A target monitoring method and system based on defense zone segmentation
By adopting the zone segmentation method in regional security products, the initial judgment of target positions and secondary judgment of video images is solved, and the problems of real-time capture and video linkage recognition of mobile targets in the existing technology are achieved, and large-scale three-dimensional monitoring is achieved, which is improved. Monitoring effect of security system.
Patent Information
- Application Number
- CN202210461043.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-28
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2042-04-28
AI Technical Summary
Existing regional security products have poor results in real-time capture, video linkage and target recognition of mobile targets, and are difficult to meet the monitoring needs of large-scale areas in the face.
The target monitoring method based on zone segmentation is adopted, and the position information of suspected targets is obtained for the initial judgment, the prevention and control areas are divided into multiple monitoring units, the video preset position is determined, the video surveillance perspective is adjusted, the target image information is extracted for secondary judgment. , determine the real target based on the results of the initial and secondary judgment.
It has achieved three-dimensional and seamless monitoring on a large scale and wide scale, meets the needs of regional security applications, improves the accuracy of real-time capture and video linkage of mobile targets, and enhances the target recognition capabilities.
Smart Images

Figure CN115002341B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of intelligent security technology, and more specifically, relates to a target monitoring method and system based on defense zone segmentation. Background Art
[0002] With the continuous development of intelligent security products, existing security products have transitioned from traditional single means to multi-dimensional linkage methods, and gradually developed into a multi-dimensional technology joint monitoring mode that combines active detection with video surveillance. At present, most mainstream security products such as infrared beamforming, vibration optical fiber, and leakage cable are combined with video surveillance technology to assist in confirming illegal intrusion targets. With the continuous change of security needs, it is particularly important to develop regional surface security products based on existing perimeter security products, especially for unmanned protection areas. It can effectively cover the entire defense area. Once the target enters the defense area, it can be discovered and tracked in time regardless of whether it passes through the boundary area smoothly. The rapid development of technologies such as artificial intelligence, the Internet of Things, and image recognition has promoted the continuous improvement of security technology and application innovation, thus deriving the integrated application of multi-dimensional detection sensor equipment and video surveillance technology.
[0003] At present, many security products have integrated video surveillance technology, most of which use fixed gun-type guarding mode, deploying a device at a certain distance, which can effectively meet the application needs of perimeter defense zone and realize image capture of targets crossing the perimeter. However, for large-scale surface areas without strict perimeter areas, it is difficult to achieve real-time target tracking and image acquisition. Obviously, traditional perimeter-type technical defense means are difficult to meet application needs; at the same time, with the change of users' technical defense application mode, the whole process tracking and monitoring of intrusion targets has gradually become the current main application mode, and the video image acquisition method has also changed from the original fixed type to a 360° all-round monitoring method without blind spots. However, the existing regional technical defense means are not ideal, mainly focusing on the problems in real-time capture of mobile targets, video linkage, and target recognition.
[0004] Therefore, it is expected to invent a target monitoring method that can effectively solve the problems existing in the prior art in real-time capture of mobile targets, video linkage, and target recognition. Summary of the invention
[0005] The purpose of the present invention is to propose a target monitoring method based on defense zone segmentation to solve the problems existing in the prior art in real-time capture of mobile targets, video linkage, and target identification.
[0006] In order to achieve the above object, the present invention provides a target monitoring method based on defense zone segmentation, comprising:
[0007] Step 1: Obtain the location information of the suspected target in the control area and make an initial judgment on the location information;
[0008] Step 2: Divide the control area into multiple monitoring units, and determine the video preset position corresponding to the suspected target based on each monitoring unit;
[0009] Step 3: Based on the video preset position corresponding to the suspected target, adjust the video surveillance viewing angle to the video preset position corresponding to the suspected target, and obtain a video image of the suspected target;
[0010] Step 4: Extract the target image information of the suspected target from the video image, and perform a secondary judgment on the target image information. If the secondary judgment result exceeds a preset value and the initial judgment result meets a preset rule, the suspected target is a real target.
[0011] Optionally, step 1 includes:
[0012] Obtaining location information of the suspected target in the control area;
[0013] Based on the location information of the suspected target, it is determined whether the trajectory information and signal strength of the suspected target meet the preset rules. If so, the suspected target is a quasi-real target.
[0014] Optionally, the step 2 includes:
[0015] Divide the control area into a plurality of monitoring units and assign corresponding attribute information to each monitoring unit, wherein the attribute information includes an ID, an area size, and an area location;
[0016] For each of the monitoring units, determining a corresponding video preset position based on the attribute information thereof;
[0017] The monitoring unit where the suspected target is located is determined by comparing the position information with the attribute information, and then based on the video preset position corresponding to the monitoring unit, the video preset position corresponding to the suspected target is determined.
[0018] Optionally, step 4 includes:
[0019] Performing frame extraction processing on the video image and extracting target image information corresponding to each frame;
[0020] Target discrimination is performed on the target image information corresponding to each frame by voting. If the number of votes for the suspected target exceeds the preset value and the initial judgment result meets the preset rule, the suspected target is a real target.
[0021] Optionally, it also includes:
[0022] Storing the location information and the video image;
[0023] as well as,
[0024] The video image is displayed and when the suspected target is the real target, an alarm message is pushed.
[0025] A target monitoring system based on defense zone segmentation includes:
[0026] Radar equipment is used to obtain the location information of suspected targets in the control area and make an initial judgment on the location information;
[0027] A linkage control unit, the linkage control unit is connected to the radar device and the video surveillance device respectively, and is used to divide the control area into a plurality of monitoring units, and determine the video preset position corresponding to the suspected target based on each of the monitoring units;
[0028] The video monitoring device is used to adjust the video monitoring viewing angle to the video preset position corresponding to the suspected target based on the video preset position corresponding to the suspected target, and obtain the video image of the suspected target;
[0029] An intelligent analysis unit, wherein the intelligent analysis unit is respectively connected to the radar device and the video surveillance device, and is used to extract target image information of the suspected target from the video image, and perform a secondary judgment on the target image information. If the secondary judgment result exceeds a preset value and the initial judgment result satisfies a preset rule, the suspected target is a real target.
[0030] Optionally, the radar device includes a position information acquisition module and a first judgment module;
[0031] The location information acquisition module is used to obtain the location information of the suspected target in the control area;
[0032] The first judgment module is used to judge whether the trajectory information and signal strength of the suspected target meet the preset rules based on the location information of the suspected target. If the trajectory information and signal strength of the suspected target meet the preset rules, the suspected target is a quasi-real target.
[0033] Optionally, the linkage control unit includes a monitoring unit division module and a preset position calling module;
[0034] The monitoring unit division module is used to divide the control area into a plurality of monitoring units and assign corresponding attribute information to each monitoring unit, wherein the attribute information includes an ID, an area size, and an area position, and at the same time, for each monitoring unit, determine its corresponding video preset position based on its attribute information;
[0035] The preset position calling module is used to determine the monitoring unit where the suspected target is located by comparing the position information with the attribute information, and then determine the video preset position corresponding to the suspected target based on the video preset position corresponding to the monitoring unit.
[0036] Optionally, the intelligent analysis unit includes an image extraction module and a second judgment module;
[0037] The image extraction module is used to perform frame extraction processing on the video image and extract the target image information corresponding to each frame;
[0038] The second judgment module is used to perform target discrimination on the target image information corresponding to each frame by voting. If the number of votes for the suspected target exceeds the preset value and the initial judgment result meets the preset rule, the suspected target is a real target.
[0039] Optionally, it also includes:
[0040] A data storage module, used for storing the location information and the video image;
[0041] The data display and alarm module is used to display the video image and push alarm information when the suspected target is the real target.
[0042] The beneficial effects of the present invention are:
[0043] The target monitoring method of the present invention first makes an initial judgment on the location information of the suspected target, and then makes a secondary judgment on the target image information of the suspected target, and determines whether the suspected target is a real target through the two judgments. The combined application of the two judgments enables the target monitoring method of the present invention to better meet the current regional security application needs, and to provide video surveillance demand-based target review capabilities for three-dimensional and seamless monitoring defense areas in large-scale and wide-area defense areas, which can effectively solve the problems existing in the prior art in real-time capture of mobile targets, video linkage, and target recognition.
[0044] Other features and advantages of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present invention.
[0046] Figure 1 A flow chart of a target monitoring method based on defense zone segmentation according to an embodiment of the present invention is shown.
[0047] Figure 2 A schematic diagram of defense area division of a target monitoring method based on defense area segmentation according to an embodiment of the present invention is shown.
[0048] Figure 3 A structural diagram of a target monitoring system based on defense zone segmentation according to an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0049] The preferred embodiments of the present invention will be described in more detail below. Although the preferred embodiments of the present invention are described below, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.
[0050] A target monitoring method based on defense zone segmentation according to the present invention includes:
[0051] Step 1: Obtain the location information of suspected targets in the control area and make an initial judgment on the location information;
[0052] Step 2: Divide the control area into multiple monitoring units, and determine the video preset position corresponding to the suspected target based on each monitoring unit;
[0053] Step 3: Based on the video preset position corresponding to the suspected target, adjust the video surveillance viewing angle to the video preset position corresponding to the suspected target, and obtain a video image of the suspected target;
[0054] Step 4: Extract the target image information of the suspected target from the video image, and perform a secondary judgment on the target image information. If the secondary judgment result exceeds the preset value and the initial judgment result meets the preset rules, the suspected target is the real target.
[0055] Specifically, the target monitoring method of the present invention first makes an initial judgment on the location information of the suspected target, and then makes a secondary judgment on the target image information of the suspected target, and determines whether the suspected target is a real target through the two judgments. The combined application of the two judgments enables the target monitoring method of the present invention to better meet the current regional security application needs, and to provide video surveillance demand-based target review capabilities for three-dimensional and seamless monitoring defense areas in large-scale and wide-area defense areas, which can effectively solve the problems existing in the prior art in real-time capture of mobile targets, video linkage, and target recognition.
[0056] Furthermore, the target monitoring method of the present invention can be well adapted to various application scenarios, especially in harsh environments such as border protection, nature reserves, and unmanned areas, and can give full play to its advantages.
[0057] In one example, step 1 includes:
[0058] Obtain the location information of suspected targets within the control area;
[0059] Based on the location information of the suspected target, it is determined whether the trajectory information and signal strength of the suspected target meet the preset rules. If so, the suspected target is a quasi-real target.
[0060] Specifically, by receiving the electromagnetic waves of suspected targets in the prevention and control area, the position information of suspected targets in the prevention and control area is obtained, real-time detection and tracking of suspected targets is realized, a unique ID is given to the suspected targets, and the trajectory information of the suspected targets during movement is recorded. When the position change of the suspected target exceeds a preset distance within a preset time, the suspected target is considered to be a real target, where the preset distance is preferably 3m; at the same time, the significance of the waveform of the reflected wave of the suspected target is judged. In general, the waveforms of people, animals and foreign objects of the same size are relatively fixed, and the authenticity of the suspected target is judged by the reflected wave waveform.
[0061] In one example, step 2 includes:
[0062] Divide the prevention and control area into multiple monitoring units and assign corresponding attribute information to each monitoring unit, including ID, area size and area location;
[0063] For each monitoring unit, determine the corresponding video preset position based on its attribute information;
[0064] The monitoring unit where the suspected target is located is determined by comparing the position information with the attribute information, and then based on the video preset position corresponding to the monitoring unit, the video preset position corresponding to the suspected target is determined.
[0065] In one example, step 4 includes:
[0066] Perform frame extraction on the video image and extract the target image information corresponding to each frame;
[0067] The target image information corresponding to each frame is voted for target identification. If the number of votes for the suspected target exceeds the preset value and the initial judgment result meets the preset rules, the suspected target is the real target.
[0068] Specifically, in practical applications, target identification mainly identifies targets such as people, animals and foreign objects, and in practical applications, video images are framed at a preset frame rate, wherein the frame rate is preferably 10 frames per second.
[0069] In one example, the target monitoring method further includes:
[0070] Storing location information and video images;
[0071] as well as,
[0072] The video image is displayed and an alarm message is pushed when the suspected target is a real target.
[0073] Specifically, the target monitoring method of the present invention is combined with an intelligent analysis algorithm, and optimization and upgrading are performed on the target discrimination mechanism and recognition method, thereby improving the accuracy of the alarm.
[0074] A target monitoring system based on defense zone segmentation includes:
[0075] Radar equipment is used to obtain the location information of suspected targets in the control area and make an initial judgment on the location information;
[0076] A linkage control unit, which is connected to the radar equipment and the video surveillance equipment respectively, and is used to divide the control area into multiple monitoring units, and determine the video preset position corresponding to the suspected target based on each monitoring unit;
[0077] The video monitoring device is used to adjust the video monitoring viewing angle to the video preset position corresponding to the suspected target based on the video preset position corresponding to the suspected target, and obtain the video image of the suspected target;
[0078] The intelligent analysis unit is connected to the radar device and the video surveillance device respectively, and is used to extract the target image information of the suspected target from the video image and perform a secondary judgment on the target image information. If the secondary judgment result exceeds the preset value and the initial judgment result meets the preset rules, the suspected target is a real target.
[0079] Specifically, the target monitoring system of the present invention adopts a combination of radar equipment and video surveillance equipment. The radar equipment serves as an active detection device to effectively monitor suspected targets in the defense zone and obtain the location information of the suspected targets, and initially judge the authenticity of the suspected targets. At the same time, the video surveillance equipment quickly locates the corresponding position according to the location information of the suspected targets provided by the radar equipment, obtains the target image information of the suspected target, and performs a secondary judgment on the authenticity of the target image information. Through the secondary judgment, it better meets the current regional security application needs, and realizes the three-dimensional and seamless monitoring of defense zones in a large range and wide area. Provide video surveillance demand target review capabilities, which can effectively solve the problems existing in the existing technology in real-time capture of mobile targets, video linkage, and target recognition.
[0080] Furthermore, the radar equipment has a detection range of up to 1 kilometer and a coverage angle of 120°, and can obtain the location information of suspected targets in real time. The radar has the characteristics of wide coverage, strong environmental adaptability, and active detection, which can realize the perception and detection of long-distance suspected targets. At the same time, it can drive video surveillance equipment to lock suspected targets in time.
[0081] Furthermore, the video surveillance equipment uses a high-definition intelligent dome camera with 360° all-round video acquisition function, the maximum detection distance is 1km, supports 100 preset position setting capabilities, and has functions such as personnel, animal and foreign object recognition, feature extraction, etc.
[0082] Furthermore, the intelligent analysis unit provides multi-dimensional analysis and computing capabilities for the transmission data of radar equipment and video surveillance equipment. After the radar equipment and video surveillance equipment obtain the location information and image information of the suspected target, they are quickly transmitted to the intelligent analysis service unit through the network, and the transmission data of the radar equipment and video surveillance equipment are processed and analyzed respectively to determine the authenticity of the suspected target.
[0083] In one example, the radar device includes a location information acquisition module and a first judgment module;
[0084] A location information acquisition module is used to obtain the location information of suspected targets in the control area;
[0085] The first judgment module is used to judge whether the trajectory information and signal strength of the suspected target meet the preset rules based on the position information of the suspected target. If the trajectory information and signal strength of the suspected target meet the preset rules, the suspected target is a quasi-real target.
[0086] In one example, the linkage control unit includes a monitoring unit division module and a preset position calling module;
[0087] The monitoring unit division module is used to divide the control area into multiple monitoring units and assign corresponding attribute information to each monitoring unit. The attribute information includes ID, area size and area location. At the same time, for each monitoring unit, the corresponding video preset position is determined based on its attribute information;
[0088] The preset position calling module is used to determine the monitoring unit where the suspected target is located by comparing the position information with the attribute information, and then determine the video preset position corresponding to the suspected target based on the video preset position corresponding to the monitoring unit.
[0089] In one example, the intelligent analysis unit includes an image extraction module and a second judgment module;
[0090] An image extraction module is used to perform frame extraction processing on the video image and extract the target image information corresponding to each frame;
[0091] The second judgment module is used to perform target discrimination on the target image information corresponding to each frame by voting. If the number of votes for the suspected target exceeds a preset value and the initial judgment result meets the preset rules, the suspected target is a real target.
[0092] Specifically, in practical applications, the preset value is preferably half of the total number of votes.
[0093] In one example, the target monitoring system further includes:
[0094] A data storage module, used for storing location information and video images;
[0095] The data display and alarm module is used to display video images and push alarm information when the suspected target is a real target.
[0096] Specifically, video image data is structured data, which takes up a huge amount of storage space and generally requires a storage time of more than 6 months. The data display and alarm module provides a comprehensive display function for multi-dimensional data such as alarm information, suspected target trajectory, alarm video, etc. When a suspected target enters the defense area, the alarm information is pushed immediately, and the video image data at the current moment is retrieved for manual review, so as to timely and effectively detect the intrusion target.
[0097] Example 1
[0098] like Figure 1 As shown, a target monitoring method based on defense zone segmentation includes:
[0099] Step 1: Obtain the location information of suspected targets in the control area and make an initial judgment on the location information;
[0100] Step 2: Divide the control area into multiple monitoring units, and determine the video preset position corresponding to the suspected target based on each monitoring unit;
[0101] Step 3: Based on the video preset position corresponding to the suspected target, adjust the video surveillance viewing angle to the video preset position corresponding to the suspected target, and obtain a video image of the suspected target;
[0102] Step 4: Extract the target image information of the suspected target from the video image, and perform a secondary judgment on the target image information. If the secondary judgment result exceeds the preset value and the initial judgment result meets the preset rules, the suspected target is the real target.
[0103] Wherein, step 1 comprises:
[0104] Obtain the location information of suspected targets within the control area;
[0105] Based on the location information of the suspected target, it is determined whether the trajectory information and signal strength of the suspected target meet the preset rules. If so, the suspected target is a quasi-real target.
[0106] Wherein, step 2 comprises:
[0107] Divide the prevention and control area into multiple monitoring units and assign corresponding attribute information to each monitoring unit, including ID, area size and area location;
[0108] For each monitoring unit, determine the corresponding video preset position based on its attribute information;
[0109] The monitoring unit where the suspected target is located is determined by comparing the position information with the attribute information, and then based on the video preset position corresponding to the monitoring unit, the video preset position corresponding to the suspected target is determined.
[0110] Specifically, Figure 2 As shown, the prevention and control area is divided into multiple monitoring units. Each monitoring unit has an area size and a unique ID, for example, 01 / 02 / 03... When a suspected target appears in the 03 monitoring unit, the video surveillance equipment will immediately adjust to the video preset position corresponding to the 03 monitoring unit, and the image viewing angle will cover the monitoring unit to achieve video linkage.
[0111] Wherein, step 4 comprises:
[0112] Perform frame extraction on the video image and extract the target image information corresponding to each frame;
[0113] The target image information corresponding to each frame is voted for target identification. If the number of votes for the suspected target exceeds the preset value and the initial judgment result meets the preset rules, the suspected target is the real target.
[0114] Among them, the target monitoring method also includes:
[0115] Storing location information and video images;
[0116] as well as,
[0117] The video image is displayed and an alarm message is pushed when the suspected target is a real target.
[0118] Example 2
[0119] like Figure 3 As shown, a target monitoring system based on defense zone segmentation includes:
[0120] Radar equipment is used to obtain the location information of suspected targets in the control area and make an initial judgment on the location information;
[0121] A linkage control unit, which is connected to the radar equipment and the video surveillance equipment respectively, and is used to divide the control area into multiple monitoring units, and determine the video preset position corresponding to the suspected target based on each monitoring unit;
[0122] The video monitoring device is used to adjust the video monitoring viewing angle to the video preset position corresponding to the suspected target based on the video preset position corresponding to the suspected target, and obtain the video image of the suspected target;
[0123] The intelligent analysis unit is connected to the radar device and the video surveillance device respectively, and is used to extract the target image information of the suspected target from the video image and perform a secondary judgment on the target image information. If the secondary judgment result exceeds the preset value and the initial judgment result meets the preset rules, the suspected target is a real target.
[0124] Among them, the radar equipment includes a position information acquisition module and a first judgment module; the position information acquisition module is used to obtain the position information of the suspected target in the control area; the first judgment module is used to judge whether the trajectory information and signal strength of the suspected target meet the preset rules based on the position information of the suspected target. If the trajectory information and signal strength of the suspected target meet the preset rules, the suspected target is a quasi-real target. The linkage control unit includes a monitoring unit division module and a preset position calling module; the monitoring unit division module is used to divide the control area into multiple monitoring units and assign corresponding attribute information to each monitoring unit, the attribute information includes ID, area size and area position, and at the same time, for each monitoring unit, the corresponding video preset position is determined based on its attribute information; the preset position calling module is used to determine the monitoring unit where the suspected target is located by comparing the position information with the attribute information, and then determine the video preset position corresponding to the suspected target based on the video preset position corresponding to the monitoring unit. The intelligent analysis unit includes an image extraction module and a second judgment module; the image extraction module is used to perform frame extraction processing on the video image and extract the target image information corresponding to each frame; the second judgment module is used to perform target discrimination on the target image information corresponding to each frame by voting. If the number of votes for the suspected target exceeds a preset value and the initial judgment result meets the preset rules, the suspected target is a real target.
[0125] The target monitoring system also includes:
[0126] A data storage module, used for storing location information and video images;
[0127] The data display and alarm module is used to display video images and push alarm information when the suspected target is a real target.
[0128] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.
Claims
1. A target monitoring method based on defense zone segmentation, characterized in that: include: Step 1: Obtain the location information of the suspected target in the control area, and make an initial judgment on the location information. Based on the location information of the suspected target, judge whether the trajectory information and signal strength of the suspected target meet the preset rules. If so, the suspected target is a quasi-real target; Specifically, the position information of the suspected target in the control area is obtained by receiving the electromagnetic wave of the suspected target in the control area, so as to realize real-time detection and tracking of the suspected target, give the suspected target a unique ID, and record the trajectory information of the suspected target during movement. When the position change of the suspected target exceeds a preset distance within a preset time, the suspected target is considered to be a quasi-real target, where the preset distance is 3m; at the same time, according to the significance of the waveform of the reflected wave of the suspected target, the authenticity of the suspected target is judged by the waveform; Step 2: Divide the control area into multiple monitoring units, and determine the video preset position corresponding to the suspected target based on each monitoring unit; Specifically, the control area is divided into a plurality of monitoring units and corresponding attribute information is assigned to each monitoring unit, wherein the attribute information includes an ID, an area size, and an area location; For each of the monitoring units, determining a corresponding video preset position based on the attribute information thereof; Determine the monitoring unit where the suspected target is located by comparing the location information with the attribute information, and then determine the video preset position corresponding to the suspected target based on the video preset position corresponding to the monitoring unit; Step 3: Based on the video preset position corresponding to the suspected target, adjust the video surveillance viewing angle to the video preset position corresponding to the suspected target, and obtain a video image of the suspected target; Step 4: Extract the target image information of the suspected target from the video image, and perform a secondary judgment on the target image information. If the secondary judgment result exceeds a preset value and the initial judgment result meets a preset rule, the suspected target is a real target.
2. The target monitoring method based on defense zone segmentation according to claim 1 is characterized in that: The step 4 comprises: Performing frame extraction processing on the video image and extracting target image information corresponding to each frame; Target discrimination is performed on the target image information corresponding to each frame by voting. If the number of votes for the suspected target exceeds the preset value and the initial judgment result meets the preset rule, the suspected target is a real target.
3. The target monitoring method based on defense zone segmentation according to claim 1 is characterized in that: Also includes: Storing the location information and the video image; as well as, The video image is displayed and when the suspected target is the real target, an alarm message is pushed.
4. A target monitoring system based on defense zone segmentation, characterized in that: include: Radar equipment, used to obtain the location information of suspected targets in the control area and make an initial judgment on the location information; The radar device includes a position information acquisition module and a first judgment module; The location information acquisition module is used to obtain the location information of the suspected target in the control area; The first judgment module is used to judge whether the trajectory information and signal strength of the suspected target meet the preset rules based on the position information of the suspected target, and if the trajectory information and signal strength of the suspected target meet the preset rules, the suspected target is a quasi-real target; By receiving the electromagnetic waves of the suspected target in the control area, the position information of the suspected target in the control area is obtained, and the real-time detection and tracking of the suspected target is realized, and the suspected target is given a unique ID, and the trajectory information of the suspected target during the movement is recorded. When the position change of the suspected target exceeds the preset distance within the preset time, the suspected target is considered to be a quasi-real target, where the preset distance is 3m; at the same time, according to the significance of the waveform of the suspected target reflection wave, the authenticity of the suspected target is judged by the waveform; A linkage control unit, the linkage control unit is connected to the radar device and the video surveillance device respectively, and is used to divide the control area into a plurality of monitoring units, and determine the video preset position corresponding to the suspected target based on each of the monitoring units; The linkage control unit includes a monitoring unit division module and a preset position calling module; The monitoring unit division module is used to divide the control area into a plurality of monitoring units and assign corresponding attribute information to each monitoring unit, wherein the attribute information includes an ID, an area size, and an area position, and at the same time, for each monitoring unit, determine its corresponding video preset position based on its attribute information; The preset position calling module is used to determine the monitoring unit where the suspected target is located by comparing the position information with the attribute information, and then determine the video preset position corresponding to the suspected target based on the video preset position corresponding to the monitoring unit; The video monitoring device is used to adjust the video monitoring viewing angle to the video preset position corresponding to the suspected target based on the video preset position corresponding to the suspected target, and obtain the video image of the suspected target; An intelligent analysis unit, wherein the intelligent analysis unit is respectively connected to the radar device and the video surveillance device, and is used to extract target image information of the suspected target from the video image, and perform a secondary judgment on the target image information. If the secondary judgment result exceeds a preset value and the initial judgment result satisfies a preset rule, the suspected target is a real target.
5. The target monitoring system based on defense zone segmentation according to claim 4 is characterized in that: The intelligent analysis unit includes an image extraction module and a second judgment module; The image extraction module is used to perform frame extraction processing on the video image and extract the target image information corresponding to each frame; The second judgment module is used to perform target discrimination on the target image information corresponding to each frame by voting. If the number of votes for the suspected target exceeds the preset value and the initial judgment result meets the preset rule, the suspected target is a real target.
6. The target monitoring system based on defense zone segmentation according to claim 4 is characterized in that: Also includes: A data storage module, used for storing the location information and the video image; The data display and alarm module is used to display the video image and push alarm information when the suspected target is the real target.
Citation Information
Patent Citations
Full-automatic anti-intrusion intelligent video monitoring alarm system for unattended villa
CN101609588A
Image storage method and device, and image retrieval method and device
CN105260412A
Method for detecting airport foreign object debris based on monitoring video of dome camera
CN105611244A
Behavior analysis method and system
CN107871111A
Intelligent visual perception system
CN111770266A
