CN-122017772-A - Pedestrian detection method, device, equipment and medium for airport periphery

CN122017772ACN 122017772 ACN122017772 ACN 122017772ACN-122017772-A

Abstract

The application provides a pedestrian detection method, device, equipment and medium for airport periphery, which are used for the technical field of airport periphery detection and can solve the technical problem that whether pedestrians exist in the periphery or not in the prior art is low in detection efficiency and accuracy. The method comprises the steps of carrying out target detection on radar data corresponding to an airport periphery to obtain a plurality of point clouds, clustering to obtain target points Yun Cu, calculating a distance mean value, a distance standard deviation and a target angle difference value corresponding to the target point cloud cluster to obtain a plurality of space feature indexes, determining a plurality of speed feature indexes according to a speed mean value and a speed variance value corresponding to the target point cloud cluster, determining a time feature index according to a target radar detection result corresponding to the target point cloud cluster, determining corresponding feature values, respectively comparing each feature value with a preset feature threshold value corresponding to each feature value to obtain a corresponding comparison result, and determining a detection result corresponding to the airport periphery, so that the efficiency and the accuracy of detecting pedestrians in the periphery are improved.

Inventors

ZHANG LIBO
ZHANG XUAN
ZHOU KEJIE
CAO LI
ZHANG HAONAN
MAO YU
LI SHAOQIN
SHI JICHENG
CHEN XULIN
REN JUN

Assignees

民航成都电子技术有限责任公司

Dates

Publication Date: 20260512
Application Date: 20260104

Claims (10)

1. A method of pedestrian detection for airport enclosures, the method comprising: performing target detection on radar data corresponding to airport boundaries to obtain a plurality of point clouds, and clustering the point clouds according to a plurality of preset thresholds to obtain at least one target point cloud cluster; Calculating a distance mean value, a distance standard deviation and a target angle difference value corresponding to the target point cloud cluster to obtain a plurality of space feature indexes, and determining a plurality of speed feature indexes according to a speed mean value and a speed variance value corresponding to the target point cloud cluster; determining a time characteristic index according to a target radar detection result corresponding to the target point cloud cluster, and determining characteristic values respectively corresponding to the space characteristic index, the speed characteristic index and the time characteristic index; and respectively comparing the characteristic values with the preset characteristic threshold values corresponding to the characteristic values to obtain corresponding comparison results, and determining detection results corresponding to the airport periphery according to the comparison results.
2. The method of claim 1, wherein clustering the point cloud according to a plurality of preset thresholds to obtain at least one target point cloud cluster comprises: Comparing the distance difference value with the corresponding preset threshold value and the angle difference value with the corresponding preset threshold value according to the distance difference value and the angle difference value between any point clouds to obtain a corresponding comparison result; if the comparison result is that the distance difference value and the angle difference value are smaller than the preset threshold value corresponding to each other, marking the point cloud as point clouds to be clustered, and clustering all the point clouds to be clustered to obtain the corresponding target point cloud cluster; and if the comparison result is that at least one of the distance difference value and the angle difference value is not smaller than the corresponding preset threshold value, marking the point cloud as a non-clustering point cloud.
3. The method of claim 1, wherein the calculating the distance mean, the distance standard deviation, and the target angle difference corresponding to the target point cloud cluster to obtain a plurality of spatial feature indexes includes: calculating the distance mean value, the distance standard deviation and the target angle difference between the maximum angle value and the minimum angle value according to the distance value and the angle value corresponding to each point cloud; And calculating a corresponding distance variance according to the cluster center corresponding to the target point cloud cluster, and obtaining a plurality of space feature indexes according to the distance mean value, the distance standard deviation, the target angle difference value, the distance variance and the number of point clouds corresponding to the target point cloud cluster.
4. The method of claim 1, wherein determining a plurality of speed feature indicators from the speed average and the speed variance values corresponding to the target point cloud cluster comprises: Calculating the speed average value and the speed variance value according to the speed values corresponding to the point clouds, and carrying out normalization processing on the echo intensity values according to the echo intensity values corresponding to the point clouds to obtain weight values corresponding to the point clouds; According to the corresponding weight values, carrying out weighted summation on the speed values of the point clouds to obtain a target speed value corresponding to the current target point cloud cluster, and calculating the difference between the adjacent target speed values according to a plurality of target speed values corresponding to the target point cloud cluster in the history time; And determining a divisor between the forward number and the number of all the differences according to the forward number corresponding to the forward difference in the differences, obtaining a speed variation value, and determining a plurality of speed characteristic indexes according to the speed average value, the speed variance value and the speed variation value.
5. The method according to claim 1, wherein the determining a time feature index according to the target radar detection result corresponding to the target point cloud cluster includes: Determining the existence time length corresponding to the target point cloud cluster according to all the target radar detection results, and judging whether the target point cloud cluster has position coincidence according to the position of the point cloud cluster corresponding to each target radar detection result; if yes, determining a coincidence time length, and determining the time feature index according to the presence time length and the coincidence time length; if the time feature index does not exist, the time feature index is determined according to the existence duration.
6. The method of claim 1, wherein determining the feature values respectively corresponding to the spatial feature index, the speed feature index, and the time feature index comprises: Determining target characteristic indexes respectively corresponding to the space characteristic indexes, the speed characteristic indexes and the time characteristic indexes according to a plurality of index thresholds respectively corresponding to the space characteristic indexes, the speed characteristic indexes and the time characteristic indexes, wherein the target characteristic indexes are characteristic indexes which do not exceed the index thresholds; And obtaining the characteristic values corresponding to the space characteristic index, the speed characteristic index and the time characteristic index according to the dividing values of the target index number and the characteristic index number, wherein the target index number is the number corresponding to the target characteristic index, and the characteristic index number is the number corresponding to the space characteristic index, the speed characteristic index and the time characteristic index.
7. The method according to claim 1, wherein the determining the detection result corresponding to the airport periphery according to the comparison result includes: Determining the comparison result; If the comparison result is that the characteristic values corresponding to the spatial characteristic index, the speed characteristic index and the time characteristic index are all larger than the corresponding preset characteristic threshold value, determining that the corresponding detection result is that pedestrians are close to the airport periphery; And if at least one of the characteristic values is not greater than the corresponding preset characteristic threshold value, determining that the corresponding detection result is that no pedestrians are close to the airport periphery.
8. A pedestrian detection device for an airport enclosure, the device comprising: The detection module is used for carrying out target detection on radar data corresponding to the airport periphery to obtain a plurality of point clouds, and clustering the point clouds according to a plurality of preset thresholds to obtain at least one target point cloud cluster; the computing module is used for computing the distance mean value, the distance standard deviation and the target angle difference value corresponding to the target point cloud cluster to obtain a plurality of space characteristic indexes, and determining a plurality of speed characteristic indexes according to the speed mean value and the speed variance value corresponding to the target point cloud cluster; The determining module is used for determining a time characteristic index according to a target radar detection result corresponding to the target point cloud cluster and determining characteristic values respectively corresponding to the space characteristic index, the speed characteristic index and the time characteristic index; and the comparison module is used for respectively comparing each characteristic value with the corresponding preset characteristic threshold value to obtain a corresponding comparison result, and determining a detection result corresponding to the airport periphery according to the comparison result.
9. A computer device, comprising: one or more processors; a memory; One or more programs, wherein the one or more programs are stored in memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored therein program code which is callable by a processor to perform the method according to any one of claims 1 to 7.

Description

Pedestrian detection method, device, equipment and medium for airport periphery Technical Field The application relates to the technical field of airport periphery detection, in particular to a pedestrian detection method, device, equipment and medium for airport periphery. Background The airport enclosure is an important component of an airport safety protection system and is mainly used for preventing irrelevant people from entering a flight area or a sensitive area, the airport enclosure usually adopts a metal net structure (such as a wire net, a steel wire net, a welding net and the like), has the characteristics of long coverage range, wide environment, surrounding facilities such as grasslands, shrubs, signboards and the like, has extremely low tolerance to false alarm, and needs quick response once alarming, so that pedestrians are quickly driven away. The existing pedestrian detection method for the airport periphery mostly adopts a simple speed or energy threshold, namely, whether the detected target is a pedestrian or not is judged by determining the speed of the detected target or the corresponding radar echo energy, and therefore non-pedestrian targets such as real pedestrian targets and vegetation swing are difficult to distinguish effectively, the false alarm rate is high, and the airport high-level security requirement is difficult to meet. Therefore, the existing pedestrian detection method for the airport periphery has the problem of low detection efficiency and accuracy. Disclosure of Invention The application provides a pedestrian detection method, device, equipment and medium for an airport enclosure, which are used for solving the problems of low detection efficiency and low accuracy of the existing pedestrian detection method for the airport enclosure. In a first aspect, the present application provides a method for detecting pedestrians around an airport, the method comprising: Performing target detection on radar data corresponding to airport boundaries to obtain a plurality of point clouds, and clustering the point clouds according to a plurality of preset thresholds to obtain at least one target point cloud cluster; calculating a distance mean value, a distance standard deviation and a target angle difference value corresponding to the target point cloud cluster to obtain a plurality of space characteristic indexes, and determining a plurality of speed characteristic indexes according to a speed mean value and a speed variance value corresponding to the target point cloud cluster; determining a time characteristic index according to a target radar detection result corresponding to the target point cloud cluster, and determining characteristic values respectively corresponding to the space characteristic index, the speed characteristic index and the time characteristic index; and respectively comparing each characteristic value with the corresponding preset characteristic threshold value to obtain a corresponding comparison result, and determining a detection result corresponding to the airport periphery according to the comparison result. In some embodiments of the present application, clustering point clouds according to a plurality of preset thresholds to obtain at least one target point cloud cluster includes: according to the distance difference value and the angle difference value between any point clouds, comparing the distance difference value with a corresponding preset threshold value and the angle difference value with a corresponding preset threshold value to obtain a corresponding comparison result; if the comparison result is that the distance difference value and the angle difference value are smaller than the corresponding preset threshold values, marking the point cloud as point clouds to be clustered, and clustering all the point clouds to be clustered to obtain corresponding target point cloud clusters; if the comparison result is that at least one of the distance difference value and the angle difference value is not smaller than the corresponding preset threshold value, the point cloud is marked as non-clustering point cloud. In some embodiments of the present application, calculating a distance mean value, a distance standard deviation, and a target angle difference value corresponding to a target point cloud cluster to obtain a plurality of spatial feature indexes includes: According to the distance value and the angle value corresponding to each point cloud, calculating a distance average value, a distance standard deviation and a target angle difference value between a maximum angle value and a minimum angle value; and calculating a corresponding distance variance according to the cluster center corresponding to the target point cloud cluster, and obtaining a plurality of space feature indexes according to the distance mean value, the distance standard deviation, the target angle difference value, the distance variance and the number of point clouds correspo