Method, device, computer equipment and storage medium for detecting objects thrown from high altitude

Abstract

The present application relates to the field of security monitoring, and in particular to a method, device, computer equipment and storage medium for detecting objects thrown from a high altitude, the method comprising: obtaining a detection area, the detection area including the starting position of the object thrown; obtaining the location of the object thrown in response to a trigger instruction of an object thrown from a high altitude, and tracking the object to obtain tracking information; if the location of the object thrown is not in the detection area, determining the starting position of the object thrown based on the tracking information. The present invention can improve the accuracy of judging the starting position of the object thrown.

Description

Technical Field

[0001] The present application relates to the field of security monitoring, and in particular to a method, device, computer equipment and storage medium for detecting objects thrown from a high altitude. Background Art

[0002] With the advancement of the modernization of residents' lives, more and more high-rise buildings are rising from the ground, and the phenomenon of throwing objects from high places is becoming more and more common. Throwing objects from high places has always attracted much attention because it is not only an uncivilized behavior, but also poses a huge threat to urban safety.

[0003] The existing method of detecting high-altitude objects dropping uses a camera to monitor the target building, and the server analyzes the monitoring video to determine whether a high-altitude object dropping event has occurred. Since the data analysis and processing of the server has a certain delay, when a high-altitude object dropping event is detected, the location of the object may not be the starting location of the object, so the judgment of the starting location of the object is inaccurate. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for detecting high-altitude objects in response to the above-mentioned technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting objects thrown from a high altitude, the method comprising:

[0006] Acquire a detection area, where the detection area includes a starting position of the parabola;

[0007] Responding to a trigger instruction of a high-altitude object throwing event, obtaining the location of the object, and tracking the object to obtain tracking information;

[0008] If the location of the parabola is not within the detection area, the starting location of the parabola is determined based on the tracking information.

[0009] In one embodiment, acquiring the detection area includes:

[0010] Determine a corresponding detection rule based on the current detection time, wherein the detection rule includes window opening detection and light detection;

[0011] The target building is detected based on the detection rules to determine the detection area.

[0012] In one embodiment, tracking the parabola to obtain tracking information includes:

[0013] acquiring an image of the parabola;

[0014] When the image area of ​​the parabola is greater than or equal to a set threshold, the parabola is tracked based on the features of the parabola image to obtain tracking information;

[0015] When the image area of ​​the parabola is smaller than a set threshold, the parabola is tracked based on the coordinates of the parabola in a preset reference coordinate system to obtain tracking information.

[0016] In one embodiment, the tracking information includes a first monitoring video containing information about the location of the parabola, and determining the starting location of the parabola based on the tracking information includes:

[0017] Obtain a second surveillance video several times before the high-altitude throwing event is triggered;

[0018] Splicing the first surveillance video with the second surveillance video to obtain a third surveillance video;

[0019] Based on the position information of the parabola in any video frame of the third monitoring video, obtaining a first feature of the parabola;

[0020] Matching the first feature with the feature in the previous video frame to obtain a second feature of the parabola, and determining the position of the parabola in the previous video frame;

[0021] The feature matching step is repeated until the feature in the previous video frame cannot be matched, and the starting position of the parabola is determined based on the position of the parabola in the corresponding video frame.

[0022] In one embodiment, the tracking information includes a first monitoring video containing information about the location of the parabola, and determining the starting location of the parabola based on the tracking information includes:

[0023] Determine the trajectory of the parabolic object based on the position information of the parabolic object in the first monitoring video;

[0024] A starting position of the parabola is determined based on the trajectory of the parabola.

[0025] In one embodiment, the method further comprises:

[0026] Acquire a target area of ​​the detection area, and use a center point of the target area as a first preset point;

[0027] The position of the detected object is taken as the second preset point;

[0028] A patrol route is generated based on the first preset point and the second preset point, and a high-altitude throwing event detection is performed based on the patrol route.

[0029] In one embodiment, acquiring the target area of ​​the detection area includes:

[0030] Based on a preset reference coordinate system, obtaining coordinates of detection points in the detection area;

[0031] Clustering the detection points based on the K-means clustering method;

[0032] The area where the cluster containing the most detection points is located is taken as the target area.

[0033] In a second aspect, an embodiment of the present invention provides a device for detecting objects thrown from a high altitude, the device comprising:

[0034] A tracking module, used to obtain the location of the object in response to a trigger instruction of a high-altitude object throwing event, and track the object to obtain tracking information;

[0035] The first determination module is used to determine the starting position of the parabola based on the tracking information if the position of the parabola is not in the detection area.

[0036] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Acquire a detection area, where the detection area includes a starting position of the parabola;

[0038] Responding to a trigger instruction of a high-altitude object throwing event, obtaining the location of the object, and tracking the object to obtain tracking information;

[0039] If the location of the parabola is not within the detection area, the starting location of the parabola is determined based on the tracking information.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the processor executes the computer program, the following steps are implemented:

[0041] Acquire a detection area, where the detection area includes a starting position of the parabola;

[0042] Responding to a trigger instruction of a high-altitude object throwing event, obtaining the location of the object, and tracking the object to obtain tracking information;

[0043] If the location of the parabola is not within the detection area, the starting location of the parabola is determined based on the tracking information.

[0044] The above method, apparatus, computer equipment and storage medium obtain a detection area, the detection area includes the starting position of the parabola, obtain the location of the parabola in response to a trigger instruction of a high-altitude parabola event, and track the parabola to obtain tracking information. If the location of the parabola is not in the detection area, the starting position of the parabola is determined based on the tracking information. The present invention can improve the accuracy of the judgment of the starting position of the parabola. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A diagram showing an application environment of a method for detecting objects thrown from a high altitude in one embodiment;

[0046] Figure 2 A schematic diagram of a process for detecting objects thrown from a high altitude in one embodiment;

[0047] Figure 3 A schematic diagram of a flow chart of a method for determining a detection area in an embodiment;

[0048] Figure 4 A schematic diagram of a flow chart of a method for obtaining tracking information in one embodiment;

[0049] Figure 5 is a schematic flow chart of a method for determining a starting position in one embodiment;

[0050] Figure 6 A schematic diagram of a flow chart of a method for determining a starting position in another embodiment;

[0051] Figure 7 is a schematic diagram of a method for determining a starting position in an exemplary embodiment;

[0052] Figure 8 A schematic diagram of a flow chart of a method for detecting objects thrown from a high altitude in another embodiment;

[0053] Fig. 9 is a flow chart of a method for determining a target area in another embodiment;

[0054] Fig.10 1 is a flow chart of an inspection process in one embodiment;

[0055] Fig.11 1 is a schematic diagram of the structure of a device for detecting objects thrown from a high altitude in one embodiment;

[0056] Fig.12 The figure is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The present application provides a method for detecting objects thrown from a high altitude, which can be applied to Figure 1In the application environment shown. Among them, the gun camera 102 and the ball camera 104 communicate with the server 106 through the network. Among them, the gun camera covers the target building from the high level downward in sequence according to the installation distance and focal length. Each gun camera has its own monitoring area. The ball camera is installed on the side of the front of the target building, and there is a certain angle with the floor. The gun camera and the ball camera are grouped and connected to the channel of the network video recorder in sequence. Each gun camera is set to a master-slave linkage mode with the ball camera, in which the gun camera is the main camera and the ball camera is the slave camera. The gun camera is used to detect high-altitude throwing events. The server obtains the location of the throwing object and controls the ball camera to track the throwing object to obtain tracking information. The server determines the starting position of the throwing object based on the tracking information. Among them, the server 106 can be implemented with an independent server or a server cluster composed of multiple servers.

[0059] In one embodiment, if Figure 2 As shown, a method for detecting high-altitude objects is provided, and the method is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0060] S202: Acquire a detection area, where the detection area includes a starting position of the parabola.

[0061] When an object is thrown from a high altitude, the starting position of the object is within the detection area. The detection area can be understood as a window-opening area or a light-on area that can be monitored.

[0062] S204: In response to a trigger instruction of a high-altitude object throwing event, the location of the object is obtained, and the object is tracked to obtain tracking information.

[0063] The high-altitude object throwing event in this embodiment does not limit the height of the thrown object. It can be understood that any object throwing event within the detection range of the target building can be regarded as a high-altitude object throwing event.

[0064] In this embodiment, the detection algorithm for high-altitude object dropping events can use a deep learning algorithm to train pictures of high-altitude object dropping events to achieve high-altitude object dropping detection, or can use a picture comparison method to compare the collected pictures with pictures without high-altitude object dropping events to achieve high-altitude object dropping detection. It can be understood that this embodiment does not limit the detection algorithm for high-altitude object dropping events, and other high-altitude object dropping event detection algorithms can also be used.

[0065] S206: If the location of the parabola is not within the detection area, determine the starting location of the parabola based on the tracking information.

[0066] Considering that the triggering of high-altitude object throwing events has a certain delay, the location of the object may not be in the detection area. In this embodiment, if the closest distance between the location of the object and the detection area is greater than the set threshold, it is judged to be out of the detection area, otherwise, it is judged to be in the detection area. When the location of the object is not in the detection area, the starting position of the object is determined based on the tracking information, so as to ensure the accuracy of the judgment of the starting position of the object.

[0067] In one embodiment, if Figure 3 As shown, obtaining the detection area includes the following steps:

[0068] S302: Determine a corresponding detection rule based on the current detection time, where the detection rule includes window opening detection and light detection;

[0069] S304: Detect the target building based on the detection rule and determine the detection area.

[0070] It is understandable that, under normal circumstances, high-altitude throwing incidents usually occur when windows or lights are open. Based on the above detection rules, the target building is detected, and the sum of the areas where windows or lights are open is determined as the detection area.

[0071] Specifically, if the current detection time is daytime, window opening detection is performed; if the current detection time is nighttime, light detection is performed. The window opening detection method uses scale-invariant feature transform (SIFT) to obtain feature points of the detection image and template image, and then uses the deep learning algorithm YOLO V3 to determine whether there is a window opening action to achieve window opening detection. The light detection method uses a deep learning algorithm to detect bright spots in the surveillance video to determine whether the light is turned on.

[0072] In this embodiment, the corresponding detection rule is determined according to the current detection time, which can improve the accuracy of determining the detection area, so that the starting position of the parabola can be determined more accurately.

[0073] Furthermore, this embodiment performs human body detection on the monitoring area of ​​the target building. When a human body is detected, the window opening detection or light detection is performed again, thereby refreshing the detection area. In addition, the window opening detection or light turning on detection can also be performed again according to the time period. In some time periods when windows or lights are frequently opened, the window opening or light detection is performed again to achieve real-time update of the detection area. By updating the detection area in real time, the accuracy of determining the detection area can be improved, so that the starting position of the parabola can be determined more accurately.

[0074] In one embodiment, if Figure 4 As shown, tracking the parabola to obtain tracking information includes the following steps:

[0075] S402: Acquire an image of the parabola;

[0076] S404: When the image area of ​​the parabola is greater than or equal to a set threshold, the parabola is tracked based on the features of the parabola image to obtain tracking information;

[0077] S406: When the image area of ​​the parabola is smaller than a set threshold, the parabola is tracked based on the coordinates of the parabola in a preset reference coordinate system to obtain tracking information.

[0078] In this embodiment, the corresponding tracking method is selected according to the image area of ​​the parabola to improve the accuracy of parabola tracking. When the image area of ​​the parabola is greater than or equal to the set threshold, clear image features can be obtained, so the parabola can be tracked by obtaining the features of the parabola image in the video frame and associating the features of the parabola image, and accurate tracking information can be obtained; when the image area of ​​the parabola is less than the set threshold, clear image features cannot be obtained, so the parabola can be tracked by establishing a reference coordinate system and determining the coordinates of the parabola in the video frame in the reference coordinate system for association, and accurate tracking information can be obtained.

[0079] In one embodiment, the tracking information includes a first monitoring video containing the location information of the parabola, such as Figure 5 As shown, determining the starting position of the parabola based on the tracking information includes the following steps:

[0080] S502: Acquire a second surveillance video several times before the high-altitude throwing event is triggered;

[0081] S504: splicing the first surveillance video and the second surveillance video to obtain a third surveillance video;

[0082] S506: Acquire a first feature of the parabola based on the position information of the parabola in any video frame of the third monitoring video;

[0083] S508: Matching the first feature with the feature in the previous video frame to obtain a second feature of the parabola, and determining the position of the parabola in the previous video frame;

[0084] S510: Repeat the feature matching step until the feature in the previous video frame cannot be matched, and then determine the starting position of the parabola based on the position of the parabola in the corresponding video frame.

[0085] In this embodiment, the monitoring device can be set to save the video recording of the first M seconds of the high-altitude throwing event, and the time can be set according to actual needs. The first monitoring video and the second monitoring video are spliced ​​to obtain a third monitoring video, and the first feature of the parabola is obtained based on the position information of the parabola in any video frame of the third monitoring video; the first feature is matched with the feature in the previous video frame to obtain the second feature of the parabola, and the position of the parabola in the previous video frame is determined, and the parabola is reversed in sequence until it cannot be matched with the feature in the previous video frame, and the starting position of the parabola is determined based on the position of the parabola in the corresponding video frame. In this embodiment, the starting position of the parabola can be accurately determined by reversely deducing the parabola feature.

[0086] In one embodiment, the tracking information includes a first monitoring video containing the location information of the parabola, such as Figure 6 As shown, determining the starting position of the parabola based on the tracking information includes the following steps:

[0087] S602: Determine the trajectory of the parabolic object based on the position information of the parabolic object in the first monitoring video;

[0088] S604: Determine the starting position of the parabola based on the trajectory of the parabola.

[0089] Figure 7 is a schematic diagram of the parabola's trajectory. Obtain the horizontal displacement difference Δx of the parabola between two points A and B at time T1 and T2, according to the formula The initial velocity v0 can be obtained, and the time t taken from the starting position to the corresponding position at time T1 can be obtained according to the formula s=v0·t, where S represents the distance from the starting position to the corresponding position at time T1. The vertical displacement H from the parabola point to the time T1 can be obtained by the formula y = ax 2 The parabolic trajectory from the starting position to time T1 is obtained by fitting +bx+c, and the position of the parabolic point is obtained by the vertical displacement, where a, b, and c represent constants.

[0090] It is understandable that some birds flying by may also trigger high-altitude object dropping events, but their motion trajectories do not conform to the trajectory of high-altitude object dropping. Therefore, in one embodiment, these abnormal situations are excluded by determining whether it is a high-altitude object dropping event based on the tracking trajectory. The trajectory tracking is obtained by analyzing the tracking information, and it is determined whether it is a high-altitude object dropping event based on the tracking trajectory. If not, it is filtered, and if so, the starting position of the object is determined.

[0091] In one embodiment, if Figure 8 As shown, a method for detecting objects thrown from a high altitude also includes the following steps:

[0092] S802: Acquire a target area of ​​the detection area, and use a center point of the target area as a first preset point;

[0093] S804: taking the position of the detected object as a second preset point;

[0094] S806: Generate an inspection route based on the first preset point and the second preset point, and perform high-altitude throwing event detection based on the inspection route.

[0095] In order to detect the incident of dropping objects from high places in a timely manner, a patrol inspection strategy is added on the basis of the above embodiment.

[0096] Among them, Fig. 9 As shown, obtaining the target area of ​​the detection area includes the following steps:

[0097] S902: Based on a preset reference coordinate system, obtaining coordinates of detection points in the detection area;

[0098] S904: clustering the detection points based on a K-means clustering method;

[0099] S906: The area where the cluster containing the most detection points is located is taken as the target area.

[0100] Assume x i (i=1,2,…,n) is the detection point, μ j =(j=1,2,…,k) is the initialized cluster center, and the cluster center is randomly selected according to the K value. The objective function can be written as:

[0101]

[0102] K clusters are obtained through iteration, and the area containing the cluster with the most detection points is taken as the target area.

[0103] The object in this embodiment refers to a person. The overall process of the inspection strategy is as follows: Fig.10As shown. By performing human body detection and face detection on the entire monitoring area, when a human body or a face is detected, the face is captured and saved, and the location of the detected object is set as the second preset point. The face and the second preset point are in one-to-one correspondence. The stay time and the number of cruises at the first preset point and the second preset point are set. The first preset point and the second preset point form a cruise route. When the cruise reaches the preset point, the high-altitude throwing event is detected. When a high-altitude throwing event occurs, the throwing is tracked to obtain tracking information. If the location of the throwing object is not in the detection area, the starting position of the throwing object is determined based on the tracking information. The thrower is the face of the preset point corresponding to the starting position, which clarifies the responsibility for the high-altitude throwing event. When each preset point reaches the set number of times, the preset point and the corresponding face picture are deleted. When the total number of preset points reaches the threshold, the preset point with the smallest number and the corresponding face picture are deleted.

[0104] This embodiment improves the accuracy of high-altitude object dropping event detection by setting the area where high-altitude object dropping events may occur as a preset point and then using a patrol detection high-altitude object dropping event strategy.

[0105] In one embodiment, when the location of the object is not within the detection area, the camera is controlled to capture faces upwards. When faces of multiple different areas are captured, the face closest to the starting location of the object is taken as the thrower, thereby clarifying the responsibility for the high-altitude throwing incident.

[0106] It should be understood that although Figure 1-10 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-10 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0107] In one embodiment, if Fig.11 As shown, the present invention provides a device for detecting objects thrown from a high altitude, the device comprising:

[0108] A first acquisition module 112, used to acquire a detection area, where the detection area includes a starting position of the parabola;

[0109] The tracking module 114 is used to obtain the location of the object in response to the trigger instruction of the high-altitude object throwing event, and track the object to obtain tracking information;

[0110] The first determination module 116 is configured to determine a starting position of the parabola based on the tracking information if the position of the parabola is not within the detection area.

[0111] In one embodiment, the first acquisition module includes:

[0112] A second determination module, configured to determine a corresponding detection rule based on a current detection time, wherein the detection rule includes window opening detection and light detection;

[0113] The third determination module is used to detect the target building based on the detection rule and determine the detection area.

[0114] In one embodiment, the tracking module includes:

[0115] A second acquisition module, used for acquiring an image of the parabola;

[0116] A third acquisition module is used to track the parabola based on the characteristics of the parabola image to obtain tracking information when the image area of ​​the parabola is greater than or equal to a set threshold;

[0117] When the image area of ​​the parabola is smaller than a set threshold, the parabola is tracked based on the coordinates of the parabola in a preset reference coordinate system to obtain tracking information.

[0118] In one embodiment, the tracking information includes a first monitoring video containing parabolic position information, and the first determining module is specifically configured to:

[0119] Obtain a second surveillance video several times before the high-altitude throwing event is triggered;

[0120] Splicing the first surveillance video with the second surveillance video to obtain a third surveillance video;

[0121] Based on the position information of the parabola in any video frame of the third monitoring video, obtaining a first feature of the parabola;

[0122] Matching the first feature with the feature in the previous video frame to obtain a second feature of the parabola, and determining the position of the parabola in the previous video frame;

[0123] The feature matching step is repeated until the feature in the previous video frame cannot be matched, and the starting position of the parabola is determined based on the position of the parabola in the corresponding video frame.

[0124] In one embodiment, the tracking information includes a first monitoring video containing parabolic position information, and the first determining module is specifically configured to:

[0125] Determine the trajectory of the parabolic object based on the position information of the parabolic object in the first monitoring video;

[0126] A starting position of the parabola is determined based on the trajectory of the parabola.

[0127] In one embodiment, the device further includes an inspection setting module, which is specifically used to:

[0128] Acquire a target area of ​​the detection area, and use a center point of the target area as a first preset point;

[0129] The position of the detected object is taken as the second preset point;

[0130] A patrol route is generated based on the first preset point and the second preset point, and a high-altitude throwing event detection is performed based on the patrol route.

[0131] In one embodiment, acquiring the target area of ​​the detection area includes:

[0132] Based on a preset reference coordinate system, obtaining coordinates of detection points in the detection area;

[0133] Clustering the detection points based on the K-means clustering method;

[0134] The area where the cluster containing the most detection points is located is taken as the target area.

[0135] For the specific definition of the high-altitude object detection device, please refer to the definition of the high-altitude object detection method above, which will not be repeated here. Each module in the above-mentioned high-altitude object detection device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0136] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store motion detection data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in any of the above-mentioned embodiments of the method for detecting high-altitude objects are implemented.

[0137] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any of the above-mentioned embodiments of the method for detecting high-altitude objects are implemented.

[0139] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above-mentioned embodiments of the method for detecting high-altitude objects are implemented.

[0140] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for detecting objects thrown from a high altitude, characterized in that: The method comprises: Acquire a detection area, where the detection area includes a starting position of the parabola; Responding to a trigger instruction of a high-altitude object throwing event, obtaining the location of the object, and tracking the object to obtain tracking information; If the location of the parabola is not within the detection area, determining the starting location of the parabola based on the tracking information; The obtaining of the detection area comprises: Determine a corresponding detection rule based on the current detection time, wherein the detection rule includes window opening detection and light detection; The target building is detected based on the detection rules to determine the detection area.

2. The method according to claim 1, characterized in that: The tracking of the parabola to obtain tracking information includes: acquiring an image of the parabola; When the image area of ​​the parabola is greater than or equal to a set threshold, the parabola is tracked based on the features of the parabola image to obtain tracking information; When the image area of ​​the parabola is smaller than a set threshold, the parabola is tracked based on the coordinates of the parabola in a preset reference coordinate system to obtain tracking information.

3. The method according to claim 1, characterized in that The tracking information includes a first monitoring video containing information about the location of the parabola, and determining the starting location of the parabola based on the tracking information includes: Obtain a second surveillance video several times before the high-altitude throwing event is triggered; Splicing the first surveillance video with the second surveillance video to obtain a third surveillance video; Based on the position information of the parabola in any video frame of the third monitoring video, obtaining a first feature of the parabola; Matching the first feature with the feature in the previous video frame to obtain a second feature of the parabola, and determining the position of the parabola in the previous video frame; The feature matching step is repeated until the feature in the previous video frame cannot be matched, and the starting position of the parabola is determined based on the position of the parabola in the corresponding video frame.

4. The method according to claim 1, characterized in that: The tracking information includes a first monitoring video containing information about the location of the parabola, and determining the starting location of the parabola based on the tracking information includes: Determine the trajectory of the parabolic object based on the position information of the parabolic object in the first monitoring video; A starting position of the parabola is determined based on the trajectory of the parabola.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire a target area of ​​the detection area, and use a center point of the target area as a first preset point; The position of the detected object is taken as the second preset point; A patrol route is generated based on the first preset point and the second preset point, and a high-altitude throwing event detection is performed based on the patrol route.

6. The method according to claim 5, characterized in that The acquiring of the target area of ​​the detection area comprises: Based on a preset reference coordinate system, obtaining coordinates of detection points in the detection area; Clustering the detection points based on the K-means clustering method; The area where the cluster containing the most detection points is located is taken as the target area.

7. A device for detecting objects thrown from a high altitude, characterized in that: The device comprises: A first acquisition module, used to acquire a detection area, where the detection area includes a starting position of the parabola; A tracking module, used to obtain the location of the object in response to a trigger instruction of a high-altitude object throwing event, and track the object to obtain tracking information; A first determination module, configured to determine a starting position of the parabola based on the tracking information if the position of the parabola is not within the detection area; The first acquisition module includes: A second determination module, configured to determine a corresponding detection rule based on a current detection time, wherein the detection rule includes window opening detection and light detection; The third determination module is used to detect the target building based on the detection rule and determine the detection area.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images