High-altitude object throwing detection method, device and equipment and storage medium
By detecting motion objects and determining high-altitude object throwing behavior on the detection image data, the problem of high-altitude object throwing detection in the prior art is solved, and accurate detection and alarm of high-altitude object throwing behavior is achieved.
Patent Information
- Application Number
- CN202510084838.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-20
- Publication Date
- 2025-05-16
AI Technical Summary
The existing high-altitude object throw detection system can easily lead to false alarms or misreports under environmental changes or misjudgment of similar objects, and cannot accurately detect and identify high-altitude object throwing behavior.
By acquiring the image data to be detected, motion target detection and object throwing at high altitude are performed. If it is determined that it is yes, it is integrated and stored and alarmed. The method includes steps such as data preprocessing, background modeling, motion object detection, motion trajectory prediction and high-altitude object throwing behavior determination.
Effective detection of object thrown at high altitudes is achieved, the detection false alarm rate is reduced, and the judgment accuracy is improved.
Smart Images
Figure CN120013987A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of high altitude object dropping detection, and in particular to a high altitude object dropping detection method, device, equipment and storage medium. Background Art
[0002] High-altitude object dropping hazard detection is to monitor and identify high-altitude object dropping behaviors through technical means to prevent injuries or property losses caused by high-altitude object dropping. Such detection systems usually rely on video surveillance, image recognition, machine learning and other technologies to identify potential dangerous behaviors and trigger alarms or warning mechanisms.
[0003] However, existing detection systems may cause false alarms or missed alarms due to environmental changes or misjudgment of similar objects. For example, the system may misjudge leaves or flying birds as objects thrown from high altitudes, or fail to detect actual throwing behavior in a timely manner.
[0004] In view of this, there is an urgent need for a method for detecting objects dropped from high places to effectively detect and identify the behavior of dropping objects from high places, and then record it and issue an alarm.
[0005] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention
[0006] The main purpose of the present invention is to provide a method, device, equipment and storage medium for detecting objects thrown from high places, aiming to solve the technical problem that the existing technology cannot accurately detect and identify the behavior of throwing objects from high places.
[0007] To achieve the above object, the present invention provides a method for detecting objects thrown from a high altitude, the method comprising the following steps:
[0008] Acquire image data to be detected;
[0009] Performing moving target detection based on the image data to be detected to obtain a moving target detection result;
[0010] Performing high-altitude object throwing behavior determination based on the image data to be detected and the moving target detection result to obtain a high-altitude object throwing determination result;
[0011] If the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored, and an alarm is issued.
[0012] Optionally, performing moving target detection based on the image data to be detected to obtain a moving target detection result specifically includes:
[0013] Performing data preprocessing on the image data to be detected to obtain processed image data;
[0014] Perform background modeling based on the processed image data to obtain a moving target recognition result;
[0015] Based on the moving target recognition result, moving target detection is performed on the processed image data to obtain a moving target detection result.
[0016] Optionally, performing data preprocessing on the image data to be detected to obtain processed image data specifically includes:
[0017] Performing image conversion based on the image data to be detected to obtain converted image data;
[0018] The converted image data is subjected to image processing to obtain the processed image data.
[0019] Optionally, performing a high-altitude object dropping behavior determination based on the to-be-detected image data and the moving target detection result to obtain a high-altitude object dropping determination result specifically includes:
[0020] Predicting the trajectory of a moving target based on the image data to be detected and the moving target detection result to obtain a moving target trajectory prediction result;
[0021] The high-altitude object throwing behavior is judged based on the motion trajectory prediction result to obtain the high-altitude object throwing judgment result.
[0022] Optionally, performing moving target trajectory prediction based on the image data to be detected and the moving target detection result to obtain a moving target trajectory prediction result specifically includes:
[0023] Based on the image data to be detected and the moving target detection result, instantaneous prediction is performed on the position of the moving target to obtain an instantaneous position prediction result;
[0024] Correcting and updating the instantaneous position prediction result based on the image data to be detected to obtain a corresponding instantaneous trajectory result;
[0025] All instantaneous trajectory results are integrated based on the motion timing information to obtain the motion trajectory prediction result.
[0026] Optionally, performing a high-altitude object dropping behavior determination based on the motion trajectory prediction result to obtain a high-altitude object dropping determination result specifically includes:
[0027] Perform trajectory analysis based on the motion trajectory prediction result to obtain a first high-altitude projectile determination result;
[0028] Performing motion feature analysis based on the motion trajectory prediction result to obtain a second high-altitude object throwing determination result;
[0029] The first high-altitude object dropping determination result and the second high-altitude object dropping determination result are integrated to obtain the high-altitude object dropping determination result.
[0030] Optionally, the method is characterized in that, before acquiring the image data to be detected, the method further comprises:
[0031] Start the high-altitude object throwing detection system;
[0032] Based on the parameter adjustment instruction, the system parameters of the high-altitude object dropping detection system are configured after startup to obtain the high-altitude object dropping detection system after parameter adjustment.
[0033] In addition, in order to achieve the above-mentioned purpose, the present invention also proposes a high-altitude object detection device, the high-altitude object detection device comprising:
[0034] Image acquisition module: obtains the image data to be detected;
[0035] Target detection module: performs moving target detection based on the image data to be detected to obtain a moving target detection result;
[0036] Behavior judgment module: based on the image data to be detected and the moving target detection result, the behavior judgment of high-altitude throwing is performed to obtain the high-altitude throwing judgment result;
[0037] Determination execution module: if the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored and an alarm is issued.
[0038] In addition, to achieve the above-mentioned objectives, the present invention also proposes a high-altitude object dropping detection device, which includes: a memory, a processor, and a high-altitude object dropping detection program stored in the memory and executable on the processor, and the high-altitude object dropping detection program is configured to implement the steps of the high-altitude object dropping detection method described above.
[0039] In addition, to achieve the above-mentioned purpose, the present invention also proposes a computer-readable storage medium storing a computer program, wherein a high-altitude object dropping detection program is stored on the storage medium, and when the high-altitude object dropping detection program is executed by a processor, the steps of the high-altitude object dropping detection method described above are implemented.
[0040] The present invention first obtains image data to be detected; performs moving target detection based on the image data to be detected to obtain a moving target detection result; performs high-altitude object dropping behavior determination based on the image data to be detected and the moving target detection result to obtain a high-altitude object dropping determination result; if the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored and an alarm is issued. The present invention obtains corresponding detection results by detecting and analyzing the image data to be detected, and then determines the high-altitude object dropping behavior based on the relevant data and the detection results, thereby achieving effective detection of high-altitude object dropping behavior and reducing the false alarm rate of detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 It is a structural schematic diagram of a high-altitude object detection device in a hardware operating environment involved in an embodiment of the present invention;
[0042] Figure 2 It is a schematic diagram of the flow chart of the first embodiment of the method for detecting objects thrown from a high altitude of the present invention;
[0043] Figure 3 It is a schematic diagram of the flow chart of the second embodiment of the method for detecting objects thrown from a high altitude of the present invention;
[0044] Figure 4 It is a schematic flow chart of a third embodiment of a method for detecting objects thrown from a high altitude according to the present invention;
[0045] Figure 5 This is a structural block diagram of the first embodiment of the high-altitude object detection device of the present invention.
[0046] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0048] Reference Figure 1 , Figure 1 The present invention is a schematic diagram of the structure of a high-altitude object detection device in the hardware operating environment involved in the embodiment of the present invention.
[0049] like Figure 1As shown, the high-altitude object detection device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0050] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the high-altitude object detection device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.
[0051] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a high-altitude object detection program.
[0052] exist Figure 1 In the high-altitude object dropping detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the high-altitude object dropping detection device of the present invention can be set in the high-altitude object dropping detection device, and the high-altitude object dropping detection device calls the high-altitude object dropping detection program stored in the memory 1005 through the processor 1001, and executes the high-altitude object dropping detection method provided by the embodiment of the present invention.
[0053] The embodiment of the present invention provides a method for detecting objects thrown from a high altitude, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a method for detecting objects thrown from a high altitude according to the present invention.
[0054] In this embodiment, the method for detecting objects thrown from a high altitude comprises the following steps:
[0055] Step S10: Acquire image data to be detected;
[0056] It should be noted that, in a specific implementation, the image data to be detected is obtained by collecting images of the working area of the high-altitude object throwing detection system through monitoring equipment or imaging equipment, and the image data to be detected can specifically be video data or image data.
[0057] It should also be noted that in the specific implementation, in order to improve the judgment accuracy of the high-altitude object throwing detection system, the camera device in the image acquisition module of the high-altitude object throwing detection system needs to be adjusted in position, angle and quantity according to the image acquisition requirements during installation (ensuring that the working angle of the camera device can cover the monitoring area, ensuring that the camera device records the entire trajectory of the object's movement, and ensuring that the camera data is complete and clear).
[0058] Step S20: performing moving target detection based on the image data to be detected to obtain a moving target detection result;
[0059] It should be noted that in the specific implementation, there are many types of target objects to be detected included in the image data to be detected, such as flying birds, leaves, and objects thrown from high altitudes. Therefore, in order to ensure that the system can accurately determine the behavior of throwing objects from high altitudes, it is necessary to identify and lock the target objects to be detected, and then make subsequent judgments based on their motion trajectory.
[0060] It can be understood that in the specific implementation, the moving target detection is performed based on the image data to be detected, and its purpose is to lock the moving target (the high-altitude object itself or interfering targets such as flying birds) in the high-altitude object throwing judgment process through the image data to be detected, and the operation finally identifies the locked object and its related image data as the moving target detection result.
[0061] Step S30: determining the high-altitude object dropping behavior based on the image data to be detected and the moving target detection result to obtain the high-altitude object dropping determination result;
[0062] It should be noted that, in the specific implementation, the process of determining the behavior of dropping objects from a high altitude is generally divided into two steps: first, the moving target is identified and locked based on the image data to be detected, and then the motion trajectory of the moving target is identified and determined based on the image data to be detected and the moving target detection result, and finally the result of determining the behavior of dropping objects from a high altitude is obtained.
[0063] Step S40: If the result of the high-altitude object dropping determination is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored and an alarm is issued.
[0064] It should be noted that, in the specific implementation, the results of the high-altitude object dropping judgment include two situations: yes and no. If the high-altitude object dropping judgment result is yes, then the "moving target" identified and judged this time is the high-altitude object dropping; if the high-altitude object dropping judgment result is no, then the "moving target" identified and judged this time is not the high-altitude object dropping (it may be naturally falling leaves or flying birds, etc.).
[0065] It should also be noted that in the specific implementation, if the result of the high-altitude object dropping judgment is yes, the image data to be detected and the high-altitude object dropping judgment result will be integrated and stored and an alarm will be issued, wherein the integrated storage is the image data (image data to be detected) and the judgment and analysis results recorded in this judgment process; the alarm operation is to report the high-altitude object dropping behavior (such as sound and light alarm or SMS notification).
[0066] This embodiment acquires image data to be detected; performs moving target detection based on the image data to be detected to obtain a moving target detection result; performs high-altitude object dropping behavior determination based on the image data to be detected and the moving target detection result to obtain a high-altitude object dropping determination result; if the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored and an alarm is issued. This embodiment obtains corresponding detection results by detecting and analyzing the image data to be detected, and then performs high-altitude object dropping behavior determination based on the relevant data and the detection results, thereby achieving effective detection of high-altitude object dropping behavior and reducing the false alarm rate of detection.
[0067] refer to Figure 3 , Figure 3 The figure is a flow chart of a second embodiment of a method for detecting objects thrown from a high altitude according to the present invention.
[0068] Based on the above first embodiment, in this embodiment, step S20 specifically includes:
[0069] Step S21: performing data preprocessing on the image data to be detected to obtain processed image data;
[0070] It should be noted that, in the specific implementation, in order to improve the overall judgment accuracy of the system, it is necessary to perform data preprocessing on the image data to be detected, wherein the data preprocessing operation specifically includes, first accessing the continuous video / picture data to be detected, then performing image grayscale processing on all the video frames / picture data to be detected (to reduce the system operation complexity and retain the main target motion information), and finally performing Gaussian blur on the converted video frame / picture data (to reduce noise interference and smooth the image) to obtain the processed image data.
[0071] It should also be noted that in the specific implementation, the specific principle of the Gaussian blur operation is:
[0072]
[0073] Where σ is the standard deviation of the control blur level.
[0074] Step S22: performing background modeling based on the processed image data to obtain a moving target recognition result;
[0075] It is understandable that, in a specific implementation, the main purpose of the background modeling operation is to extract static background information from the video sequence, thereby achieving separation of dynamic foreground objects. This is conducive to further analysis and processing of video content, such as motion detection, scene understanding, and event detection (such as intrusion detection and traffic monitoring).
[0076] It should also be noted that, in this embodiment, the background modeling operation is implemented based on a Gaussian mixture model (GMM), which is used to extract the background information of the current scene and regularly update the background model to adapt to changes in illumination or dynamic changes in the environment. A Gaussian mixture model (GMM) is a probability distribution model that can dynamically assign multiple Gaussian distributions to each pixel to describe the background and foreground respectively (the background distribution usually occupies a higher weight, and the foreground distribution corresponds to a distribution with a lower weight), wherein the formula for dynamically updating the background model is:
[0077] μ t =(1-α)μ t-1 +αx t
[0078] σ t 2 =(1-α)σ t-1 2 +α(x t -μ t ) 2
[0079] Among them, μ t and σ t 2 are the mean and variance of the current pixel distribution, α is the learning rate, x t is the current pixel value.
[0080] Step S23: performing moving target detection on the processed image data based on the moving target recognition result to obtain a moving target detection result.
[0081] It should be noted that in the specific implementation, the processed image data is subjected to moving target detection based on the moving target recognition result, and its purpose is to detect and identify the moving target, which specifically includes first extracting the foreground target from the video frame, then reducing the isolated noise points and enhancing the integrity of the target area through morphological operations (such as dilation and erosion), and finally using the connected domain analysis algorithm to extract the bounding box of the foreground target to lock the moving target. The role of the morphological operation (dilation and erosion operation) is to remove noise points and enhance the connectivity of the target area (erosion operation removes pixels at the edge of the target and shrinks the target area; dilation operation fills the gaps in the target area and expands the target area).
[0082] This embodiment first performs data preprocessing on the image data to be detected, then performs background modeling based on the processed image data, and finally performs moving target detection on the processed image data based on the obtained moving target recognition result to obtain the moving target detection result, thereby realizing the detection and recognition of the moving target, and further providing a basis for the subsequent determination of the motion trajectory of the moving target.
[0083] Furthermore, data preprocessing is performed on the image data to be detected to obtain processed image data, which specifically includes: performing image conversion based on the image data to be detected to obtain converted image data; performing image processing on the converted image data to obtain processed image data.
[0084] refer to Figure 4 , Figure 4 The figure is a flow chart of a third embodiment of a method for detecting objects thrown from a high altitude according to the present invention.
[0085] Based on the above first embodiment, in this embodiment, step S30 specifically includes:
[0086] Step S31: Predicting the moving target trajectory based on the image data to be detected and the moving target detection result to obtain a moving target trajectory prediction result;
[0087] It should be noted that in the specific implementation, the trajectory prediction of the moving target is based on the Kalman filter and the Hungarian algorithm. The Kalman filter uses the historical state (position and speed) of the moving target to predict its position at the next moment, and then updates the state of the moving target in combination with the current detection result. Its recursive process includes the following two steps:
[0088] Prediction equation:
[0089] P k | k-1 =AP k-1 | k-1 A T +Q
[0090] Update equation: Kk =P k | k-1 H T (HP k | k-1 H T +R) -1
[0091]
[0092] Among them, x^ is the target state, P is the covariance matrix, K is the Kalman gain, Q and R are process noise and measurement noise.
[0093] The Hungarian algorithm solves the inter-frame target matching problem by constructing a cost matrix to ensure the uniqueness and consistency of multiple targets.
[0094] Step S32: Determine the behavior of dropping objects from a high altitude based on the motion trajectory prediction result to obtain a determination result of dropping objects from a high altitude.
[0095] It can be understood that in a specific implementation, the purpose of judging the behavior of dropping objects from a high altitude based on the prediction results of the motion trajectory is to analyze whether the moving target meets the characteristics of the behavior of dropping objects from a high altitude according to the trajectory of the moving target (by calculating the speed, acceleration and trajectory curvature of the target, and screening the targets that meet the characteristics of the behavior of dropping objects from a high altitude). The specific judgment process may include trajectory verticality judgment and acceleration change judgment. The trajectory verticality judgment is to first calculate the trajectory direction of the target. If most of the movement directions point to the ground (vertical direction), it can be judged as a high-altitude drop. The acceleration change judgment is to calculate the acceleration of the target during the movement. If its acceleration meets the characteristics of gravity acceleration (close to 9.8m / s 2 ), which further confirms the parabolic behavior.
[0096] This embodiment first predicts the trajectory of the moving target based on the image data to be detected and the moving target detection results, and then determines the high-altitude throwing behavior based on the obtained motion trajectory prediction results, so as to finally obtain the high-altitude throwing determination results, realize the effective identification of the motion trajectory of the moving target, and then take corresponding processing operations.
[0097] Furthermore, based on the image data to be detected and the moving target detection result, a moving target trajectory prediction is performed to obtain a moving target trajectory prediction result, specifically including: performing instantaneous prediction of the moving target position based on the image data to be detected and the moving target detection result to obtain an instantaneous position prediction result; correcting and updating the instantaneous position prediction result based on the image data to be detected to obtain a corresponding instantaneous trajectory result; integrating all instantaneous trajectory results based on motion timing information to obtain a moving target trajectory prediction result.
[0098] It should be noted that, in a specific implementation, the instantaneous position prediction result refers to the prediction result corresponding to a certain moment of the moving target, and by integrating all the instantaneous position prediction results of the moving target according to the motion sequence, the motion trajectory prediction result can be obtained.
[0099] Furthermore, based on the motion trajectory prediction result, a high-altitude object dropping behavior judgment is performed to obtain a high-altitude object dropping judgment result, specifically including: performing trajectory analysis based on the motion trajectory prediction result to obtain a first high-altitude object dropping judgment result; performing motion feature analysis based on the motion trajectory prediction result to obtain a second high-altitude object dropping judgment result; integrating the first high-altitude object dropping judgment result and the second high-altitude object dropping judgment result to obtain a high-altitude object dropping judgment result.
[0100] It can be understood that in the specific implementation, only when the first high-altitude object throwing determination result and the second high-altitude object throwing determination result are both displayed as yes (when both determine that the motion trajectory is the high-altitude object throwing motion trajectory), the obtained high-altitude object throwing determination result will be displayed as yes, otherwise it will be no.
[0101] Furthermore, before acquiring the image data to be detected, it also includes: starting the high-altitude object throwing detection system; configuring the system parameters of the high-altitude object throwing detection system after starting based on the parameter adjustment instruction, and obtaining the high-altitude object throwing detection system after the parameters are adjusted.
[0102] It should be noted that, in the specific implementation, the high-altitude object throwing detection system mainly includes video acquisition equipment and detection algorithm modules. Before normal operation (before obtaining the image data to be detected), in order to ensure the collection of valid image data, it is necessary to adjust the corresponding system parameters according to work requirements, including the adjustment of the camera viewing angle, the adjustment of the background modeling update rate, the adjustment of the motion target tracking parameters and the adjustment of the motion behavior judgment threshold.
[0103] In addition, an embodiment of the present invention also proposes a computer-readable storage medium storing a computer program, wherein a high-altitude object dropping detection program is stored on the storage medium. When the high-altitude object dropping detection program is executed by a processor, the steps of the high-altitude object dropping detection method described above are implemented.
[0104] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.
[0105] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the high-altitude object detection device of the present invention.
[0106] like Figure 5 As shown, the high-altitude object detection device proposed in the embodiment of the present invention includes:
[0107] Image acquisition module 10: acquires image data to be detected;
[0108] Target detection module 20: performs moving target detection based on the image data to be detected, and obtains a moving target detection result;
[0109] Behavior judgment module 30: performs high-altitude object throwing behavior judgment based on the image data to be detected and the moving target detection result, and obtains the high-altitude object throwing judgment result;
[0110] Determination execution module 40: If the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored and an alarm is issued.
[0111] This embodiment first obtains the image data to be detected; performs moving target detection based on the image data to be detected to obtain a moving target detection result; performs a high-altitude object dropping behavior judgment based on the image data to be detected and the moving target detection result to obtain a high-altitude object dropping judgment result; if the high-altitude object dropping judgment result is yes, the image data to be detected and the high-altitude object dropping judgment result are integrated and stored and an alarm is issued. This embodiment obtains the corresponding detection result by detecting and analyzing the image data to be detected, and then judges the high-altitude object dropping behavior based on the relevant data and the detection result, thereby achieving effective detection of high-altitude object dropping behavior and reducing the false alarm rate of detection.
[0112] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.
[0113] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.
[0114] In addition, for technical details that are not described in detail in this embodiment, please refer to the high-altitude object detection method provided in any embodiment of the present invention, and will not be repeated here.
[0115] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0116] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0118] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for detecting objects thrown from a high altitude, characterized in that: include: Acquire image data to be detected; Performing moving target detection based on the image data to be detected to obtain a moving target detection result; Performing high-altitude object throwing behavior determination based on the image data to be detected and the moving target detection result to obtain a high-altitude object throwing determination result; If the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored, and an alarm is issued.
2. The method for detecting objects thrown from a height according to claim 1, characterized in that: Performing moving target detection based on the image data to be detected to obtain a moving target detection result specifically includes: Performing data preprocessing on the image data to be detected to obtain processed image data; Perform background modeling based on the processed image data to obtain a moving target recognition result; Based on the moving target recognition result, moving target detection is performed on the processed image data to obtain a moving target detection result.
3. The method for detecting objects thrown from a high altitude according to claim 2, characterized in that: Performing data preprocessing on the image data to be detected to obtain processed image data specifically includes: Performing image conversion based on the image data to be detected to obtain converted image data; The converted image data is subjected to image processing to obtain the processed image data.
4. The method for detecting objects thrown from a high altitude according to claim 1, characterized in that: The high-altitude object dropping behavior is determined based on the image data to be detected and the moving target detection result, and the high-altitude object dropping determination result is obtained, specifically including: Predicting the trajectory of a moving target based on the image data to be detected and the moving target detection result to obtain a moving target trajectory prediction result; The high-altitude object throwing behavior is judged based on the motion trajectory prediction result to obtain the high-altitude object throwing judgment result.
5. The method for detecting objects thrown from a height according to claim 4, characterized in that: The moving target trajectory is predicted based on the image data to be detected and the moving target detection result to obtain the moving target trajectory prediction result, which specifically includes: Based on the image data to be detected and the moving target detection result, instantaneous prediction is performed on the position of the moving target to obtain an instantaneous position prediction result; Correcting and updating the instantaneous position prediction result based on the image data to be detected to obtain a corresponding instantaneous trajectory result; All instantaneous trajectory results are integrated based on the motion timing information to obtain the motion trajectory prediction result.
6. The method for detecting objects thrown from a height according to claim 4, characterized in that: Based on the motion trajectory prediction result, the high-altitude object throwing behavior is judged to obtain the high-altitude object throwing judgment result, which specifically includes: Perform trajectory analysis based on the motion trajectory prediction result to obtain a first high-altitude projectile determination result; Performing motion feature analysis based on the motion trajectory prediction result to obtain a second high-altitude thrown object determination result; The first high-altitude object dropping determination result and the second high-altitude object dropping determination result are integrated to obtain the high-altitude object dropping determination result.
7. The method for detecting objects thrown from a height according to any one of claims 1 to 6, characterized in that: Before obtaining the image data to be detected, it also includes: Start the high-altitude object throwing detection system; Based on the parameter adjustment instruction, the system parameters of the high-altitude object dropping detection system are configured after startup to obtain the high-altitude object dropping detection system after parameter adjustment.
8. A device for detecting objects thrown from a high altitude, characterized in that: The high-altitude object throwing detection device comprises: Image acquisition module: obtains the image data to be detected; Target detection module: performs moving target detection based on the image data to be detected to obtain a moving target detection result; Behavior judgment module: based on the image data to be detected and the moving target detection result, the behavior judgment of high-altitude throwing is performed to obtain the high-altitude throwing judgment result; Determination execution module: if the high-altitude object dropping determination result is yes, the image data to be detected and the high-altitude object dropping determination result are integrated and stored and an alarm is issued.
9. A device for detecting objects thrown from a high altitude, characterized in that: The high-altitude object dropping detection device includes: a memory, a processor, and a high-altitude object dropping detection program stored in the memory and executable on the processor, wherein the high-altitude object dropping detection program is configured to implement the high-altitude object dropping detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the method for detecting objects thrown from a high altitude as described in any one of claims 1 to 7 can be implemented.