximum trough peak value f min Given the row coordinates p and q corresponding to two points, and considering that the distance between the two points is less than 10 pixels, if the distance is within the width range of a typical laser line, then the center position of that laser point is taken as the index. m = (p+q) / 2, then compare the gray values ​​of the three pixels above and below the point, and finally determine the laser candidate point with the largest gray value in the region, and the existing laser candidate point is unique in the corresponding region.

[0070] In some embodiments, please refer to Figure 3 The step of determining the laser line reference position based on the laser candidate point image includes:

[0071] S301. The pixel values ​​of each row in the laser candidate point image are accumulated to obtain multiple accumulated pixel values;

[0072] S302. Traverse the multiple accumulated pixel values ​​to determine the maximum accumulated pixel value;

[0073] S303. Determine the reference position of the laser line according to the row number corresponding to the maximum accumulated pixel value.

[0074] In this embodiment, the pixel values ​​of each row in the structured light image are accumulated, and the result is stored in the corresponding row of a container of size 1*h. Then, the container is traversed to find the largest value, and the row number corresponding to it is the reference position of the laser line.

[0075] It should be noted that by obtaining the reference position of the laser line, a basis can be provided for finding the laser point position, thereby reducing the line lifting error caused by the influence of light.

[0076] In some embodiments, please refer to Figure 4 The step of determining the laser line of the structured light image in the next frame based on the position of the first laser point in the previous frame of the structured light image includes:

[0077] S401. Mark the position of the first laser point in each column of the structured light image of the previous frame;

[0078] S402. Based on the position of the first laser point in each column of the previous frame structured light image, determine the laser point acquisition range of the corresponding column in the next frame structured light image.

[0079] S403. Based on the laser point acquisition range, a preset differential method is used to acquire the second laser point in the corresponding column of the next frame structured light image;

[0080] S404. Determine the structured light image laser line for the next frame based on the second laser point in each column.

[0081] In this embodiment, based on the position of the first laser point obtained after extraction and processing of each column recorded in the previous frame of structured light image, the current frame of structured light image takes a range of 60 pixels wide above and below the corresponding laser point position in the previous frame of structured light image, and extracts the laser points according to a difference template of 10 pixels, so that the second laser point of each column is unique.

[0082] Furthermore, if the second laser point cannot be extracted according to the range described above, a new range is taken from the first row of the column to the upper boundary of the defined range for calculation and extraction of the second laser point; if the second laser point still cannot be successfully extracted, a new range is taken from the lower boundary of the newly defined range to the last row of the column for calculation and extraction of the second laser point; after performing the above steps column by column, the extracted laser lines are finally denoised to obtain the laser line extraction result of the structured light image.

[0083] It should be noted that after acquiring the laser lines of the previous and next frames, the acquired two-dimensional data of the runway is transmitted to the foreign object detection and processing platform using a 4G / 5G wireless transmission module; at the same time, a gyroscope is used to detect the motion state of the vehicle, and the opening and closing of the transmission channel is controlled according to the motion state of the vehicle.

[0084] In some embodiments, converting the distance between the laser line and the baseline in each frame of the structured light image into the height information of the target object according to a preset triangulation relationship includes:

[0085] Based on the angle between the laser installation direction and the horizontal plane, the ratio between the actual shooting distance of the camera and the pixels of the structured light image, and the degree of influence of the camera laser line calibration value on each column of the structured light image, the two-dimensional coordinates of the triangulation points of each column of the structured light image are determined.

[0086] Based on the two-dimensional coordinates, the height information of the target object is determined.

[0087] In this embodiment, the laser is installed at an angle θ to the horizontal of the ground, the actual distance captured by the camera is k relative to the pixel ratio in the image, and the calibration value H of the camera's laser line is set. base The two-dimensional coordinates of the conversion point in this column are obtained as (x0, y0); the height conversion formula for the conversion point (x0, y0) in a certain column in the current structured light image is Z = ((H base -y o )*k)*tanθ; Set the time of the previous frame of structured light image to T0, the time of the current frame image to T1, and the fixed speed of the moving detection vehicle to V0; The coordinates in the direction of motion are X=(T1-T0)*V0, and the coordinates of the current point are Y=x0; The current point (x0,y0) is successfully converted into a three-dimensional point (X,Y,Z), and the three-dimensional information of all points is managed through the PCL point cloud library, ultimately forming a three-dimensional point cloud entity of the detected foreign object.

[0088] In some embodiments, determining whether the target object is a foreign object based on the height information includes:

[0089] The height information is compared with a preset height threshold to obtain the comparison result;

[0090] Based on the comparison results, it is determined whether the target object is a foreign object.

[0091] In this embodiment, a height threshold H is set. t Filter the height data of each point in the point cloud space and compare them; for the current point A with coordinates (x0, y0, z0), if z0 is greater than H... t If z0 is less than Ht, then store x0 and y0 of A in the depth map; if z0 is less than Ht, then do not process it; display the points greater than z0 in the depth map, perform connected component detection on the entire region, and mark the region.

[0092] Based on the above-described laser scanning-based FOD detection method, this embodiment of the invention also provides a laser scanning-based FOD detection device 500. Please refer to [link to relevant documentation]. Figure 5The laser scanning-based FOD detection device 500 includes a sub-region determination module 510, a laser candidate point determination module 520, a laser line reference position determination module 530, a first structured light image laser line determination module 540, a second structured light image laser line determination module 550, and a laser scanning-based FOD detection module 560.

[0093] The sub-region determination module 510 is used to divide the first few frames of the multi-frame continuous airport runway surface structured light image into multiple sub-structured light image regions.

[0094] The laser candidate point determination module 520 is used to determine the laser candidate points of each sub-structured light image region of each frame of structured light image according to a preset differential calculation method.

[0095] The laser line reference position determination module 530 is used to map the laser candidate points onto an image of the same size, obtain a laser candidate point image, and determine the laser line reference position based on the laser candidate point image.

[0096] The first structured light image laser line determination module 540 is used to determine the position of the laser candidate point closest to the laser line reference position in each column of the structured light image according to the laser line reference position and mark it as the first laser point, and determine the laser line of the structured light image in the first few frames according to each first laser point.

[0097] The second structured light image laser line determination module 550 is used to determine the extraction range of the second laser point of the structured light image in the next frame and extract the second laser point based on the position of the first laser point of the previous frame structured light image, thereby determining the laser line of the structured light image in the next frame.

[0098] The FOD detection module 560 based on laser scanning is used to convert the distance between the laser line and the baseline of each frame of the structured light image into the height information of the target object according to a preset triangulation relationship, and to determine whether the target object is a foreign object based on the height information.

[0099] like Figure 6 As shown, based on the aforementioned laser scanning-based FOD detection method, this invention also provides an electronic device, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device includes a processor 610, a memory 620, and a display 630. Figure 6 Only some components of the electronic device are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0100] In some embodiments, memory 620 may be an internal storage unit of the electronic device, such as a hard disk or memory. In other embodiments, memory 620 may be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Furthermore, memory 620 may include both internal and external storage units. Memory 620 is used to store application software and various types of data installed on the electronic device, such as program code installed on the electronic device. Memory 620 may also be used to temporarily store data that has been output or will be output. In one embodiment, memory 620 stores a laser scanning-based FOD detection program 640, which can be executed by processor 610 to implement the laser scanning-based FOD detection methods of the various embodiments of this application.

[0101] In some embodiments, processor 610 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 620 or process data, such as performing a laser scanning-based FOD detection method.

[0102] In some embodiments, display 630 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 630 is used to display information from the laser-scanning FOD detection device and to display a visual user interface. Components 610-630 of the electronic device communicate with each other via a system bus.

[0103] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The storage medium can be a memory, magnetic disk, optical disk, etc.

[0104] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A FOD detection method based on laser scanning, characterized by, The method comprises the following steps: dividing a plurality of continuous airport runway surface structured light images into a plurality of sub-structured light image regions; determining laser candidate points of each of the sub-structured light image regions of each frame of structured light image according to a preset difference calculation method; mapping the laser candidate points to an image of the same size to obtain a laser candidate point image and determining a laser line reference position based on the laser candidate point image; determining a laser candidate point position closest to the laser line reference position in each column of the structured light image and marking the laser candidate point position as a first laser point according to the laser line reference position, and determining a laser line of the structured light image of the previous frame according to the first laser point; determining a second laser point extraction range of the structured light image of the next frame and performing second laser point extraction according to the first laser point position of the structured light image of the previous frame as the center, and determining a laser line of the structured light image of the next frame, comprising: marking the first laser point position of each column of the structured light image of the previous frame; determining a laser point collection range of the corresponding column of the structured light image of the next frame according to the marked first laser point position of each column of the structured light image of the previous frame; collecting the second laser point of the corresponding column of the structured light image of the next frame based on the laser point collection range; and determining a laser line range of the structured light image of the next frame according to the second laser point of each column. According to a preset triangular conversion relationship, converting a distance between the laser line of each frame of the structured light image and a reference line into height information of a target object, and determining whether the target object is a foreign object according to the height information.

2. The laser scanning-based FOD detection method of claim 1, wherein, The method comprises the following steps: applying a preset binary method to perform grayscale processing on the structured light image to obtain a grayscale structured light image located within a set pixel grayscale range, and dividing the grayscale structured light image into a plurality of sub-structured light image regions; performing backward difference on each of the sub-structured light image regions according to a preset difference module to obtain a plurality of difference pixels according to a preset difference calculation method; determining a difference curve according to the plurality of difference pixels of each of the sub-structured light image regions; determining a laser candidate point based on a laser point range determined by the difference curve.

3. The laser scanning based FOD detection method of claim 1, wherein, The method comprises the following steps: accumulating pixel values of each row of the laser candidate point image to obtain a plurality of accumulated pixel values; traversing the plurality of accumulated pixel values to determine a maximum accumulated pixel value; determining the laser line reference position according to a row number corresponding to the maximum accumulated pixel value.

4. The laser scanning based FOD detection method of claim 1, wherein, The method comprises the following steps: determining two-dimensional coordinates of a triangular conversion point of each column of the structured light image according to an included angle between a laser installation direction and a horizontal plane, a proportional relationship between an actual distance of a camera and pixels of the structured light image, and an influence degree of a camera laser line calibration value on each column of the structured light image. Determine height information of the target object based on the two-dimensional coordinates.

5. The laser scanning based FOD detection method of claim 4, wherein, Before determining whether the target object is a foreign object based on the height information, the method further comprises: Based on the height information of each frame of the structured light image, perform line-by-line accumulation on multiple frames of the structured light image to obtain a three-dimensional entity point cloud of the target object.

6. The laser scanning based FOD detection method of claim 5, wherein, The step of determining whether the target object is a foreign object based on the height information comprises: Compare the height information with a preset height threshold to obtain a comparison result; Determine whether the target object is a foreign object based on the comparison result.

7. A laser scanning based FOD detection apparatus, characterized by, The method comprises: A sub-region determination module is configured to divide multiple frames of continuous airport runway surface structured light images into multiple sub-structured light image regions; A laser candidate point determination module is configured to determine laser candidate points of each of the sub-structured light image regions of each frame of the structured light image based on a preset differential calculation method; A laser line reference position determination module is configured to map the laser candidate points to an image of the same size to obtain a laser candidate point image and determine a laser line reference position based on the laser candidate point image; A first structured light image laser line determination module is configured to determine positions of laser candidate points closest to the laser line reference position in each column of the structured light image and mark them as first laser points based on the laser line reference position, and determine laser lines of the structured light image of previous frames based on the first laser points; A second structured light image laser line determination module is configured to determine a second laser point extraction range of a next frame of the structured light image based on the first laser point positions of a previous frame of the structured light image and perform second laser point extraction to determine a laser line of the next frame of the structured light image, including: marking the first laser point positions of each column of the previous frame of the structured light image; determining a laser point collection range of a corresponding column of the next frame of the structured light image based on the marked first laser point positions of each column of the previous frame of the structured light image; collecting second laser points of the corresponding column of the next frame of the structured light image based on the laser point collection range using a preset differential method; and determining a laser line range of the next frame of the structured light image based on the second laser points of each column. A FOD detection module based on laser scanning is configured to convert distances between the laser lines of each frame of the structured light image and a reference line into height information of the target object based on a preset triangular conversion relationship, and determine whether the target object is a foreign object based on the height information.

8. An electronic device, comprising: The method comprises: A processor and a memory; The memory stores a computer readable program that can be executed by the processor; The processor executes the computer readable program to implement the steps of the FOD detection method based on laser scanning as claimed in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores one or more programs that can be executed by one or more processors to implement the steps of the FOD detection method based on laser scanning as claimed in any one of claims 1-6.

Images