Simple law enforcement system and device for low-altitude safety supervision and storage medium

Abstract

The invention discloses a simple law enforcement system and device for low-altitude safety supervision, and a storage medium, and relates to the technical field of low-altitude safety supervision, and the system comprises a data obtaining module, a data processing module, a data construction module, a constructed data obtaining module, a threshold obtaining module, and a judgment module. The construction data acquisition module is used for constructing a real-time reference difference value based on the divided regions; the threshold acquisition module is used for acquiring a reference difference threshold based on the infrared images of the first number of unmanned aerial vehicles; and the judgment module is used for judging whether the flyer is a target flyer based on the real-time reference difference value and a reference difference value threshold value, and judging whether the target flyer enters a no-fly zone based on the radar information of the flyer if the flyer is the target flyer. And the false alarm rate of intrusion of the unmanned aerial vehicle is relatively high.

Description

Technical Field

[0001] The present invention relates to the technical field of low-altitude safety supervision, and in particular to a simple law enforcement system, equipment and storage medium for low-altitude safety supervision. Background Art

[0002] With the deepening of low-altitude airspace reform and the explosive growth of the drone industry, urban low-altitude airspace is becoming a core carrier for innovative applications such as logistics distribution, emergency rescue, and smart inspections. At the same time, incidents of undeclared drones intruding into airport clear zones and airspace over sensitive facilities are becoming frequent, posing serious challenges to public safety, privacy protection, and airspace order.

[0003] Low-altitude safety supervision obtains dynamic data of low-altitude targets such as drones, processes and analyzes the data through the tower edge computing room, and then transmits the processing results to relevant law enforcement agencies or emergency response units in real time through a secure and reliable communication network. However, in the drone identification process, due to interference from kites, balloons, and birds that imitate the appearance of drones, the false alarm rate of drone intrusions is relatively high. For example, the patent application with publication number CN119179057A discloses a drone identification and tracking method combined with a low-altitude radar AI algorithm. This solution fails to establish feature data to distinguish drones and cannot effectively distinguish drones, resulting in a high false alarm rate for drone intrusions. The existing low-altitude safety supervision technology fails to establish feature data to distinguish drones, resulting in a high false alarm rate for drone intrusions. Summary of the Invention

[0004] The present invention aims to solve, at least to a certain extent, one of the technical problems in the prior art by constructing a real-time reference difference based on the divided areas; obtaining a reference difference threshold based on the infrared images of a first number of drones; and judging whether the flying object is a target flying object based on the real-time reference difference and the reference difference threshold. This solves the problem that the existing low-altitude safety supervision technology fails to establish characteristic data to distinguish drones, resulting in a high false alarm rate for drone intrusions.

[0005] To achieve the above-mentioned purpose, the present invention provides a simple law enforcement system for low-altitude safety supervision, comprising:

[0006] Data acquisition module, data processing module, data construction module, construction data acquisition module, threshold acquisition module and judgment module;

[0007] The data acquisition module is used to obtain an infrared image of the flying object in the white-hot mode, which is marked as the flying object infrared image; and obtain radar information of the flying object;

[0008] The data processing module is used to send the infrared image of the flying object and the radar information of the flying object to the tower edge computing power room, and the tower edge computing power room performs image processing on the infrared image of the flying object to obtain a binary image of the drone;

[0009] The data construction module is used to construct partition rectangles based on the UAV binary image;

[0010] The construction data acquisition module is used to construct a real-time reference difference based on the divided areas;

[0011] The threshold value acquisition module is used to obtain a reference difference threshold value based on the infrared images of the first number of drones;

[0012] The judgment module is used to judge whether the flying object is a target flying object based on the real-time reference difference and the reference difference threshold. If so, it is used to judge whether the target flying object enters a no-fly zone based on the radar information of the flying object.

[0013] Furthermore, the data processing module is configured with a grayscale strategy, and the grayscale strategy includes:

[0014] Determine whether the infrared image of the flying object is a single-channel grayscale image. If so, mark the infrared image of the flying object as a grayscale image of the flying object. If not, convert the infrared image of the flying object into a single-channel grayscale image and mark it as a grayscale image of the flying object.

[0015] Furthermore, the data processing module is configured with a histogram drawing strategy, and the histogram drawing strategy includes:

[0016] Divide the grayscale value from 0 to 255 into k equal intervals, marked as interval ranges;

[0017] The frequency of the grayscale value in each interval range in the grayscale image of the flying object is marked as interval frequency;

[0018] Draw a histogram with grayscale value as X-axis, interval frequency as Y-axis, and interval range as histogram interval, marked as grayscale histogram.

[0019] Furthermore, the data processing module is configured with a binarization strategy, which includes:

[0020] In the grayscale histogram, the interval range that is larger than the interval frequency on the left and right sides is marked as the peak range;

[0021] The median of the peak interval is marked as the peak median; the smallest peak median is obtained and marked as the first median; the largest peak median is obtained and marked as the second median;

[0022] Get the interval range that is greater than the first median and less than the second median, and mark it as the middle range;

[0023] Get the middle range with the smallest interval frequency and mark it as the threshold range;

[0024] Get the median value of the threshold range and mark it as the binarization threshold;

[0025] The grayscale values ​​in the grayscale image of the flying object that are greater than or equal to the binarization threshold are set to 0, and the grayscale values ​​that are less than the binarization threshold are set to 0 to obtain a binary image of the flying object.

[0026] Furthermore, the data construction module is configured with a flying object rectangle construction strategy, and the flying object rectangle construction strategy includes:

[0027] Establish a plane rectangular coordinate system, mark it as the reference coordinate system, and place the binary image of the flying object in the reference coordinate system;

[0028] Obtain the continuous area composed of pixels with a gray value of 0 in the binary image of the flying object, mark it as the continuous area, and obtain the continuous area with the largest number of pixels, mark it as the target area;

[0029] Get the coordinate point with the smallest horizontal coordinate in the target area, mark it as the first coordinate point, draw a straight line parallel to the Y axis through the first coordinate point, mark it as the first straight line; get the coordinate point with the largest horizontal coordinate in the target area, mark it as the second coordinate point, draw a straight line parallel to the Y axis through the second coordinate point, mark it as the second straight line; get the coordinate point with the smallest vertical coordinate in the target area, mark it as the third coordinate point, draw a straight line parallel to the X axis through the third coordinate point, mark it as the third straight line; get the coordinate point with the largest vertical coordinate in the target area, mark it as the fourth coordinate point, draw a straight line parallel to the X axis through the fourth coordinate point, mark it as the fourth straight line; get the rectangle enclosed by the first straight line, the second straight line, the third straight line and the fourth straight line, mark it as the flying object rectangle.

[0030] Furthermore, the data construction module is configured with a partitioning rectangle construction strategy, and the partitioning rectangle construction strategy includes:

[0031] Only keep the object rectangle in the reference coordinate system and place the grayscale image of the object in the same position as the binary image of the object;

[0032] Get one side of the flying object rectangle parallel to the X-axis, mark it as the X-axis parallel side, draw n coordinate points on the X-axis parallel side to divide the X-axis parallel side into n+1 equal intervals, marked as the first interval coordinate points; draw a straight line parallel to the Y-axis through the first interval coordinate point, mark it as the first parallel straight line; get one side of the flying object rectangle parallel to the Y-axis, mark it as the Y-axis parallel side, draw m coordinate points on the Y-axis parallel side to divide the Y-axis parallel side into m+1 equal intervals, marked as the second interval coordinate points; draw a straight line parallel to the X-axis through the second interval coordinate point, mark it as the second parallel straight line; mark the (n+1)×(m+1) rectangles formed by the first parallel straight line and the second parallel straight line as dividing rectangles.

[0033] Furthermore, the construction data acquisition module is configured with a construction data acquisition strategy, and the construction data acquisition strategy includes:

[0034] Get the mean of the grayscale values ​​within each divided rectangle, marked as the rectangle grayscale value; get the divided rectangle corresponding to the maximum grayscale value of the rectangle, marked as the target rectangle;

[0035] Get the center point of the target rectangle and mark it as the reference midpoint;

[0036] Get the minimum distance from the reference midpoint to the target rectangle, marked as reference distance;

[0037] Set a length smaller than the reference distance and mark it as the set length;

[0038] Draw a circle with the reference midpoint as the circle and the set length as the radius, marked as the first drawn circle; draw a circle with the reference midpoint as the circle and half of the set length as the radius, marked as the second drawn circle;

[0039] Obtain the mean of the grayscale values ​​within the second drawn circle in the grayscale image of the flying object, marked as the first grayscale mean; obtain the mean of the grayscale values ​​of the portion of the grayscale image of the flying object that does not intersect the first drawn circle and the second drawn circle, marked as the second grayscale mean;

[0040] The difference between the first grayscale mean and the second grayscale mean is calculated and marked as a real-time reference difference.

[0041] Furthermore, the threshold acquisition module is configured with a historical data processing strategy, and the historical data processing strategy includes:

[0042] Obtaining real-time reference differences of infrared images of a first number of UAVs and marking them as historical reference differences;

[0043] Obtain the range of historical reference difference values, divide the range of historical reference difference values ​​into h equally spaced ranges, and mark them as historical ranges; count the frequency of historical reference difference values ​​in each historical range, and mark them as historical frequencies.

[0044] Furthermore, the threshold acquisition module is configured with a threshold acquisition strategy, and the threshold acquisition strategy includes:

[0045] The abnormal frequency threshold is calculated as: tc=p×D / h; where tc is the abnormal frequency threshold, p is a constant between 0 and 1, and D is the first quantity;

[0046] Sort the historical ranges from small to large; obtain the historical frequency of the smallest historical range and mark it as the judgment frequency; delete the historical range corresponding to the judgment frequency that is less than the abnormal frequency threshold, obtain the minimum value of the historical range after deletion, and mark it as the reference difference threshold.

[0047] Furthermore, the judgment module is configured with a judgment strategy, and the judgment strategy includes:

[0048] Determine whether the real-time reference difference satisfies a reference difference threshold that is greater than or equal to the reference difference threshold. If so, identify the flying object as a target flying object; for radar information of the target flying object, where the radar information includes the position of the target flying object, determine whether the position of the target flying object is within a no-fly zone. If so, generate an abnormal signal, and transmit the abnormal signal and radar information to the regulatory unit in real time through the communication network.

[0049] Beneficial effects of the present invention: The present invention constructs a real-time reference difference based on the divided areas; obtains a reference difference threshold based on the infrared images of a first number of drones; and determines whether a flying object is a target flying object based on the real-time reference difference and the reference difference threshold. This has the advantage of effectively reducing interference with drone identification caused by kites, balloons, and birds that mimic the appearance of drones, thereby reducing the false alarm rate of drone intrusions.

[0050] The present invention constructs a real-time reference difference based on the divided areas. The advantage is that when the drone is working, the temperature of the motor position is higher than that of other parts, while the overall temperature difference between kites, balloons and birds that imitate the appearance of a drone and themselves is smaller. Therefore, by constructing a real-time reference difference based on the infrared image, the drone can be distinguished from other interferences, reducing the false alarm rate of drone intrusion. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a functional block diagram of the system of the present invention;

[0052] Figure 2 is a schematic diagram of a grayscale histogram of the present invention;

[0053] Figure 3 is a schematic diagram of a rectangular flying object of the present invention;

[0054] Figure 4 A schematic diagram of a rectangle divided according to the present invention;

[0055] Figure 5 is a schematic diagram of a first drawn circle and a second drawn circle of the present invention;

[0056] Figure 6 A flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] Example 1, please refer to Figure 1 As shown, a simple law enforcement system for low-altitude safety supervision includes: a data acquisition module, a data processing module, a data construction module, a construction data acquisition module, a threshold acquisition module and a judgment module;

[0059] The data acquisition module is used to obtain infrared images of flying objects in white-hot mode, marked as flying object infrared images; obtain radar information of flying objects; infrared images in white-hot mode facilitate subsequent image processing;

[0060] The data processing module is used to send the infrared image of the flying object and the radar information of the flying object to the tower edge computing power room, and the tower edge computing power room performs image processing on the infrared image of the flying object to obtain the binary image of the drone; combined with edge computing to reduce computing pressure;

[0061] The data processing module is configured with a grayscale strategy, which includes:

[0062] Determine whether the infrared image of the flying object is a single-channel grayscale image. If so, mark the infrared image of the flying object as a grayscale image of the flying object. If not, convert the infrared image of the flying object into a single-channel grayscale image and mark it as a grayscale image of the flying object. The infrared image in the incandescent mode may be a single-channel grayscale image, which is usually the required single-channel grayscale image, or it may be an RGB camouflaged grayscale image. What is needed here is a single-channel grayscale image, so the RGB camouflaged grayscale is converted into a single-channel grayscale image.

[0063] The data processing module is configured with a histogram drawing strategy, which includes:

[0064] Divide the grayscale value of 0-255 into k equally spaced ranges, marked as interval ranges. The grayscale image of the flying object includes the flying object and the sky background, so the setting of k is to distinguish the grayscale value distribution of the flying object and the sky background. Therefore, the k value cannot be too small, for example, k is 8.

[0065] The frequency of the grayscale value in each interval range in the grayscale image of the flying object is marked as interval frequency;

[0066] Draw a histogram with grayscale value as X-axis, interval frequency as Y-axis, and interval range as histogram interval, marked as grayscale histogram;

[0067] In practical applications, please refer to Figure 2 As shown, the grayscale histogram is drawn.

[0068] The data processing module is configured with a binarization strategy, which includes:

[0069] In the grayscale histogram, the interval range that is larger than the interval frequency on the left and right sides is marked as the peak range;

[0070] The median of the peak interval is marked as the peak median; the smallest peak median is obtained and marked as the first median; the largest peak median is obtained and marked as the second median;

[0071] Get the interval range that is greater than the first median and less than the second median, and mark it as the middle range;

[0072] Get the middle range with the smallest interval frequency and mark it as the threshold range;

[0073] Get the median value of the threshold range and mark it as the binarization threshold;

[0074] In the grayscale image of the flying object, the grayscale values ​​greater than or equal to the binarization threshold are set to 0, and the grayscale values ​​less than the binarization threshold are set to 0 to obtain a binary image of the flying object; because the temperature of the drone is generally higher than the ambient temperature;

[0075] In practical applications, please refer to Figure 2 As shown, the first median is 47, the second median is 174, the interval range greater than 47 and less than 174 is obtained, marked as the middle range, the threshold range is 95 to 127, the median of the threshold range is 111, and the binarization threshold is 111. The grayscale values ​​greater than or equal to 111 in the grayscale image of the flying object are set to 0, and the grayscale values ​​less than 111 are set to 0 to obtain a binary image of the flying object.

[0076] The data construction module is used to construct partition rectangles based on the UAV binary image;

[0077] The data construction module is configured with a flying object rectangle construction strategy, which includes:

[0078] Establish a plane rectangular coordinate system, mark it as the reference coordinate system, and place the binary image of the flying object in the reference coordinate system;

[0079] Obtain the continuous area composed of pixels with a gray value of 0 in the binary image of the flying object, mark it as the continuous area, and obtain the continuous area with the largest number of pixels, mark it as the target area;

[0080] Obtain a coordinate point with the smallest horizontal coordinate in the target area, mark it as the first coordinate point, draw a straight line parallel to the Y axis through the first coordinate point, mark it as the first straight line; obtain a coordinate point with the largest horizontal coordinate in the target area, mark it as the second coordinate point, draw a straight line parallel to the Y axis through the second coordinate point, mark it as the second straight line; obtain a coordinate point with the smallest vertical coordinate in the target area, mark it as the third coordinate point, draw a straight line parallel to the X axis through the third coordinate point, mark it as the third straight line; obtain a coordinate point with the largest vertical coordinate in the target area, mark it as the fourth coordinate point, draw a straight line parallel to the X axis through the fourth coordinate point, mark it as the fourth straight line; obtain a rectangle surrounded by the first straight line, the second straight line, the third straight line, and the fourth straight line, mark it as the flying object rectangle; the flying object rectangle is the area of ​​the flying object to be analyzed in the flying object binary image, which facilitates the subsequent processing of the area of ​​the flying object in the flying object grayscale image;

[0081] In practical applications, please refer to Figure 3 As shown, the flying object rectangle is drawn.

[0082] The data construction module is configured with a partitioning rectangle construction strategy, which includes:

[0083] Keep only the object rectangle in the reference coordinate system, and place the object grayscale image in the same position as the object binary image. The object binary image and the object grayscale image have the same size and can be placed in the same position. Then, the object rectangle can be used to obtain the position of the object in the object grayscale image.

[0084] Obtain one side of the object's rectangle parallel to the X-axis, marking it as the X-axis parallel side. Draw n coordinate points on the X-axis parallel side to divide the X-axis parallel side into n+1 equally spaced points, marking them as the first interval coordinate points. Draw a line parallel to the Y-axis through the first interval coordinate point, marking it as the first parallel line. Obtain one side of the object's rectangle parallel to the Y-axis, marking it as the Y-axis parallel side. Draw m coordinate points on the Y-axis parallel side to divide the Y-axis parallel side into m+1 equally spaced points, marking them as the second interval coordinate points. Draw a line parallel to the X-axis through the second interval coordinate point, marking it as the second parallel line. Mark the (n+1)×(m+1) rectangles formed by the first and second parallel lines as partition rectangles. To obtain the center position of the object, divide the object rectangle into multiple rectangles. The object is a region, and multiple partition rectangles are divided to facilitate the determination of the proportion of the partition rectangle position where the object's center position is located. If a single coordinate point is processed, there may be interference points, which may cause errors in obtaining the object's center.

[0085] In practical applications, please refer to Figure 4 As shown, n and m are set based on the length of the side parallel to the X axis and the side parallel to the Y axis, for example Figure 4As shown, n is set to 5, m is set to 3, and a coordinate point 5 is drawn on the side parallel to the X-axis to divide the side parallel to the X-axis into 6 equal intervals, marked as the first interval coordinate point; a straight line parallel to the Y-axis is drawn through the first interval coordinate point, marked as the first parallel straight line; one side of the flying object rectangle parallel to the Y-axis is obtained, marked as the Y-axis parallel side, and a coordinate point 3 is drawn on the side parallel to the Y-axis to divide the side parallel to the Y-axis into 4 equal intervals, marked as the second interval coordinate point; a straight line parallel to the X-axis is drawn through the second interval coordinate point, marked as the second parallel straight line; the 24 rectangles formed by the first parallel straight line and the second parallel straight line are marked as dividing rectangles.

[0086] Constructing a data acquisition module for constructing real-time reference difference values ​​based on the divided areas;

[0087] The build data acquisition module is configured with a build data acquisition strategy, which includes:

[0088] Get the mean of the grayscale values ​​within each divided rectangle, marked as the rectangle grayscale value; get the divided rectangle corresponding to the maximum value of the rectangle grayscale value, marked as the target rectangle; the larger the rectangle grayscale value, the larger the proportion of flying objects in the target rectangle;

[0089] Get the point with the highest grayscale value in the target rectangle and mark it as the reference midpoint; if the flying object has a motor, the motor position is higher than the drone material temperature;

[0090] Get the minimum distance from the reference midpoint to the target rectangle, marked as the reference distance. To prevent the first drawn circle from being drawn within the aircraft, the reference distance is generally set to be smaller than the reference distance. At the same time, the first drawn circle must be larger than the motor range.

[0091] Set a length smaller than the reference distance and mark it as the set length;

[0092] Draw a circle with the reference midpoint as the circle and the set length as the radius, marked as the first drawn circle; draw a circle with the reference midpoint as the circle and half of the set length as the radius, marked as the second drawn circle;

[0093] Obtain the mean of the grayscale values ​​within the second drawn circle in the grayscale image of the flying object, marked as the first grayscale mean; obtain the mean of the grayscale values ​​of the portion of the grayscale image of the flying object that does not intersect the first drawn circle and the second drawn circle, marked as the second grayscale mean;

[0094] Calculate the difference between the first grayscale mean and the second grayscale mean, and mark it as a real-time reference difference; if there is a motor, when the motor is working, the motor temperature is higher than the ambient temperature, and there is a difference;

[0095] In practical applications, please refer to Figure 5, the set length is 100mm, and the first drawn circle and the second drawn circle are drawn. If the first grayscale mean is 221 and the second grayscale mean is 190, the real-time reference difference is 31.

[0096] The threshold value acquisition module is used to obtain a reference difference threshold value based on the infrared images of the first number of drones;

[0097] The threshold acquisition module is configured with a historical data processing strategy, which includes:

[0098] Obtaining real-time reference differences of infrared images of a first number of UAVs and marking them as historical reference differences;

[0099] Obtain the range of historical reference difference values, divide the range of historical reference difference values ​​into h equally spaced ranges, and mark them as historical ranges; count the frequency of historical reference difference values ​​in each historical range, and mark them as historical frequencies; the first number is to obtain the distribution of historical reference difference values, so the more the better, for example, the first number is 200; h is set to obtain the distribution of historical reference difference values, for example, h is 10;

[0100] In practical applications, the range of the reference difference threshold is 12 to 42, and the range of historical reference difference values ​​is evenly divided into 10 equally spaced ranges, namely 12 to 15, 15 to 18, ..., 39 to 42;

[0101] The threshold acquisition module is configured with a threshold acquisition strategy, which includes:

[0102] The abnormal frequency threshold is calculated as: tc = p × D / h; where tc is the abnormal frequency threshold, p is a constant between 0 and 1, and D is the first quantity; to filter out larger or smaller data, the abnormal frequency threshold is smaller, and the ratio of p should be less than 0.5, for example 0.1;

[0103] Sort the historical ranges from small to large; obtain the historical frequency of the smallest historical range and mark it as the judgment frequency; delete the historical range corresponding to the judgment frequency that is less than the abnormal frequency threshold to improve the range accuracy;

[0104] In actual applications, the calculated abnormal frequency threshold is: tc = 0.1 × 200 / 10 = 2; the historical frequency of 12 to 15 is 1, and the historical range of 2 to 15 corresponding to the judgment frequency less than 2 is deleted. The minimum value of the historical range after deletion is 15, so the reference difference threshold is 15.

[0105] The judgment module is used to judge whether the flying object is a target flying object based on the real-time reference difference and the reference difference threshold, and if so, to judge whether the target flying object enters a no-fly zone based on the radar information of the flying object;

[0106] The judgment module is configured with a judgment strategy, which includes:

[0107] Determine whether the real-time reference difference satisfies a reference difference threshold. If so, identify the flying object as a target flying object. Determine whether the target flying object's radar information, including its location, is within a no-fly zone. If so, generate an abnormal signal, and transmit the abnormal signal and radar information to the supervisory unit in real time via a communication network. Determine whether the real-time reference difference satisfies a reference difference threshold. It can be preliminarily determined that the flying object has a motor. When the motor is working, the motor temperature is higher than the ambient temperature, and there is a difference. Kites, balloons, and birds that imitate the appearance of drones have a smaller overall temperature difference compared to their own temperature.

[0108] In actual applications, if the real-time reference difference 31 is greater than the reference difference threshold 15, the flying object is identified as a target flying object, and it is determined whether the position of the target flying object is within the no-fly zone. If so, the abnormal signal and radar information are transmitted to the regulatory unit in real time through the communication network.

[0109] Example 2, please refer to Figure 6 As shown, a simple law enforcement method for low-altitude safety supervision includes the following steps:

[0110] Step S1, obtaining an infrared image of the flying object in white-hot mode, marked as the flying object infrared image; obtaining radar information of the flying object;

[0111] Step S2: Send the infrared image of the flying object and the radar information of the flying object to the tower edge computing power room, and use the tower edge computing power room to process the infrared image of the flying object to obtain a binary image of the drone. Step S2 includes the following sub-steps:

[0112] Step S201: determine whether the infrared image of the flying object is a single-channel grayscale image. If so, mark the infrared image of the flying object as a grayscale image of the flying object. If not, convert the infrared image of the flying object into a single-channel grayscale image and mark it as a grayscale image of the flying object.

[0113] Step S202, divide the grayscale value of 0-255 into k equal interval ranges, marked as interval ranges;

[0114] Step S203, the frequency of the grayscale value in each interval range in the grayscale image of the flying object is marked as interval frequency;

[0115] Step S204, draw a histogram with the grayscale value as the X-axis, the interval frequency as the Y-axis, and the interval range as the histogram interval, and mark it as grayscale histogram;

[0116] Step S205: in the grayscale histogram, mark the interval range that is larger than the interval frequency of the adjacent intervals on the left and right sides as the peak range;

[0117] Step S206: Mark the median of the peak interval as the peak median; obtain the minimum peak median, mark it as the first median, and obtain the maximum peak median, mark it as the second median;

[0118] Step S207, obtaining an interval range that is greater than the first median value and less than the second median value, and marking it as a middle range;

[0119] Step S208, obtaining the middle range with the minimum interval frequency, marking it as the threshold range;

[0120] Step S209, obtaining the median value of the threshold range and marking it as the binarization threshold;

[0121] Step S210 , setting the grayscale values ​​in the flying object grayscale image that are greater than or equal to the binarization threshold to 0, and setting the grayscale values ​​that are less than the binarization threshold to 0, to obtain a binary image of the flying object.

[0122] Step S3, constructing a partitioning rectangle based on the binary image of the drone; Step S3 includes the following sub-steps:

[0123] Step S301: Establish a plane rectangular coordinate system, mark it as a reference coordinate system, and place the binary image of the flying object in the reference coordinate system;

[0124] Step S302: Obtain a continuous region consisting of pixels with a grayscale value of 0 in the binary image of the flying object, mark it as a continuous region, and obtain a continuous region with the largest number of pixels, mark it as a target region;

[0125] Step S303: Obtain a coordinate point with the smallest horizontal coordinate in the target area, mark it as the first coordinate point, draw a straight line parallel to the Y axis through the first coordinate point, mark it as the first straight line; obtain a coordinate point with the largest horizontal coordinate in the target area, mark it as the second coordinate point, draw a straight line parallel to the Y axis through the second coordinate point, mark it as the second straight line; obtain a coordinate point with the smallest vertical coordinate in the target area, mark it as the third coordinate point, draw a straight line parallel to the X axis through the third coordinate point, mark it as the third straight line; obtain a coordinate point with the largest vertical coordinate in the target area, mark it as the fourth coordinate point, draw a straight line parallel to the X axis through the fourth coordinate point, mark it as the fourth straight line; obtain a rectangle enclosed by the first straight line, the second straight line, the third straight line, and the fourth straight line, mark it as the flying object rectangle;

[0126] Step S304: retain only the flying object rectangle in the reference coordinate system and place the flying object grayscale image at the same position as the flying object binary image;

[0127] Step S305: obtain a side of the flying object rectangle parallel to the X-axis, mark it as the X-axis parallel side, draw n coordinate points on the X-axis parallel side to divide the X-axis parallel side into n+1 equally spaced points, mark them as first interval coordinate points; draw a straight line parallel to the Y-axis through the first interval coordinate point, mark it as the first parallel straight line; obtain a side of the flying object rectangle parallel to the Y-axis, mark it as the Y-axis parallel side, draw m coordinate points on the Y-axis parallel side to divide the Y-axis parallel side into m+1 equally spaced points, mark them as second interval coordinate points; draw a straight line parallel to the X-axis through the second interval coordinate point, mark it as the second parallel straight line; mark the (n+1)×(m+1) rectangles formed by the first parallel straight line and the second parallel straight line as dividing rectangles.

[0128] Step S4, constructing a real-time reference difference based on the divided areas; Step S4 includes the following sub-steps:

[0129] Step S401, obtaining the mean value of the grayscale value in each divided rectangle, marking it as the rectangle grayscale value; obtaining the divided rectangle corresponding to the maximum value of the rectangle grayscale value, marking it as the target rectangle;

[0130] Step S402: Obtain the center point of the target rectangle and mark it as the reference midpoint;

[0131] Step S403, obtaining the minimum distance from the reference midpoint to the target rectangle, and marking it as the reference distance;

[0132] Step S404, setting a length smaller than the reference distance, marked as the set length;

[0133] Step S405: Draw a circle with the reference midpoint as the circle and the set length as the radius, marked as the first drawn circle; draw a circle with the reference midpoint as the circle and half of the set length as the radius, marked as the second drawn circle;

[0134] Step S406: Obtain the mean of the grayscale values ​​within the second drawn circle in the grayscale image of the flying object, and mark it as the first grayscale mean; obtain the mean of the grayscale values ​​of the portion of the grayscale image of the flying object that does not intersect with the second drawn circle, and mark it as the second grayscale mean;

[0135] Step S407 : Calculate the difference between the first grayscale mean and the second grayscale mean, and mark it as a real-time reference difference.

[0136] Step S5, obtaining a reference difference threshold based on the infrared images of the first number of drones; Step S5 includes the following sub-steps:

[0137] Step S501: obtaining real-time reference differences of infrared images of a first number of drones and marking them as historical reference differences;

[0138] Step S502: Obtain the range of historical reference difference values, divide the range of historical reference difference values ​​into h equally spaced ranges, and mark them as historical ranges; count the frequency of historical reference difference values ​​in each historical range, and mark them as historical frequencies;

[0139] Step S503 , calculating the abnormal frequency threshold as: tc=p×D / h; wherein tc is the abnormal frequency threshold, p is a constant between 0 and 1, and D is the first quantity;

[0140] Step S504, sort the historical ranges from small to large; obtain the historical frequency of the smallest historical range, mark it as the judgment frequency; delete the historical range corresponding to the judgment frequency less than the abnormal frequency threshold, obtain the minimum value of the historical range after deletion, and mark it as the reference difference threshold.

[0141] Step S6, determining whether the flying object is a target flying object based on the real-time reference difference and the reference difference threshold; if so, determining whether the target flying object enters a no-fly zone based on the radar information of the flying object; Step S6 includes the following sub-steps:

[0142] Step S601, determine whether the real-time reference difference satisfies a reference difference threshold that is greater than or equal to the reference difference threshold. If so, identify the flying object as a target flying object; based on the radar information of the target flying object, where the radar information includes the position of the target flying object, determine whether the position of the target flying object is within the no-fly zone. If so, generate an abnormal signal, and transmit the abnormal signal and radar information to the supervisory unit in real time through the communication network.

[0143] In Example 3, the present application further provides an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a simplified law enforcement method for low-altitude safety supervision are executed to implement the following functions: obtaining an infrared image of an aircraft in white-hot mode and marking it as an infrared image of the aircraft; obtaining radar information of the aircraft; sending the infrared image of the aircraft and the radar information of the aircraft to an edge computing power room at the tower edge computing power room, performing image processing on the infrared image of the aircraft to obtain a binary image of the drone; constructing partition rectangles based on the binary image of the drone; constructing real-time reference differences based on the partitioned areas; obtaining a reference difference threshold based on the infrared images of a first number of drones; determining whether the aircraft is a target aircraft based on the real-time reference difference and the reference difference threshold, and if so, determining whether the target aircraft has entered a no-fly zone based on the radar information of the aircraft.

[0144] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0145] Example 4. The present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a simple law enforcement method for low-altitude safety supervision provided by the above methods, the method including: obtaining an infrared image of an aircraft in white-hot mode, marking it as an infrared image of the aircraft; obtaining radar information of the aircraft; sending the infrared image of the aircraft and the radar information of the aircraft to the tower edge computing power room, and performing image processing on the infrared image of the aircraft through the tower edge computing power room to obtain a binary image of the drone; constructing a partitioning rectangle based on the binary image of the drone; constructing a real-time reference difference based on the partitioned area; obtaining a reference difference threshold based on the infrared images of a first number of drones; judging whether the aircraft is a target aircraft based on the real-time reference difference and the reference difference threshold, and if so, judging whether the target aircraft enters a no-fly zone based on the radar information of the aircraft.

[0146] Example 5. The present application also provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by the processor, the steps in the above-mentioned simple law enforcement method for low-altitude safety supervision are executed to achieve the following functions: obtain an infrared image of the flying object in the white-hot mode, marked as the infrared image of the flying object; obtain the radar information of the flying object; send the infrared image of the flying object and the radar information of the flying object to the tower edge computing power room, and perform image processing on the infrared image of the flying object through the tower edge computing power room to obtain a binary image of the drone; construct a partitioning rectangle based on the binary image of the drone; construct a real-time reference difference based on the partitioned area; obtain a reference difference threshold based on the infrared image of the first number of drones; judge whether the flying object is the target flying object based on the real-time reference difference and the reference difference threshold, and if so, judge whether the target flying object enters the no-fly zone based on the radar information of the flying object.

[0147] Through the description of the above embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the essence of the above technical solutions or the portion that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (such as a personal computer, server, or network device) to execute the methods described in various embodiments or certain portions of the embodiments.

[0148] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A simple law enforcement system for low-altitude safety supervision, characterized by: include: Data acquisition module, data processing module, data construction module, construction data acquisition module, threshold acquisition module and judgment module; The data acquisition module is used to obtain an infrared image of the flying object in the white-hot mode, which is marked as the flying object infrared image; and obtain radar information of the flying object; The data processing module is used to send the infrared image of the flying object and the radar information of the flying object to the tower edge computing power room, and the tower edge computing power room performs image processing on the infrared image of the flying object to obtain a binary image of the drone; The data construction module is used to construct partition rectangles based on the UAV binary image; The construction data acquisition module is used to construct a real-time reference difference based on the divided areas; The threshold value acquisition module is used to obtain a reference difference threshold value based on the infrared images of the first number of drones; The judgment module is used to judge whether the flying object is a target flying object based on the real-time reference difference and the reference difference threshold. If so, it is used to judge whether the target flying object enters a no-fly zone based on the radar information of the flying object.

2. A simplified law enforcement system for low-altitude safety supervision according to claim 1, characterized in that: The data processing module is configured with a grayscale strategy, which includes: Determine whether the infrared image of the flying object is a single-channel grayscale image. If so, mark the infrared image of the flying object as a grayscale image of the flying object. If not, convert the infrared image of the flying object into a single-channel grayscale image and mark it as a grayscale image of the flying object.

3. A simplified law enforcement system for low-altitude safety supervision according to claim 2, characterized in that: The data processing module is configured with a histogram drawing strategy, which includes: Divide the grayscale value from 0 to 255 into k equal intervals, marked as interval ranges; The frequency of the grayscale value in each interval range in the grayscale image of the flying object is marked as interval frequency; Draw a histogram with grayscale value as X-axis, interval frequency as Y-axis, and interval range as histogram interval, marked as grayscale histogram.

4. A simplified law enforcement system for low-altitude safety supervision according to claim 3, characterized in that: The data processing module is configured with a binarization strategy, which includes: In the grayscale histogram, the interval range that is larger than the interval frequency on the left and right sides is marked as the peak range; The median of the peak interval is marked as the peak median; the smallest peak median is obtained and marked as the first median; the largest peak median is obtained and marked as the second median; Get the interval range that is greater than the first median and less than the second median, and mark it as the middle range; Get the middle range with the smallest interval frequency and mark it as the threshold range; Get the median value of the threshold range and mark it as the binarization threshold; The grayscale values ​​in the grayscale image of the flying object that are greater than or equal to the binarization threshold are set to 0, and the grayscale values ​​that are less than the binarization threshold are set to 0 to obtain a binary image of the flying object.

5. A simplified law enforcement system for low-altitude safety supervision according to claim 4, characterized in that: The data construction module is configured with a flying object rectangle construction strategy, and the flying object rectangle construction strategy includes: Establish a plane rectangular coordinate system, mark it as the reference coordinate system, and place the binary image of the flying object in the reference coordinate system; Obtain the continuous area composed of pixels with a gray value of 0 in the binary image of the flying object, mark it as the continuous area, and obtain the continuous area with the largest number of pixels, mark it as the target area; Get the coordinate point with the smallest horizontal coordinate in the target area, mark it as the first coordinate point, draw a straight line parallel to the Y axis through the first coordinate point, mark it as the first straight line; get the coordinate point with the largest horizontal coordinate in the target area, mark it as the second coordinate point, draw a straight line parallel to the Y axis through the second coordinate point, mark it as the second straight line; get the coordinate point with the smallest vertical coordinate in the target area, mark it as the third coordinate point, draw a straight line parallel to the X axis through the third coordinate point, mark it as the third straight line; get the coordinate point with the largest vertical coordinate in the target area, mark it as the fourth coordinate point, draw a straight line parallel to the X axis through the fourth coordinate point, mark it as the fourth straight line; get the rectangle enclosed by the first straight line, the second straight line, the third straight line and the fourth straight line, mark it as the flying object rectangle.

6. A simplified law enforcement system for low-altitude safety supervision according to claim 5, characterized in that: The data construction module is configured with a partitioning rectangle construction strategy, and the partitioning rectangle construction strategy includes: Only keep the object rectangle in the reference coordinate system and place the grayscale image of the object in the same position as the binary image of the object; Get one side of the flying object rectangle parallel to the X-axis, mark it as the X-axis parallel side, draw n coordinate points on the X-axis parallel side to divide the X-axis parallel side into n+1 equal intervals, marked as the first interval coordinate points; draw a straight line parallel to the Y-axis through the first interval coordinate point, mark it as the first parallel straight line; get one side of the flying object rectangle parallel to the Y-axis, mark it as the Y-axis parallel side, draw m coordinate points on the Y-axis parallel side to divide the Y-axis parallel side into m+1 equal intervals, marked as the second interval coordinate points; draw a straight line parallel to the X-axis through the second interval coordinate point, mark it as the second parallel straight line; mark the (n+1)×(m+1) rectangles formed by the first parallel straight line and the second parallel straight line as dividing rectangles.

7. A simplified law enforcement system for low-altitude safety supervision according to claim 6, characterized in that: The construction data acquisition module is configured with a construction data acquisition strategy, and the construction data acquisition strategy includes: Get the mean of the grayscale values ​​within each divided rectangle, marked as the rectangle grayscale value; get the divided rectangle corresponding to the maximum grayscale value of the rectangle, marked as the target rectangle; Get the center point of the target rectangle and mark it as the reference midpoint; Get the minimum distance from the reference midpoint to the target rectangle, marked as reference distance; Set a length smaller than the reference distance and mark it as the set length; Draw a circle with the reference midpoint as the circle and the set length as the radius, marked as the first drawn circle; draw a circle with the reference midpoint as the circle and half of the set length as the radius, marked as the second drawn circle; Obtain the mean of the grayscale values ​​within the second drawn circle in the grayscale image of the flying object, marked as the first grayscale mean; obtain the mean of the grayscale values ​​of the portion of the grayscale image of the flying object that does not intersect with the second drawn circle, marked as the second grayscale mean; The difference between the first grayscale mean and the second grayscale mean is calculated and marked as a real-time reference difference.

8. A simplified law enforcement system for low-altitude safety supervision according to claim 7, characterized in that: The threshold acquisition module is configured with a historical data processing strategy, which includes: Obtaining real-time reference differences of infrared images of a first number of UAVs and marking them as historical reference differences; Obtain the range of historical reference difference values, divide the range of historical reference difference values ​​into h equally spaced ranges, and mark them as historical ranges; count the frequency of historical reference difference values ​​in each historical range, and mark them as historical frequencies.

9. A simplified law enforcement system for low-altitude safety supervision according to claim 8, characterized in that: The threshold acquisition module is configured with a threshold acquisition strategy, and the threshold acquisition strategy includes: The abnormal frequency threshold is calculated as: tc=p×D / h; where tc is the abnormal frequency threshold, p is a constant between 0 and 1, and D is the first quantity; Sort the historical ranges from small to large; obtain the historical frequency of the smallest historical range and mark it as the judgment frequency; delete the historical range corresponding to the judgment frequency that is less than the abnormal frequency threshold, obtain the minimum value of the historical range after deletion, and mark it as the reference difference threshold.

10. A simplified law enforcement system for low-altitude safety supervision according to claim 9, characterized in that: The judgment module is configured with a judgment strategy, and the judgment strategy includes: Determine whether the real-time reference difference satisfies a reference difference threshold that is greater than or equal to the reference difference threshold. If so, identify the flying object as a target flying object; for radar information of the target flying object, where the radar information includes the position of the target flying object, determine whether the position of the target flying object is within a no-fly zone. If so, generate an abnormal signal, and transmit the abnormal signal and radar information to the regulatory unit in real time through the communication network.

Images