Intelligent law enforcement evidence obtaining method and system based on comprehensive information integration

Abstract

The invention provides an intelligent law enforcement evidence obtaining method and system based on comprehensive information integration, and relates to the technical field of data processing, and the method comprises the steps: synchronously obtaining the original data of a photoelectric evidence obtaining device, a navigation radar, a ship automatic recognition system and a unification device through a multi-source data collection interface, and protocol analysis and standardization processing are carried out to form a unified structured data stream. Space-time fusion of the radar track and the AIS information is realized based on the data stream, a fusion target object is generated, and a dynamic situation target set is constructed; utilizing the abnormal behavior model to automatically identify suspicious behaviors and outputting an alarm; identifying a target type and a board number in combination with the photoelectric video stream, and updating or newly adding a ship file; meanwhile, a photoelectric guiding instruction is generated through azimuth calculation, and automatic target tracking and video collection are achieved; and finally, performing time correlation and integration on the multi-source data, generating a law enforcement evidence chain and automatically outputting an evidence obtaining report. The efficiency of the law enforcement evidence obtaining process can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to an intelligent law enforcement evidence collection method and system based on comprehensive information integration. Background Technology

[0002] Currently, during the execution of law enforcement and evidence collection missions by coast guard vessels, the maritime situation around the vessels is complex. The target information data obtained through equipment such as Automatic Identification System (AIS) and radar is large in volume and relatively scattered. There is a lack of comprehensive, multi-angle, and multi-type evidence acquisition methods, as well as a lack of real-time back-end evidence processing methods. During the investigation and evidence collection process, it is not convenient to make rapid command and decision-making, which increases the difficulty and cost of subsequent law enforcement.

[0003] Currently, relying on manual methods to analyze and identify abnormal behavior is quite challenging. There is a lack of effective technical means to define rules for abnormal behavior and to provide early warnings. Operators cannot quickly analyze and assess suspicious behavior, making it difficult to adapt to increasingly complex and demanding maritime law enforcement tasks. Therefore, it is crucial to develop a set of law enforcement evidence collection equipment suitable for coast guard vessels, capable of working in conjunction with other equipment in the integrated law enforcement system to meet the investigation and evidence collection needs of the coast guard's daily patrols, surveillance, and duty operations.

[0004] Therefore, an automated method is needed to improve the efficiency of the law enforcement evidence collection process. Summary of the Invention

[0005] This invention provides an intelligent law enforcement evidence collection method and system based on comprehensive information integration, which can improve the efficiency of the law enforcement evidence collection process.

[0006] In a first aspect, the present invention provides an intelligent law enforcement evidence collection method based on comprehensive information integration, the method comprising: The system synchronously acquires raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through a multi-source data acquisition interface, and performs protocol parsing and standardization processing on the raw data to form a unified structured data stream. Based on the unified structured data stream, the navigation radar track information and the ship automatic identification system information are spatially correlated and time-synchronized. Based on the target position parameters, heading parameters and identification marks, a fused target object is generated, and a dynamic situational target set is established. The dynamic situation target set is used to identify abnormal behaviors based on a preset abnormal behavior model, and abnormal behavior alarm information is output. The target execution type and hull number in the photoelectric video stream corresponding to the fused target object are identified to generate a target identification result. The target identification result is then matched with the ship database to update or add target file information. Based on the azimuth parameters of the locked target, an optoelectronic guidance command is generated and sent to the optoelectronic evidence collection device through the data processing module. The optoelectronic evidence collection device is then controlled to perform target tracking and video acquisition, and the video stream is returned in real time for display and identification analysis. The navigation radar information, the automatic identification system information, photoelectric video data, the target recognition results, and the abnormal behavior alarm information are correlated and integrated over time to generate a law enforcement evidence chain record, and an evidence collection report that can be played back and exported is output according to the evidence template.

[0007] Based on the above technical solutions, preferably, the step of spatially associating and temporally synchronizing navigation radar track information and automatic identification system information according to the unified structured data stream, generating fused target objects based on target position parameters, heading parameters, and identification markers, and establishing a dynamic situational target set specifically includes: A unified time reference is established through the system management module, and time alignment is performed on the structured data from the navigation radar and the automatic identification system of ships, so as to achieve time consistency of multi-source data by using standardized timestamps as indexes. The coordinate transformation module converts the polar coordinate data of the navigation radar into latitude and longitude coordinates in the geographic coordinate system, and performs spatial coordinate projection on the data output by the Automatic Identification System of Ships to unify it into the global geographic reference system. In the fusion algorithm module, the target position parameters, the heading parameters, the speed parameters and the identification mark are used as matching conditions. Multidimensional matching calculation is performed based on the sliding time window and the spatial neighborhood threshold. The identification mark verification and uniqueness verification are performed on the target set whose time difference and spatial distance are both lower than the preset threshold. The successfully matched radar targets are fused with the targets of the Automatic Identification System (AIS) to generate a fused target object, and dynamic status updates are performed by combining the heading change rate and track continuity parameters. A candidate cache pool is established for unmatched targets and maintained using a time threshold mechanism. When a candidate target has complete data within a preset time window, the fusion update is automatically performed. All fused target objects are stored in the dynamic situation target cache using a dynamic hash table structure, recording real-time position, speed, heading, and update timestamp information. Targets that have not been updated are automatically removed according to an expiration cleanup policy to ensure the real-time performance and continuity of the dynamic situation target set.

[0008] Based on the above technical solutions, preferably, the step of identifying abnormal behaviors based on a preset abnormal behavior model of the dynamic situation target set and outputting abnormal behavior alarm information specifically includes: An abnormal behavior model set is pre-established in the abnormal behavior analysis module, which includes a jurisdictional sea area model, a temporary warning zone model, a fishing ban zone model, and a target approach model. The spatial boundary of the abnormal behavior model set is formed by the user marking it on the electronic nautical chart layer and stored in the early warning model management library. After receiving the dynamic situation target set, the timestamp, latitude and longitude coordinates, heading parameters and speed parameters of the fused target object are used as input data. The model matching operation is used to determine whether the target has entered the spatial boundary defined by the model or violated the behavior rules. When the fusion target object is detected to have entered an unauthorized jurisdictional sea area, temporary maritime warning zone or fishing ban zone, or when the spatial distance between any two targets is less than the proximity threshold, the corresponding abnormal behavior model is triggered and abnormal behavior alarm information is generated. The abnormal behavior alarm information, including alarm type, time, target unique identifier and track information, is written into the alarm data cache area, and the alarm results are synchronized to the integrated situation interface through the message push mechanism. The abnormal target is highlighted and displayed on the electronic nautical chart. The client maintains an exception list and an exception refresh time field. When the target does not receive new exception data within a set time threshold, the highlighting status is automatically canceled and the exception is removed from the exception list.

[0009] Based on the above technical solutions, preferably, the step of identifying the target execution type and hull number in the photoelectric video stream corresponding to the fused target object, generating a target identification result, and matching the target identification result with the ship database to update or add target file information specifically includes: The photoelectric evidence collection device is controlled by servo control commands to collect video streams of the target area, and the video streams of the target area are pushed to the target recognition module using streaming media services; The target recognition module listens to the streaming address and performs frame-by-frame segmentation and image preprocessing on the received video frames. It inputs the framed images into the trained multi-layer convolutional neural network model for type recognition and outputs the category label and confidence result of the ship target in each frame image. The identified target area is enhanced with character features and optical character recognition. The target hull number is extracted and the hull number recognition confidence is calculated. A target recognition result containing target type, hull number and confidence information is generated. The target recognition result is pushed to the law enforcement evidence collection command equipment software in real time through the user data packet protocol and is displayed on the comprehensive situation interface in the form of video overlay annotation. The system calls the ship database interface and uses the hull number information as the key field for matching. When the corresponding ship file information exists in the database, the system updates the latest identification time and video sample in the ship file. When the corresponding information does not exist in the database, the system automatically generates a new ship file entry and writes the basic information, image sample and confidence data of the identification result into it.

[0010] Based on the above technical solutions, preferably, the step of generating photoelectric guidance commands according to the azimuth parameters of the locked target, sending them to the photoelectric evidence collection device through the data processing module, controlling the photoelectric evidence collection device to perform target tracking and video acquisition, and returning the video stream in real time for display and identification analysis, specifically includes: The system receives the lock command from law enforcement personnel on the fused target object in the integrated situation interface, extracts the bearing parameters, distance parameters and heading parameters of the fused target object, and calculates the target relative bearing angle and target elevation angle in combination with the ship's navigation data; The data processing module generates a photoelectric guidance instruction package based on the calculation results. The photoelectric guidance instruction package includes a servo control field, an azimuth parameter field, a pitch parameter field, a focus adjustment field, and a video channel control field. The photoelectric guidance instruction packet is sent to the control interface of the photoelectric evidence collection device via the User Datagram Protocol. After parsing the instruction, the photoelectric evidence collection device drives the servo execution unit to adjust the gimbal attitude according to the azimuth and pitch angle parameters, so that the optical axis is aligned with the target direction, and automatically adjusts the zoom ratio and focus depth according to the distance parameters to ensure image clarity. When the photoelectric forensics equipment enters the target tracking mode, it calculates the target displacement vector and scale change based on feature matching between consecutive video frames, and corrects the servo control commands in real time to maintain the optical axis tracking of the target. When the target experiences changes in angular velocity or occlusion, a prediction compensation algorithm is triggered to calculate the target's position based on the target's motion trajectory parameters from the previous moment in order to achieve continuous tracking. While the photoelectric evidence collection device performs target tracking, it collects target video streams in real time and pushes them to the front-end interface of the law enforcement evidence collection command device through a streaming media service, with timestamps and device status identification fields attached, thus forming a closed-loop photoelectric guidance process from target locking, orientation calculation, guidance command generation, device control to video transmission and identification analysis.

[0011] Based on the above technical solutions, preferably, the step of temporally correlating and integrating the navigation radar information, the automatic identification system information, photoelectric video data, the target recognition results, and the abnormal behavior alarm information to generate a law enforcement evidence chain record, and outputting a replayable and exportable evidence collection report based on the evidence template, specifically includes: The evidence chain generation module obtains navigation radar information with timestamp and source identifier fields, automatic identification system information, photoelectric video data, target recognition results and abnormal behavior alarm information from the data fusion module, abnormal behavior analysis module, target recognition module and photoelectric guidance module, respectively. Time standardization processing is performed based on the standard time provided by the time synchronization device, and the timestamps of various data are uniformly converted into Coordinated Universal Time format and a time series index table is established according to the chronological order. Based on the identification field of the fused target object, logical mapping and cross-comparison are performed on the multi-source data to associate the information of the same target in different modules and form a target data association table; Spatial matching is performed using the spatial position parameters and heading parameters of navigation radar information and automatic identification system information as key fields to generate a fused track sequence; Frame-level synchronization is performed by matching the frame timestamp of the optoelectronic video data with the unique identifier of the target in the target recognition result, thereby establishing the correspondence between video frames and recognition results. Based on the alarm time of abnormal behavior alarm information and the trajectory and video segments associated with the target identification location, a mapping relationship between behavioral events and video evidence is generated; Each associated result is encapsulated into an evidence chain data package with timestamp as the primary index and target unique identifier as the secondary index. The evidence chain data package includes track dataset, photoelectric video index file, identification result file and alarm record; The evidence chain generation module performs formatted export of the evidence chain data package based on the preset evidence template, and automatically generates an evidence report document containing evidence collection time, target information, track changes, identified images, descriptions of abnormal behavior, and video index content.

[0012] Based on the above technical solutions, preferably, the step of synchronously acquiring raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through a multi-source data acquisition interface, and performing protocol parsing and standardization processing on the raw data to form a unified structured data stream, specifically includes: Configure the configuration information and protocol message format of the photoelectric evidence collection device, the navigation radar, the automatic identification system for ships, and the timing device in the system management module respectively; Establish data communication channels with each device according to the configuration information, and receive real-time raw data output by the photoelectric evidence collection device, the navigation radar, the automatic identification system for ships, and the timing device in a periodic sampling manner; The original data is processed by message structure recognition and field mapping. The target track information output by the navigation radar is converted into a standardized data structure containing target bearing parameters, distance parameters, speed parameters and heading parameters. The static and dynamic information output by the automatic identification system is parsed into a unified field format. The time information output by the time synchronization device is synchronously updated to the system standard time format. The video data output by the photoelectric evidence collection device is used to generate corresponding video stream description data. The message transmission protocol performs unified encapsulation, field validation, and timestamp indexing on various parsed data to form a structured data stream with consistent structure and uniform format.

[0013] In a second aspect, the present invention provides an intelligent law enforcement evidence collection system based on comprehensive information integration. The system is used to execute an intelligent law enforcement evidence collection method based on comprehensive information integration as described above. The system includes an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to synchronously acquire raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through a multi-source data acquisition interface, and to perform protocol parsing and standardization processing on the raw data to form a unified structured data stream. The processing module is used to perform spatial correlation and temporal synchronization processing on navigation radar track information and automatic identification system information based on the unified structured data stream, generate fused target objects based on target position parameters, heading parameters and identification marks, and establish a dynamic situational target set. The processing module is used to identify abnormal behaviors of the dynamic situation target set based on a preset abnormal behavior model and output abnormal behavior alarm information. The processing module is used to identify the target execution type and hull number in the photoelectric video stream corresponding to the fused target object, generate a target identification result, and match the target identification result with the ship database to update or add target file information. The processing module is used to generate photoelectric guidance commands based on the azimuth parameters of the locked target, send them to the photoelectric evidence collection device through the data processing module, control the photoelectric evidence collection device to perform target tracking and video acquisition, and return the video stream in real time for display and identification analysis; The output module is used to perform time correlation and integration of the navigation radar information, the ship automatic identification system information, photoelectric video data, the target recognition result and the abnormal behavior alarm information, generate law enforcement evidence chain record, and output a playback and exportable evidence collection report based on the evidence template.

[0014] In a third aspect of the invention, an electronic device is provided, including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any of the preceding embodiments.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions that, when executed, perform the method as described in any of the preceding claims.

[0016] In summary, one or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: 1. This invention automates and enables real-time processing of the entire law enforcement evidence collection process, from target detection, identification, and tracking to evidence chain generation, by constructing a multi-source information fusion and intelligent analysis workflow. Through unified collection, standardized processing, and time synchronization of data from photoelectric evidence collection equipment, navigation radar, automatic identification systems for ships, and time synchronization equipment, the system can quickly establish a dynamic situational target set and automatically identify suspicious targets based on abnormal behavior models, achieving behavioral early warning. Combined with photoelectric guidance command generation and intelligent target recognition, it improves the accuracy of target tracking and image evidence collection. Simultaneously, it generates a complete law enforcement evidence chain through the time correlation of multi-source data and automatically outputs evidence collection reports, thereby significantly reducing manual intervention, shortening data analysis and evidence processing time, and improving the efficiency and accuracy of law enforcement decision-making and evidence collection.

[0017] 2. Time synchronization and spatial fusion of information from navigation radar and the Automatic Identification System (AIS) for ships were achieved, realizing a unified spatiotemporal reference for heterogeneous sensor data. This enabled the formation of a continuous and accurate fused target object set in a dynamic environment. The problem of time drift and spatial deviation between radar tracks and AIS messages was resolved, allowing the system to perceive the target's track status and movement trends in real time, thus improving the accuracy and stability of target identification and situational awareness.

[0018] 3. An anomalous behavior model set was established, encompassing jurisdictional waters, temporary warning zones, fishing ban zones, and target proximity models, enabling multi-dimensional anomaly detection based on spatial regions and behavioral characteristics. It can automatically identify anomalous behaviors such as illegal intrusion, boundary crossings, or proximity risks, generating alarm information and highlighting it in real-time on electronic nautical charts. This achieves intelligent identification and dynamic early warning of anomalous target behavior, significantly reducing the burden of manual analysis and improving law enforcement response efficiency and risk management capabilities.

[0019] 4. By combining optoelectronic video streams with target recognition algorithms, convolutional neural networks and optical character recognition models are used to automatically identify target types and hull numbers, and match them with a ship database to achieve automatic updates or additions to ship files. This realizes the intelligent conversion of optoelectronic video data into structured target information, reduces manual comparison steps, ensures the accuracy of target identification and the integrity of data management, thereby improving the efficiency and reliability of optoelectronic forensics in evidence collection and information archiving.

[0020] 5. Based on the target's azimuth parameters, photoelectric guidance commands are generated. Combined with servo control and predictive compensation algorithms, automatic target tracking and continuous video acquisition are achieved. A closed-loop control chain is established from target locking and angle calculation to automatic guidance of the photoelectric equipment. This enables the photoelectric equipment to maintain stable tracking and clear imaging even when the target is moving or obstructed, thereby ensuring the continuity of the evidence collection process and the integrity of video evidence. This effectively improves the automation and accuracy of evidence collection in dynamic maritime scenarios. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating an intelligent law enforcement evidence collection method based on comprehensive information integration disclosed in an embodiment of the present invention. Figure 2 This is a functional framework diagram of a law enforcement evidence collection command device disclosed in an embodiment of this application; Figure 3 This is an architecture diagram of a law enforcement evidence collection command equipment software disclosed in an embodiment of this application; Figure 4 This is a schematic diagram of a module of an intelligent law enforcement evidence collection system based on comprehensive information integration disclosed in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention.

[0022] Explanation of reference numerals in the attached drawings: 401, acquisition module; 402, processing module; 403, output module; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. Detailed Implementation

[0023] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0024] In the description of the embodiments of the present invention, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0025] In the description of the embodiments of the present invention, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0026] Currently, when coast guard vessels are carrying out law enforcement and evidence collection missions, they face the challenges of complex maritime situations and large, dispersed target data. Relying on equipment such as automatic identification systems and radar makes it difficult to achieve multi-dimensional evidence fusion and real-time analysis. This results in a lack of automated abnormal behavior identification and early warning mechanisms in the evidence collection process, leading to low command and decision-making efficiency and a heavy burden of manual analysis. It is difficult to adapt to the high-intensity, multi-task law enforcement needs. Therefore, there is an urgent need to build a coast guard vessel law enforcement and evidence collection equipment with multi-source information fusion, intelligent identification, and automatic early warning functions to improve evidence collection efficiency and the level of intelligence in the law enforcement process.

[0027] This embodiment discloses an intelligent law enforcement evidence collection method based on comprehensive information integration, referring to... Figure 1 This includes the following steps S110-S160: S110 synchronously acquires raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through multi-source data acquisition interfaces, and performs protocol parsing and standardization processing on the raw data to form a unified structured data stream.

[0028] In one possible implementation, this application discloses a law enforcement evidence collection command device. This device connects to photoelectric evidence collection, navigation radar, and AIS devices via an integrated network. It collects data on targets entering the sensing area and performs intelligent analysis of the collected data based on AI technology. Through abnormal behavior analysis algorithms, it automatically analyzes and identifies abnormal target behavior and issues alerts for suspicious targets. Simultaneously, through target recognition algorithms, it identifies the type and hull number of suspicious targets, assisting the operator in commanding and making evidence collection decisions. The device collects and integrates trajectory data, image data, video data, abnormal behavior analysis data, and target recognition result data for the same law enforcement target to form a complete chain of law enforcement evidence.

[0029] The law enforcement evidence collection command equipment integrates advanced image recognition algorithms, enabling it to identify target vessel types and extract information such as hull numbers. Based on this information, it matches it with a database, querying the target vessel's basic information in the built-in vessel database and comparing it with the target's static AIS information. This allows it to determine if the target vessel has engaged in any abnormal behavior, such as AIS information tampering, providing operators with accurate and reliable decision-making support. This improves the intelligence level of the law enforcement system and the efficiency of law enforcement evidence collection. It also enhances the comprehensive combat capabilities of the operational service system and effectively improves the efficiency of maritime law enforcement and rights protection.

[0030] The law enforcement evidence collection command equipment connects to an integrated network to acquire information from photoelectric evidence collection, timing equipment, navigation radar, AIS, integrated command, and integrated navigation devices, and collects data on targets entering the detection area. Due to space constraints on the law enforcement equipment's control console, the command telephone control panel is pre-installed on the law enforcement evidence collection command equipment.

[0031] The law enforcement evidence collection command equipment can use data fusion services to process target track information detected by navigation radar and target information reported by AIS equipment to form law enforcement evidence collection targets.

[0032] During a ship's voyage, optoelectronic equipment is guided to acquire visual information about suspicious vessels or vessels of interest. Each vessel within the field of view of these equipment is a pre-defined target for identification. The identification algorithm supports the recognition of various target types, including passenger ships, container ships, cargo ships, speedboats, and buoys. AI technology is used to intelligently analyze the collected data. Anomaly behavior analysis algorithms automatically analyze and identify abnormal target behavior, issuing alerts for suspicious targets. Simultaneously, target recognition algorithms identify the type and hull number of suspicious targets, assisting commanders in decision-making and evidence collection. The system allows for displaying and modifying target identification results and supports manually adding other target field information.

[0033] Collect and integrate the trajectory data, picture data, video data, abnormal behavior analysis data, and target recognition result data of the same law enforcement target to form a complete law enforcement evidence chain record. Provide the function of exporting the evidence chain record to provide data basis for the operator's auxiliary law enforcement decision-making. Refer to Figure 2 , the devices related to the function interface of the law enforcement evidence collection and command device mainly include: integrated navigation system, law enforcement device console, optoelectronic evidence collection, navigation radar, time synchronization device, integrated command system, and voice communication terminal. The function interface of the law enforcement evidence collection and command device includes a network interface.

[0034] As the core control and data fusion center of the maritime law enforcement evidence collection system, the function framework of the law enforcement evidence collection and command device consists of four parts: data collection layer, processing and analysis layer, instruction interaction layer, and communication interface layer, realizing the comprehensive access, intelligent processing, device control, and information distribution of multi-source information. First, in the data collection layer, the law enforcement evidence collection and command device establishes multi-channel data communication connections with navigation radar, integrated navigation system, optoelectronic devices, time synchronization devices, and voice communication terminals. The navigation radar sends the target track information in real time through the standard communication interface to represent the spatial distribution and dynamic changes of maritime targets; the integrated navigation system outputs AIS information, attitude information, and position information to provide geographic coordinates and motion parameter support for target recognition and situation analysis; the optoelectronic devices transmit the optoelectronic video image data in real time to provide visual evidence-taking images; the time synchronization device outputs the standard time signal to stamp a unified time stamp on all data in the system to ensure time synchronization; the voice communication terminal transmits the telephone information through the data link to record the voice dispatching and instruction confirmation.

[0035] Secondly, in the processing and analysis layer, the law enforcement evidence collection and command device performs protocol parsing, data cleaning, and standardization processing on the received multi-source information to form a unified structured data stream. The system performs time alignment and spatial coordinate mapping on the data from different devices according to the time synchronization benchmark, generates fused target objects, and establishes a dynamic situation target set. The fused data is input into the abnormal behavior analysis module and the target recognition module to realize the real-time analysis of the target behavior pattern, track anomaly, and optoelectronic image recognition result, and generate abnormal behavior alarm information and target recognition result.

[0036] In the instruction interaction layer, the law enforcement evidence collection and command device, as the instruction center, receives the target guidance information from the integrated command system, and calculates and generates the optoelectronic guidance instruction according to the target azimuth, distance, and heading. The guidance instruction is encoded by the data processing module and sent to the optoelectronic device control interface to control the servo system to perform target tracking and video collection. The device returns the status feedback information to the integrated command system during operation so that the operator can grasp the working status of the optoelectronic device and the target locking situation in real time. At the same time, the system can feedback the target guidance result to the law enforcement device console to ensure the联动一致 of each subsystem.

[0037] At the communication interface layer, the law enforcement evidence collection and command equipment undertakes the interaction and relay of various data and instructions. The equipment communicates with external modules through a message bus protocol to achieve low-latency transmission and asynchronous scheduling of information; it maintains the real-time and continuity of multi-source data through multi-threaded communication channels with timing modules, optoelectronic devices, integrated navigation systems, and radar modules; and it achieves bidirectional interaction with the integrated command system and voice communication terminals through standardized interfaces, realizing a closed-loop process from situational data perception, target guidance, video transmission to voice communication recording.

[0038] In summary, the law enforcement evidence collection command equipment serves three functions within the system architecture: a multi-source information fusion center, an intelligent analysis core, and a control and dispatch hub. Through the collaboration of modules such as radar, AIS, photoelectric sensors, and time synchronization, it achieves full-process automation from target detection, identification, tracking, and anomaly warning to evidence chain generation, providing efficient evidence collection support and decision-making basis driven by data fusion for coast guard law enforcement.

[0039] In one possible implementation, this application discloses law enforcement evidence collection command equipment software, which is based on platform services and refers to... Figure 3 It adopts a four-layer architecture consisting of an access layer, a data service layer, a data storage layer, and an application layer. This provides auxiliary decision-making for law enforcement activities by maritime vessels and meets the needs of law enforcement evidence collection.

[0040] This software adopts a front-end and back-end separation architecture, supporting both JAR package deployment and container deployment. This architecture clearly defines system responsibilities, improving development efficiency and maintainability. The front-end focuses on user interface and experience, while the back-end handles business logic and data processing. They interact via a RESTful API, facilitating parallel development and independent deployment. The system software supports multiple deployment methods to handle different application scenarios. JAR package deployment has a low barrier to entry and facilitates rapid iteration. Container deployment improves environment isolation, provides resource management, batch deployment, and rolling updates, and performs more stably in production environments with complex network and file systems, while also being easier to maintain.

[0041] The application layer, belonging to the system's user operation layer, mainly includes the comprehensive situational awareness and system management modules. Utilizing these two modules, the system discovers and identifies suspicious targets through situational processing, target recognition, and abnormal behavior analysis, forming a complete chain of evidence to assist users in law enforcement evidence collection and command decision-making. All data logic operations and user request processing are implemented using technologies such as Spring Boot 2.x, MyBatis-Plus, and WebSocket. The data storage layer provides system data storage and query functions. It is responsible for storing data collected by the perception layer, software configuration data, evidence-gathering video data, and legal and regulatory documents. Relational databases, time-series databases, and file databases are used for system data access. The data service layer is the core business processing layer of the system. This layer is divided into two modules: a data processing module and an algorithm service module. It implements protocol data acquisition, parsing, storage, and data analysis processing. Using a self-developed data processing module, it supports parsing MQTT, HTTP, UDP, and other protocol messages; and uses target recognition, data fusion, and behavior analysis algorithms to analyze and process data from the data processing module. The access layer is the foundation for the system's interaction with the external environment. By collecting data from various sensors, it provides necessary data support to upper-layer modules. It can access sensor device data using multiple communication protocols such as MQTT, HTTP, and UDP.

[0042] The primary application scenario for the law enforcement evidence collection command equipment software is the investigation and evidence collection work in the daily law enforcement activities of coast guard vessels. First, the data fusion service processes AIS data and navigation radar target data to form a situational target profile. Based on the acquired fused data, the behavior analysis module performs real-time calculation and analysis on the navigation data of the situational targets, filtering and identifying suspicious targets and issuing real-time alerts. It then guides optoelectronic equipment to track the filtered suspicious targets, continuously acquiring video data of the targets. Simultaneously, using target detection technology, it detects targets in the video and labels their type and hull number. Finally, it links data with the ship database to query target details.

[0043] After completing the above evidence collection process, the radar detection information, AIS information, ship trajectory information, photoelectric evidence video, abnormal alarm data and other data of suspicious targets generated in the above multiple stages are recorded to form a complete chain of evidence.

[0044] In one possible implementation, raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system (AIS), and timing equipment are synchronously acquired through a multi-source data acquisition interface. The raw data undergoes protocol parsing and standardization to form a unified structured data stream. Specifically, this includes: configuring the configuration information and protocol message formats of the photoelectric evidence collection equipment, navigation radar, AIS, and timing equipment in the system management module; establishing data communication channels with each device based on the configuration information, and receiving real-time raw data output by the photoelectric evidence collection equipment, navigation radar, AIS, and timing equipment through periodic sampling; performing message structure recognition and field mapping processing on the raw data, converting the target track information output by the navigation radar into a standardized data structure containing target bearing parameters, distance parameters, speed parameters, and heading parameters; parsing the static and dynamic information output by the AIS into a unified field format; synchronously updating the time information output by the timing equipment to the system's standard time format; and generating corresponding video stream description data from the video data output by the photoelectric evidence collection equipment; and performing unified encapsulation, field verification, and timestamp indexing on various parsed data through a message transmission protocol to form a structured data stream with consistent structure and unified format.

[0045] Specifically, when configuring the configuration information and protocol message formats of photoelectric evidence collection equipment, navigation radar, automatic identification system (AIS), and time synchronization equipment in the system management module, the system management module first establishes a unified device registry structure. Each device corresponds to a unique device identifier, device type field, communication protocol field, data message format field, and connection parameter field. The device type field identifies the type of device, such as "photoelectric evidence collection equipment," "navigation radar," "automatic identification system," and "time synchronization equipment." The communication protocol field indicates the type of communication protocol used by the device, such as User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), or Message Queuing Telemetry Transmitter (MQTT). The data message format field describes the structure definition of the device's output data in detail, including the message header, data payload, and checksum field. The connection parameter field contains the device's network address, communication port number, and authentication parameters, which are used by the system to automatically establish a secure communication connection during runtime. The system management module loads this configuration table during the runtime phase to achieve unified management and dynamic calling of communication parameters for all devices, thereby providing a standardized communication interface and parsing template for subsequent multi-source data acquisition processes.

[0046] Based on the configuration information, data communication channels are established with each device. When receiving real-time raw data from photoelectric evidence collection equipment, navigation radar, automatic identification systems (AIS), and timing devices using a periodic sampling method, the system's data acquisition module starts an independent acquisition thread for each device according to the device registry content and establishes a data communication channel with the device through a protocol adapter. For devices using the UDP protocol, the acquisition module receives data packets by listening on a specified port; for devices using the MQTT protocol, the acquisition module receives data pushed by the device by subscribing to a specific topic; for devices using the HTTP protocol, the acquisition module periodically sends data request messages to the device and parses the response content. The periodic sampling method means that the acquisition module performs cyclic data reception operations according to the sampling period defined in the configuration file to ensure that the time interval for data updates from each device is fixed and continuous. When receiving real-time raw data, the system also appends a timestamp field to ensure time alignment consistency of subsequent multi-source data.

[0047] When performing message structure identification and field mapping on the raw data, the parsing module first identifies the message structure based on the protocol message format fields corresponding to the device, dividing the data packet into a message header, payload, and checksum. The message header information is used to verify the device identity and data integrity, while the payload contains target parameters, time parameters, or video stream segment data. The parsing module uses a field mapping table to perform a matching operation on the payload fields, mapping device-specific field names to system-wide common field names. For data output by navigation radar, the parsing module extracts target azimuth parameters, distance parameters, speed parameters, and heading parameters, and converts them into standardized data structures to represent the spatial position and motion state of the radar target; the azimuth parameter represents the angular position of the target relative to the radar antenna, the distance parameter represents the distance between the target and the radar device, the speed parameter represents the target's moving speed, and the heading parameter represents the target's moving direction angle. For data output by the Automatic Identification System (AIS), the parsing module parses the static and dynamic information. Static information includes fixed attributes such as ship name, call sign, and MMSI code, while dynamic information includes attributes that change over time, such as latitude and longitude coordinates, heading, speed, and time stamps. For data output from time synchronization devices, the parsing module extracts the time field, converts the raw time value into Coordinated Universal Time (UTC) format, and uses it as the system standard time to ensure a unified time base for all collected data. For video data output from optoelectronic forensics devices, the parsing module extracts video stream metadata, including frame rate, resolution, encoding format, and video channel number, and generates a corresponding video stream description data file for subsequent streaming media push and recognition module calls.

[0048] When performing unified encapsulation, field validation, and timestamp indexing on various parsed data using message transmission protocols, the data processing module first performs integrity and field consistency checks on the parsing results to ensure that all data conforms to the system's internal JSON format definition. The unified encapsulation process involves encapsulating data from different devices into data packets with a unified field structure according to internal data specifications. These packets include device type, data content, timestamp, checksum, and source identifier fields. Field validation verifies whether the message data has been truncated or corrupted using validation algorithms. Timestamp indexing writes the time value under a unified time base to each record, enabling the system to sort and merge data chronologically. The encapsulated data is distributed via message transmission protocols, using MQTT for asynchronous multi-topic transmission or an HTTP interface for business modules to call. Ultimately, the system generates a structured data stream with a consistent structure and unified format, providing a standardized and traceable data foundation for subsequent multi-source information fusion, abnormal behavior analysis, and evidence chain construction.

[0049] S120 performs spatial correlation and temporal synchronization processing on navigation radar track information and automatic identification system information based on unified structured data stream, generates fused target objects based on target position parameters, heading parameters and identification marks, and establishes a dynamic situational target set.

[0050] In one possible implementation, spatial correlation and temporal synchronization processing are performed on navigation radar track information and Automatic Identification System (AIS) information based on a unified structured data stream. A fused target object is generated based on target position parameters, heading parameters, and identification markers, and a dynamic situational target set is established. Specifically, this includes: establishing a unified time synchronization reference through a system management module; performing time alignment operations on structured data from navigation radar and AIS; and achieving time consistency of multi-source data using standardized timestamps as indexes. A coordinate transformation module converts navigation radar polar coordinate data to latitude and longitude coordinates in a geographic coordinate system and performs spatial coordinate projection on the data output by AIS to unify it to a global geographic reference system. In the fusion algorithm module, target position parameters, heading parameters, speed parameters, and... Using identification tags as matching criteria, multi-dimensional matching calculations are performed based on a sliding time window and spatial neighborhood thresholds. For target sets where both the time difference and spatial distance are below the preset thresholds, identification tag verification and uniqueness verification are performed. Successfully matched radar targets are fused with targets from the Automatic Identification System (AIS) to generate fused target objects, and dynamic status updates are performed in conjunction with heading change rate and track continuity parameters. A candidate cache pool is established for unmatched targets and maintained using a time threshold mechanism. When candidate targets have complete data within the preset time window, fusion updates are automatically performed. All fused target objects are stored in the dynamic situation target cache using a dynamic hash table structure, recording real-time position, speed, heading, and update timestamp information. Targets without updates are automatically removed according to an expiration cleanup strategy to ensure the real-time nature and continuity of the dynamic situation target set.

[0051] Specifically, the system management module first establishes a unified time synchronization benchmark. This benchmark is based on the Coordinated Universal Time (UTC) signal provided by the time synchronization equipment for global time synchronization, ensuring that data from navigation radar and the Automatic Identification System (AIS) are compared and fused under a unified time benchmark. This time synchronization mechanism uses a standardized timestamp as a unique index field. When receiving data from navigation radar and AIS, the system adds a standardized timestamp field to each data record. Time alignment is performed by calculating the time difference between timestamps from different data sources. If the time difference exceeds a preset threshold, the data processing module performs linear interpolation correction to achieve time consistency across multiple data sources.

[0052] When converting navigation radar polar coordinate data to latitude and longitude coordinates in the geographic coordinate system via the coordinate transformation module, the system employs a geographic projection algorithm to unify the polar and geographic coordinate systems. The raw data output by the navigation radar is based on distance and azimuth. The coordinate transformation module uses the latitude and longitude of the radar equipment installation point and its azimuth reference to convert the polar coordinates to geographic coordinates. The corresponding longitude and latitude offsets are calculated using the arctangent function, achieving precise positioning of the target point in the geographic coordinate system. For data output by the Automatic Identification System (AIS), since its raw data is latitude and longitude coordinates, the system only needs to uniformly map it to the global geographic reference system via the spatial coordinate projection module to ensure consistency with the spatial position of the radar target. This step ensures that the position information of all targets is subsequently compared and fused under a unified coordinate system, thereby avoiding spatial deviations caused by inconsistent coordinate references.

[0053] In the fusion algorithm module, target position parameters, heading parameters, speed parameters, and identification markers are used as matching conditions. The system employs a joint judgment mechanism of sliding time windows and spatial neighborhood thresholds to achieve multi-dimensional matching calculations. The sliding time window limits the time range of data matching to ensure that the time difference between records from different data sources does not exceed the system's allowed time difference threshold. The spatial neighborhood threshold constrains the spatial distance range of the target. The system calculates the geographical distance between radar targets and targets in the Automatic Identification System (AIS). When the distance is less than the threshold and the heading difference is less than the angle threshold, the two are determined to be potential matches for the same target. The fusion algorithm compares the identification markers of the candidate target set, performing uniqueness verification using a unique identification marker field (e.g., MMSI code). If a match is successful, the target correspondence is determined; otherwise, the target is entered into the candidate cache pool for subsequent updates.

[0054] Successfully matched radar targets and targets from the Automatic Identification System (AIS) are fused to generate a fused target object. The fusion module calculates a weighted average based on the position information, speed parameters, and heading parameters of both targets as the fusion result, and further calculates the heading change rate and track continuity parameters. The heading change rate reflects the stability of the target's motion direction, while the track continuity parameter determines whether the target's trajectory is continuous. When the track continuity deviation exceeds a threshold, the system automatically triggers a relocation mechanism. The dynamic state of the fused target object is updated in real time with each new data input to ensure continuous perception and accuracy of the target's motion characteristics.

[0055] For unmatched targets, the system establishes a candidate cache pool structure, which is maintained using a time threshold mechanism. Candidate targets are stored in the cache for a fixed time period. If new track data or identification data is received within the time window and successfully matches the target, the system immediately performs a fusion update; if no matching data is found by the end of the time window, the candidate target is automatically removed from the cache pool. This mechanism ensures the continuity of target tracking even under short-term communication delays or data loss, while preventing long-term invalid data from occupying storage space.

[0056] All fused target objects are stored in a dynamic situational target cache using a dynamic hash table structure. This hash table uses a unique target identifier as the key, and each target key includes a real-time position field, a speed field, a heading field, and an update timestamp field. The system has an expiration cleanup policy; when a target has not updated its data within a set time period, the record is automatically removed. The situational processing module periodically reads the hash table content and pushes it to the front-end integrated situational interface to achieve real-time visualization and situational updates of target vessels. This design ensures the real-time nature and data integrity of the dynamic situational target set, enabling law enforcement command personnel to continuously observe target track changes and status updates on the electronic chart interface, achieving real-time situational awareness through multi-source information fusion.

[0057] S130 identifies abnormal behaviors in the dynamic situation target set based on a preset abnormal behavior model and outputs abnormal behavior alarm information.

[0058] In one possible implementation, the dynamic situation target set is used to identify abnormal behaviors based on a preset abnormal behavior model, and abnormal behavior alarm information is output. Specifically, this includes: pre-establishing an abnormal behavior model set in the abnormal behavior analysis module, which includes a jurisdictional sea area model, a temporary warning zone model, a fishing ban zone model, and a target approach model. The spatial boundary of the abnormal behavior model set is marked by the user on the electronic nautical chart layer and stored in the early warning model management library; after receiving the dynamic situation target set, using the timestamp, latitude and longitude coordinates, heading parameters, and speed parameters of the fused target object as input data, the model matching operation is used to determine whether the target has entered the spatial boundary defined by the model or violated the behavior. The rules are as follows: when a target object is detected to have entered an unauthorized jurisdictional waters, temporary maritime warning zone, or fishing ban zone, or when the spatial distance between any two targets is less than the proximity threshold, the corresponding abnormal behavior model is triggered, and abnormal behavior alarm information is generated. The abnormal behavior alarm information, including alarm type, time, target unique identifier, and track information, is written to the alarm data cache, and the alarm results are synchronized to the integrated situation interface through a message push mechanism. Abnormal targets are highlighted and displayed on the electronic nautical chart. An abnormal list and an abnormal refresh time field are maintained on the client. When a target does not receive new abnormal data within a set time threshold, the highlighting status is automatically canceled and it is removed from the abnormal list.

[0059] Specifically, during the system initialization phase, the abnormal behavior analysis module first establishes a set of abnormal behavior models, including models of jurisdictional sea areas, temporary warning zones, fishing ban zones, and target approach models. Each model consists of spatial boundary definition data and behavior judgment parameters. The spatial boundary is drawn by the user using annotation tools on the electronic nautical chart layer. The annotation content includes the coordinates of the region vertices, the boundary closure method, and the region type label, forming a polygonal spatial range. After annotation is completed, the system saves the spatial boundary and model parameters together to the early warning model management library. The early warning model management library is an independent database table structure used to maintain the activation status, parameter configuration, threshold conditions, and corresponding algorithm service binding information of the early warning models, ensuring that each abnormal behavior model can be dynamically loaded or deactivated during operation.

[0060] After receiving a dynamic set of targets, the abnormal behavior analysis module uses the timestamp, latitude and longitude coordinates, heading parameters, and speed parameters of the target objects as input to trigger a model matching operation. The model matching operation compares the target's geographical location with the spatial boundary of the warning model to determine spatial constraints, specifically whether the target's latitude and longitude fall within the polygonal area of ​​the model boundary. If the target is located inside the model boundary, it is considered to have entered the spatial range defined by the model. Simultaneously, the system performs dynamic behavior judgment on the heading and speed parameters to determine if the target exhibits abnormal heading deviation or overspeed behavior. When the target's rate of change of heading exceeds a threshold or its speed exceeds the upper limit set by the model, the system marks it as a target with abnormal behavior. This process achieves dual anomaly identification based on spatial location and dynamic characteristics, ensuring the accuracy and timeliness of anomaly detection.

[0061] When the system detects that a target object has entered an unauthorized jurisdictional waters, temporary warning zone, or fishing ban area, or when the spatial distance between any two targets is below a proximity threshold, the corresponding abnormal behavior model is triggered. This proximity threshold is a distance parameter configured in the system's early warning model management library, used to determine whether two targets are too close. After triggering the model, the system generates an abnormal behavior alarm message, including the alarm type (e.g., jurisdictional intrusion, illegal operation, target approach), alarm time, target's unique identifier, target's current trajectory information, and behavior description. The abnormal behavior recognition algorithm runs in a multi-threaded manner, ensuring real-time parallel detection of multiple targets.

[0062] After an abnormal behavior alarm is generated, the system writes it to the alarm data cache, which uses a Redis cache structure for storage, with the target's unique identifier as the key and the alarm content as key-value pairs. The message push module synchronizes the alarm results to the comprehensive situational awareness interface through a publish-subscribe mechanism, highlighting abnormal targets on the electronic nautical chart. Different types of alarms are distinguished by different colors; for example, red indicates illegal intrusion, yellow indicates approaching the warning zone, and orange indicates approaching other targets. Users can view detailed alarm records on the warning information interface, including alarm time, duration, and target movement trajectory.

[0063] On the client side, an anomaly list and an anomaly refresh time field are maintained. The anomaly list stores target information currently in an alarm state, and the anomaly refresh time field records the latest update time for each alarm. When the system does not receive new anomaly data for a target within a set time threshold period, the client automatically performs an alarm status clearing operation, cancels the target's highlighted status, and removes the record from the anomaly list. This refresh mechanism prevents expired alarms from being continuously displayed, ensuring the real-time accuracy of the content displayed on the situational awareness interface. Users can also manually disable alarms; the system will record the disabling time and archive it in the alarm history database, realizing a complete cycle of anomaly detection, alarm issuance, and status maintenance, thereby supporting multi-model real-time early warning and dynamic risk perception in maritime law enforcement scenarios.

[0064] S140 will integrate the target execution type and hull number recognition from the photoelectric video stream corresponding to the target object to generate a target recognition result, and match the target recognition result with the ship database to update or add target file information.

[0065] In one possible implementation, the target execution type and hull number recognition in the fused photoelectric video stream corresponding to the target object are used to generate a target recognition result. This result is then matched with a ship database to update or add target profile information. Specifically, this includes: controlling the photoelectric evidence collection device to acquire the target area video stream via servo control commands, and pushing the target area video stream to the target recognition module using a streaming media service; the target recognition module listens to the push address and performs frame-by-frame segmentation and image preprocessing on the received video frames, inputting the segmented images into a trained multi-layer convolutional neural network model for type recognition, and outputting the category label and confidence result of the ship target in each frame; and then... The system performs character feature enhancement and optical character recognition on the identified target area, extracts the target hull number, calculates the hull number recognition confidence level, and generates a target recognition result containing target type, hull number, and confidence level information. The target recognition result is pushed to the law enforcement evidence collection command equipment software in real time via the User Datagram Protocol and is simultaneously displayed on the integrated situation interface in a video overlay annotation manner. The system calls the ship database interface to match the hull number information as a key field. When the corresponding ship file information exists in the database, the system updates the latest recognition time and video sample in the ship file. When the corresponding information does not exist in the database, the system automatically generates a new ship file entry and writes the basic information, image sample, and confidence level data of the recognition result.

[0066] Specifically, servo control commands are generated by the photoelectric guidance module and sent to the photoelectric forensics equipment. These commands include azimuth, pitch, zoom ratio, and video channel control parameters, used to control the gimbal attitude and lens focal length of the photoelectric forensics equipment, thereby accurately locking onto the target area. Upon receiving the servo control commands, the photoelectric forensics equipment starts the video acquisition program and continuously captures images of the designated target area, generating a real-time video stream. This video stream contains multi-channel compressed encoded data, which is encapsulated and pushed via a streaming media service. After receiving the video output from the photoelectric forensics equipment, the streaming media service encapsulates the data stream using the RTSP or WebRTC protocol and registers the push address with the system's media directory service, enabling the target recognition module to subscribe to this push address and achieve dynamic access to multi-source video.

[0067] The target recognition module monitors the streaming media address and receives video frame data in real time through a subscription mechanism. It performs frame segmentation and image preprocessing on each video frame. Frame segmentation involves breaking down continuous video stream data into independent static image frames for subsequent frame-by-frame analysis by the deep learning model. Image preprocessing includes noise suppression, brightness normalization, edge enhancement, and scaling to ensure that the images input to the model maintain consistency in brightness, contrast, and size. The preprocessed image frames are then input into a trained multi-layer convolutional neural network model for feature extraction and type classification. The convolutional neural network model consists of multiple convolutional layers, pooling layers, and fully connected layers, automatically extracting local and global structural features from the image to identify different types of ship targets. The model outputs the target category label for each frame, such as passenger ship, cargo ship, speedboat, fishing boat, buoy, etc., along with its corresponding confidence value. The confidence value represents the reliability of the model's judgment and ranges from 0 to 1.

[0068] The identified target area is further enhanced with character feature enhancement and optical character recognition (OCR). Character feature enhancement employs morphological filtering and edge sharpening algorithms to highlight the texture features of the hull number character area in the image, reducing interference from sea surface reflections and wave textures. Subsequently, the OCR algorithm extracts the hull number character information from the target image. The OCR algorithm uses a convolutional recurrent network to predict the sequence of character images, outputting the hull number text string and calculating the hull number recognition confidence score. The system merges the ship type, hull number, and the two confidence scores to generate a target recognition result data packet. The recognition module pushes this result to the law enforcement evidence collection command equipment software in real time via the User Datagram Protocol (UDP) to ensure data transmission with minimal latency. After receiving the recognition result, the law enforcement evidence collection command equipment presents the identified target area and corresponding hull number information in a video overlay annotation format on the comprehensive situational interface. The hull number label and confidence score percentage are displayed in real time on the video frame to support law enforcement personnel in intuitively confirming the validity of the recognition result.

[0069] The ship database interface maintains real-time interaction with the identification module in the system background, with the hull number information as the sole key field. Upon receiving the target identification result, the system first queries the ship database using the hull number field. If a matching record exists, the latest identification time field and the corresponding video sample field of the ship's file are updated. This update operation is handled by a database transaction control mechanism to prevent multi-threaded write conflicts. If the corresponding hull number information does not exist in the database, the system automatically creates a new record in the ship file table and writes the ship's basic attributes, including hull number, type, initial identification time, identification confidence level, video sample path, and target screenshot. This new entry is also registered in the database index table for rapid retrieval during subsequent matching. The system supports subsequent manual confirmation and supplementation of newly added ship file information. Law enforcement personnel can view identification history records, correct hull number identification errors, or upload supplementary images through the file management interface, thereby ensuring data consistency and traceability between the database and the actual evidence collection results. Ultimately, this identification process achieves fully automated closed-loop linkage between photoelectric evidence collection equipment, streaming media services, the target identification module, and the ship database, ensuring that the target identification results are synchronous, reliable, and valid evidence across spatial, temporal, and identity dimensions.

[0070] S150 generates photoelectric guidance commands based on the azimuth parameters of the locked target, sends them to the photoelectric evidence collection equipment through the data processing module, controls the photoelectric evidence collection equipment to perform target tracking and video acquisition, and returns the video stream in real time for display and identification analysis.

[0071] In one possible implementation, an electro-optical guidance command is generated based on the azimuth parameters of the locked target. This command is then sent to the electro-optical evidence collection equipment via a data processing module. The equipment is then controlled to perform target tracking and video acquisition, and a real-time video stream is returned for display and analysis. Specifically, this includes: receiving the lock command from law enforcement personnel on the fused target object in the integrated situational awareness interface; extracting the azimuth, distance, and heading parameters of the fused target object; and calculating the target's relative azimuth and altitude angles based on the ship's navigation data. The data processing module generates an electro-optical guidance command packet based on the calculation results. This packet includes servo control fields, azimuth parameter fields, pitch angle parameter fields, focus adjustment fields, and video channel control fields. The electro-optical guidance command packet is then sent to the control interface of the electro-optical evidence collection equipment via a User Datagram Protocol (UDP). The equipment parses the command and drives the servo execution unit. The gimbal attitude is adjusted based on azimuth and pitch parameters to align the optical axis with the target direction. The zoom magnification and depth of focus are automatically adjusted based on distance parameters to ensure image clarity. When the photoelectric evidence collection equipment enters target tracking mode, the target displacement vector and scale change are calculated based on feature matching between consecutive video frames. Servo control commands are corrected in real time to maintain the optical axis tracking the target. In the event of changes in the target's angular velocity or occlusion, a prediction compensation algorithm is triggered to calculate the target's position based on the target's motion trajectory parameters from the previous moment to achieve continuous tracking. While the photoelectric evidence collection equipment is performing target tracking, the target video stream is acquired in real time and pushed to the front-end interface of the law enforcement evidence collection command equipment via streaming media service, with timestamp and device status identification fields. This forms a closed-loop photoelectric guidance process from target locking, azimuth calculation, guidance command generation, equipment control to video transmission and identification analysis.

[0072] Specifically, the integrated situational awareness interface serves as the front-end operating platform of the law enforcement evidence collection system, displaying the real-time position and status of the fused target object on the electronic nautical chart. When law enforcement personnel select a target and perform a lock-on operation on the interface, the system immediately retrieves the corresponding fused target object's bearing, distance, and heading parameters from the dynamic situational awareness target cache. The bearing parameter represents the angular difference between the target and the ship's reference direction; the distance parameter represents the spatial distance between the ship and the target; and the heading parameter represents the target's own direction of motion. Simultaneously, the system retrieves real-time navigation data from the ship's navigation module, including parameters such as the ship's position, attitude angles, bow angle, and pitch angle, and determines the target's relative bearing and altitude angle through a coordinate geometry calculation model. The target's relative bearing angle is the angle between the ship's reference line and the target's direction, used to indicate the target's direction in the horizontal plane; the target altitude angle is the elevation angle of the target relative to the ship's horizontal line of sight, used to calculate the electro-optical lens's pitch angle command. These two angle parameters serve as key inputs for subsequent electro-optical guidance and control.

[0073] After receiving the target's relative azimuth and elevation angles, the data processing module executes guidance command generation calculations. The command generation algorithm, based on the kinematic parameters, servo response characteristics, and gimbal angular velocity limitations of the photoelectric forensics equipment, smooths and interpolates the angle commands to prevent target loss due to excessively rapid rotation. The module ultimately generates a photoelectric guidance command package. The servo control field sets the gimbal's rotation mode and execution priority; the azimuth parameter field defines the horizontal rotation angle; the pitch angle parameter field defines the vertical adjustment angle; the focus adjustment field calculates a suitable zoom ratio based on the distance parameter to ensure the target's proportion in the image; and the video channel control field specifies the currently enabled video acquisition channel or resolution mode. The entire command package uses a structured encapsulation format and is transmitted in JSON data structure or binary frame form to ensure data integrity and reliability in low-bandwidth maritime communication environments.

[0074] The generated photoelectric guidance command packet is sent to the control interface of the photoelectric forensics equipment via the User Datagram Protocol (UDP). The UDP protocol, with its low latency and connectionless nature, is suitable for high-frequency real-time control scenarios. Upon receiving the command, the photoelectric forensics equipment parses the content of each field through its internal parsing module and sends it to the servo execution unit. The servo execution unit includes a dual-axis gimbal motor controller and a lens zoom motor controller. It adjusts the gimbal attitude based on azimuth and pitch parameters to ensure the optical axis accurately points towards the target. Simultaneously, it automatically adjusts the zoom magnification and depth of focus based on distance parameters to achieve clear imaging. The focus adjustment algorithm employs a dual-feedback control mode, dynamically optimizing the focus position by monitoring the video frame sharpness index in real time, ensuring optimal sharpness even when the target is moving rapidly or its distance changes.

[0075] Once the photoelectric forensics equipment enters target tracking mode, the target tracking algorithm takes over the servo control process. The system calculates the target displacement vector and scale change based on feature matching of consecutive video frames. It uses a combination of optical flow, feature point matching, and template updating to extract the target's displacement and scale change information in adjacent frames. The displacement vector is used to calculate the target's offset in the frame, and the scale change is used to determine the distance change trend between the target and the equipment. Based on the calculation results, the system corrects the servo control commands in real time, fine-tuning the pan-tilt angle and focal length parameters to keep the target always centered in the frame, forming a dynamic closed-loop tracking system.

[0076] When the target experiences a sudden change in angular velocity or is partially occluded by other objects, the system automatically triggers a prediction compensation algorithm. This algorithm, based on Kalman filtering principles, uses the target's historical trajectory data as input and leverages the target's previous position, velocity, and acceleration parameters to predict its possible position in the near future. This allows for advance adjustment of servo commands, ensuring continuous tracking of the optical axis. If the occlusion duration exceeds a threshold, the system switches to search mode, performing a gimbal scan within the target prediction range until the target image is recaptured.

[0077] While the optoelectronic forensics equipment tracks the target, the video acquisition module captures the target video stream in real time. The video stream is compressed into H.264 or H.265 format by the encoding module and pushed via a streaming media service. The streaming media service encapsulates the video stream into an RTSP or WebRTC protocol stream and pushes it to the front-end interface of the law enforcement forensics command equipment. To ensure the synchronization and traceability of the forensic video, the system embeds a timestamp and device status identifier fields into each video frame. The timestamp marks the standard time of video frame generation, and the device status identifier records the pan-tilt angle, focal length, and tracking mode status. After receiving the video stream, the front-end interface synchronously displays the real-time target image, the optoelectronic equipment angle status, and video frame time information, realizing a closed-loop optoelectronic guidance process from target locking, orientation calculation, command generation, equipment control to video transmission and identification analysis. This closed-loop architecture ensures the spatiotemporal consistency of the forensic video and situational data, improving the accuracy and real-time performance of target acquisition, tracking, and evidence collection.

[0078] S160 performs time correlation and integration of navigation radar information, automatic identification system information, photoelectric video data, target recognition results and abnormal behavior alarm information to generate a law enforcement evidence chain record, and outputs a playback-able and exportable evidence collection report based on the evidence template.

[0079] In one possible implementation, navigation radar information, Automatic Identification System (AIS) information, electro-optical video data, target recognition results, and abnormal behavior alarm information are correlated and integrated over time to generate a law enforcement evidence chain record. Based on the evidence template, a replayable and exportable evidence report is output. Specifically, the evidence chain generation module obtains navigation radar information, AIS information, electro-optical video data, target recognition results, and abnormal behavior alarm information with timestamps and source identifier fields from the data fusion module, abnormal behavior analysis module, target recognition module, and electro-optical guidance module, respectively. Time standardization processing is performed using the standard time provided by the time synchronization equipment as a reference, uniformly converting the timestamps of various data types to Coordinated Universal Time (UTC) format and establishing a time series index table according to chronological order. Based on the identification identifier field of the fused target object, logical mapping and cross-comparison are performed on the multi-source data to correlate information about the same target in different modules, forming a... The system generates a target data association table; performs spatial matching using the spatial position parameters and heading parameters of navigation radar information and Automatic Identification System (AIS) information as key fields to generate a fused track sequence; performs frame-level synchronization using the frame timestamps of optoelectronic video data and the unique identifier of the target recognition result as matching conditions to establish the correspondence between video frames and recognition results; generates a mapping relationship between behavioral events and image evidence based on the alarm time of abnormal behavior alarm information and the track segments and video segments associated with the target identifier location; encapsulates each association result into an evidence chain data package with the timestamp as the primary index and the unique identifier of the target as the secondary index. The evidence chain data package includes a track dataset, optoelectronic video index file, recognition result file, and alarm record; the evidence chain generation module performs formatted export of the evidence chain data package according to a preset evidence template, automatically generating an evidence report document containing the evidence collection time, target information, track changes, recognition images, abnormal behavior descriptions, and video index content.

[0080] Specifically, the evidence chain generation module involves multiple synchronization and fusion stages. First, it extracts data with timestamps and source identifiers from the data fusion module, abnormal behavior analysis module, target recognition module, and photoelectric guidance module. This data includes navigation radar information, Automatic Identification System (AIS) information, photoelectric video data, target recognition results, and abnormal behavior alarm information. Each data point is accompanied by a source identifier field during the generation stage to distinguish the data source module and ensure traceability during subsequent data integration. The system uses a unified time signal output by the time synchronization device as a reference during data acquisition, ensuring that the data output by multiple modules has an aligned time base.

[0081] During time standardization, the system converts all data timestamps to Coordinated Universal Time (UTC) format and establishes a time series index table. The time series index table uses the UTC timestamp as the primary key field to sort and associate various data types. This process eliminates time errors caused by clock deviations between different devices, ensuring that subsequent data synchronization, matching, and playback operations can accurately reconstruct the sequence of events during law enforcement. Standardized time synchronization employs an interpolation resampling mechanism, automatically interpolating and filling in time nodes when data intervals exceed the sampling threshold, maintaining the continuity of the timeline.

[0082] Based on the identification field of the fused target object, the system performs logical mapping and cross-comparison operations on multi-source data. Logical mapping achieves unified association of targets between different modules by matching unique identification identifiers. The system constructs a target data association table, establishing mapping relationships between radar tracks, AIS messages, photoelectric identification results, anomaly alarms, and video clips, achieving a one-to-one correspondence between multi-source data. The cross-comparison process utilizes a triple matching standard of spatial location, timestamp, and identification identifier to merge and verify potentially duplicate targets, avoiding data redundancy.

[0083] In the spatial matching phase, the system performs matching using spatial position parameters and heading parameters from navigation radar information and Automatic Identification System (AIS) information as key fields. Spatial position parameters represent the target's latitude and longitude coordinates in the geographic coordinate system, while heading parameters represent the target's direction of motion angle. The system calculates the spatial distance and heading angle difference between the target and the two data sources; when both are below a set threshold, the target is identified as the same entity. This generates a fused track sequence, which describes the target's continuous movement trajectory over time, used for subsequent evidence presentation and trajectory playback.

[0084] Frame-level synchronization between optoelectronic video data and target recognition results is achieved by matching video frame timestamps with unique target identifiers. The video frame timestamp identifies the acquisition time of each frame in the video. The system matches this timestamp with the time field of the target recognition result to establish a correspondence between video frames and recognition results. In the synchronized data structure, each video frame is associated with a corresponding recognition category and confidence level, enabling the synchronous display of recognition tags and analysis results during playback of the evidence video.

[0085] Abnormal behavior alerts are used to establish the correlation between behavioral events and video evidence. Based on the alert time and target identifier in the alert information, the system retrieves corresponding flight path segments and video clips, thus forming a mapping relationship between behavioral events and video evidence. This mapping relationship identifies the time of occurrence, duration, and spatial location of the abnormal event in the evidence chain, enabling law enforcement officers to quickly locate abnormal behavioral evidence during video playback.

[0086] After integration, the system encapsulates all related results into an evidence chain data package. The evidence chain data package uses timestamps as the primary index and target unique identifiers as secondary indexes. The data package structure includes a flight track dataset, photoelectric video index files, identification result files, and alarm records. All data has a unified format definition and a time field index.

[0087] Finally, the evidence chain generation module performs formatted export of the evidence chain data package according to a preset evidence template. The template defines the field layout and content organization of the evidence collection report, including the evidence collection time, basic target information, trajectory change process, identified images, description of abnormal behavior, and video index content. The export process automatically generates a replayable and exportable evidence collection report document. Each data segment in the report can be traced back to the original record, realizing a visual reproduction of the entire law enforcement process and a complete chain display of evidence.

[0088] This embodiment also discloses an intelligent law enforcement evidence collection system based on comprehensive information integration, referring to... Figure 4 The system includes an acquisition module 401, a processing module 402, and an output module 403. It is used to execute any of the intelligent law enforcement evidence collection methods based on comprehensive information integration described above, wherein: The acquisition module 401 is used to synchronously acquire raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through a multi-source data acquisition interface, and to perform protocol parsing and standardization processing on the raw data to form a unified structured data stream.

[0089] The processing module 402 is used to perform spatial correlation and temporal synchronization processing on navigation radar track information and automatic identification system information based on a unified structured data stream, generate fused target objects based on target position parameters, heading parameters and identification marks, and establish a dynamic situational target set.

[0090] The processing module 402 is used to identify abnormal behaviors of the dynamic situation target set based on a preset abnormal behavior model and output abnormal behavior alarm information.

[0091] The processing module 402 is used to identify the target execution type and hull number in the photoelectric video stream corresponding to the fused target object, generate the target identification result, and match the target identification result with the ship database to update or add target file information.

[0092] The processing module 402 is used to generate photoelectric guidance commands based on the azimuth parameters of the locked target, and send them to the photoelectric evidence collection device through the data processing module. The data processing module controls the photoelectric evidence collection device to perform target tracking and video acquisition, and returns the video stream in real time for display and identification analysis.

[0093] Output module 403 is used to perform time correlation and integration of navigation radar information, automatic identification system information, photoelectric video data, target recognition results and abnormal behavior alarm information, generate law enforcement evidence chain records, and output a playbackable and exportable evidence collection report based on the evidence template.

[0094] It should be noted that the system provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0095] This embodiment also discloses an electronic device, as shown in the reference. Figure 5 The electronic device may include: at least one processor 501, at least one communication bus 502, user interface 503, network interface 504, and at least one memory 505.

[0096] The communication bus 502 is used to enable communication between these components.

[0097] The user interface 503 may include a display screen and a camera. Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0098] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0099] The processor 501 may include one or more processing cores. The processor 501 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 505, and by calling data stored in memory 505. Optionally, the processor 501 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 501 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications. The GPU is responsible for rendering and drawing the content required for display. The modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 501 and may be implemented as a separate chip.

[0100] The memory 505 may include random access memory (RAM) or read-only memory. Optionally, the memory may include a non-transitory computer-readable storage medium. The memory 505 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the various method embodiments described above, etc. The data storage area may store data involved in the various method embodiments described above. Optionally, the memory 505 may also be at least one storage system located remotely from the aforementioned processor 501. As a computer storage medium, the memory 505 may include an operating system, a network communication module, a user interface 503 module, and an application program for an intelligent law enforcement evidence collection method based on comprehensive information integration.

[0101] exist Figure 5In the illustrated electronic device, the user interface 503 is primarily used to provide an input interface for the user and to acquire user input data. The processor 501 can be used to call an application program stored in the memory 505 that represents an intelligent law enforcement evidence collection method based on comprehensive information integration. When executed by one or more processors 501, the electronic device performs one or more methods as described in the above embodiments.

[0102] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, as some steps can be performed in other orders or simultaneously according to the present invention. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0103] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0104] In the embodiments provided by this invention, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between systems or units may be electrical or other forms.

[0105] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0106] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0107] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 505 and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned memory 505 includes various media capable of storing program code, such as a USB flash drive, external hard drive, magnetic disk, or optical disk.

[0108] The present invention also discloses a computer-readable storage medium storing instructions. When executed by one or more processors 501, these instructions cause an electronic device to perform one or more methods as described in the above embodiments.

[0109] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truths. This invention is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. An intelligent law enforcement evidence collection method based on comprehensive information integration, characterized in that, The method includes: The system synchronously acquires raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through a multi-source data acquisition interface, and performs protocol parsing and standardization processing on the raw data to form a unified structured data stream. Based on the unified structured data stream, the navigation radar track information and the ship automatic identification system information are spatially correlated and time-synchronized. Based on the target position parameters, heading parameters and identification marks, a fused target object is generated, and a dynamic situational target set is established. The dynamic situation target set is used to identify abnormal behaviors based on a preset abnormal behavior model, and abnormal behavior alarm information is output. The target execution type and hull number in the photoelectric video stream corresponding to the fused target object are identified to generate a target identification result. The target identification result is then matched with the ship database to update or add target file information. Based on the azimuth parameters of the locked target, an optoelectronic guidance command is generated and sent to the optoelectronic evidence collection device through the data processing module. The optoelectronic evidence collection device is then controlled to perform target tracking and video acquisition, and the video stream is returned in real time for display and identification analysis. The navigation radar information, the automatic identification system information, photoelectric video data, the target recognition results, and the abnormal behavior alarm information are correlated and integrated over time to generate a law enforcement evidence chain record, and an evidence collection report that can be played back and exported is output according to the evidence template.

2. The intelligent law enforcement evidence collection method based on comprehensive information integration according to claim 1, characterized in that, The process of spatially associating and temporally synchronizing navigation radar track information with Automatic Identification System (AIS) information based on the unified structured data stream, generating fused target objects based on target position parameters, heading parameters, and identification markers, and establishing a dynamic situational target set specifically includes: A unified time reference is established through the system management module, and time alignment is performed on the structured data from the navigation radar and the automatic identification system of ships, so as to achieve time consistency of multi-source data by using standardized timestamps as indexes. The coordinate transformation module converts the polar coordinate data of the navigation radar into latitude and longitude coordinates in the geographic coordinate system, and performs spatial coordinate projection on the data output by the Automatic Identification System of Ships to unify it into the global geographic reference system. In the fusion algorithm module, the target position parameters, the heading parameters, the speed parameters and the identification mark are used as matching conditions. Multidimensional matching calculation is performed based on the sliding time window and the spatial neighborhood threshold. The identification mark verification and uniqueness verification are performed on the target set whose time difference and spatial distance are both lower than the preset threshold. The successfully matched radar targets are fused with the targets of the Automatic Identification System (AIS) to generate a fused target object, and dynamic status updates are performed by combining the heading change rate and track continuity parameters. A candidate cache pool is established for unmatched targets and maintained using a time threshold mechanism. When a candidate target has complete data within a preset time window, the fusion update is automatically performed. All fused target objects are stored in the dynamic situation target cache using a dynamic hash table structure, recording real-time position, speed, heading, and update timestamp information. Targets that have not been updated are automatically removed according to an expiration cleanup policy to ensure the real-time performance and continuity of the dynamic situation target set.

3. The intelligent law enforcement evidence collection method based on comprehensive information integration according to claim 1, characterized in that, The step of identifying abnormal behaviors based on a preset abnormal behavior model of the dynamic situation target set and outputting abnormal behavior alarm information specifically includes: An abnormal behavior model set is pre-established in the abnormal behavior analysis module, which includes a jurisdictional sea area model, a temporary warning zone model, a fishing ban zone model, and a target approach model. The spatial boundary of the abnormal behavior model set is formed by the user marking it on the electronic nautical chart layer and stored in the early warning model management library. After receiving the dynamic situation target set, the timestamp, latitude and longitude coordinates, heading parameters and speed parameters of the fused target object are used as input data. The model matching operation is used to determine whether the target has entered the spatial boundary defined by the model or violated the behavior rules. When the fusion target object is detected to have entered an unauthorized jurisdictional sea area, temporary maritime warning zone or fishing ban zone, or when the spatial distance between any two targets is less than the proximity threshold, the corresponding abnormal behavior model is triggered and abnormal behavior alarm information is generated. The abnormal behavior alarm information, including alarm type, time, target unique identifier and track information, is written into the alarm data cache area, and the alarm results are synchronized to the integrated situation interface through the message push mechanism. The abnormal target is highlighted and displayed on the electronic nautical chart. The client maintains an exception list and an exception refresh time field. When the target does not receive new exception data within a set time threshold, the highlighting status is automatically canceled and the exception is removed from the exception list.

4. The intelligent law enforcement evidence collection method based on comprehensive information integration according to claim 1, characterized in that, The step of identifying the target execution type and hull number in the photoelectric video stream corresponding to the fused target object, generating a target identification result, and matching the target identification result with the ship database to update or add target file information specifically includes: The photoelectric evidence collection device is controlled by servo control commands to collect video streams of the target area, and the video streams of the target area are pushed to the target recognition module using streaming media services; The target recognition module listens to the streaming address and performs frame-by-frame segmentation and image preprocessing on the received video frames. It inputs the framed images into the trained multi-layer convolutional neural network model for type recognition and outputs the category label and confidence result of the ship target in each frame image. The identified target area is enhanced with character features and optical character recognition. The target hull number is extracted and the hull number recognition confidence is calculated. A target recognition result containing target type, hull number and confidence information is generated. The target recognition result is pushed to the law enforcement evidence collection command equipment software in real time through the user data packet protocol and is displayed on the comprehensive situation interface in the form of video overlay annotation. The system calls the ship database interface and uses the hull number information as the key field for matching. When the corresponding ship file information exists in the database, the system updates the latest identification time and video sample in the ship file. When the corresponding information does not exist in the database, the system automatically generates a new ship file entry and writes the basic information, image sample and confidence data of the identification result into it.

5. The intelligent law enforcement evidence collection method based on comprehensive information integration according to claim 1, characterized in that, The process of generating photoelectric guidance commands based on the azimuth parameters of the locked target, sending them to the photoelectric evidence collection device via the data processing module, controlling the device to perform target tracking and video acquisition, and returning the video stream in real time for display and identification analysis, specifically includes: The system receives the lock command from law enforcement personnel on the fused target object in the integrated situation interface, extracts the bearing parameters, distance parameters and heading parameters of the fused target object, and calculates the target relative bearing angle and target elevation angle in combination with the ship's navigation data; The data processing module generates a photoelectric guidance instruction package based on the calculation results. The photoelectric guidance instruction package includes a servo control field, an azimuth parameter field, a pitch parameter field, a focus adjustment field, and a video channel control field. The photoelectric guidance instruction packet is sent to the control interface of the photoelectric evidence collection device via the User Datagram Protocol. After parsing the instruction, the photoelectric evidence collection device drives the servo execution unit to adjust the gimbal attitude according to the azimuth and pitch angle parameters, so that the optical axis is aligned with the target direction, and automatically adjusts the zoom ratio and focus depth according to the distance parameters to ensure image clarity. When the photoelectric forensics equipment enters the target tracking mode, it calculates the target displacement vector and scale change based on feature matching between consecutive video frames, and corrects the servo control commands in real time to maintain the optical axis tracking of the target. When the target experiences changes in angular velocity or occlusion, a prediction compensation algorithm is triggered to calculate the target's position based on the target's motion trajectory parameters from the previous moment in order to achieve continuous tracking. While the photoelectric evidence collection device performs target tracking, it collects target video streams in real time and pushes them to the front-end interface of the law enforcement evidence collection command device through a streaming media service, with timestamps and device status identification fields attached, thus forming a closed-loop photoelectric guidance process from target locking, orientation calculation, guidance command generation, device control to video transmission and identification analysis.

6. The intelligent law enforcement evidence collection method based on comprehensive information integration according to claim 1, characterized in that, The process involves temporally correlating and integrating the navigation radar information, the automatic identification system information, photoelectric video data, the target recognition results, and the abnormal behavior alarm information to generate a law enforcement evidence chain record. Based on the evidence template, a replayable and exportable evidence collection report is output, specifically including: The evidence chain generation module obtains navigation radar information with timestamp and source identifier fields, automatic identification system information, photoelectric video data, target recognition results and abnormal behavior alarm information from the data fusion module, abnormal behavior analysis module, target recognition module and photoelectric guidance module, respectively. Time standardization processing is performed based on the standard time provided by the time synchronization device, and the timestamps of various data are uniformly converted into Coordinated Universal Time format and a time series index table is established according to the chronological order. Based on the identification field of the fused target object, logical mapping and cross-comparison are performed on the multi-source data to associate the information of the same target in different modules and form a target data association table; Spatial matching is performed using the spatial position parameters and heading parameters of navigation radar information and automatic identification system information as key fields to generate a fused track sequence; Frame-level synchronization is performed by matching the frame timestamp of the optoelectronic video data with the unique identifier of the target in the target recognition result, thereby establishing the correspondence between video frames and recognition results. Based on the alarm time of abnormal behavior alarm information and the trajectory and video segments associated with the target identification location, a mapping relationship between behavioral events and video evidence is generated; Each associated result is encapsulated into an evidence chain data package with timestamp as the primary index and target unique identifier as the secondary index. The evidence chain data package includes track dataset, photoelectric video index file, identification result file and alarm record; The evidence chain generation module performs formatted export of the evidence chain data package based on the preset evidence template, and automatically generates an evidence report document containing evidence collection time, target information, track changes, identified images, descriptions of abnormal behavior, and video index content.

7. The intelligent law enforcement evidence collection method based on comprehensive information integration according to claim 1, characterized in that, The process involves synchronously acquiring raw data from photoelectric evidence collection equipment, navigation radar, automatic identification systems (AIS) for ships, and time synchronization equipment via a multi-source data acquisition interface, and performing protocol parsing and standardization processing on the raw data to form a unified structured data stream. Specifically, this includes: Configure the configuration information and protocol message format of the photoelectric evidence collection device, the navigation radar, the automatic identification system for ships, and the timing device in the system management module respectively; Establish data communication channels with each device according to the configuration information, and receive real-time raw data output by the photoelectric evidence collection device, the navigation radar, the automatic identification system for ships, and the timing device in a periodic sampling manner; The original data is processed by message structure recognition and field mapping. The target track information output by the navigation radar is converted into a standardized data structure containing target bearing parameters, distance parameters, speed parameters and heading parameters. The static and dynamic information output by the automatic identification system is parsed into a unified field format. The time information output by the time synchronization device is synchronously updated to the system standard time format. The video data output by the photoelectric evidence collection device is used to generate corresponding video stream description data. The message transmission protocol performs unified encapsulation, field validation, and timestamp indexing on various parsed data to form a structured data stream with consistent structure and uniform format.

8. An intelligent law enforcement evidence collection system based on comprehensive information integration, characterized in that, The system is used to execute an intelligent law enforcement evidence collection method based on comprehensive information integration as described in any one of claims 1-7. The system includes an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to synchronously acquire raw data from photoelectric evidence collection equipment, navigation radar, automatic identification system for ships, and time synchronization equipment through a multi-source data acquisition interface, and to perform protocol parsing and standardization processing on the raw data to form a unified structured data stream. The processing module is used to perform spatial correlation and temporal synchronization processing on navigation radar track information and automatic identification system information based on the unified structured data stream, generate fused target objects based on target position parameters, heading parameters and identification marks, and establish a dynamic situational target set. The processing module is used to identify abnormal behaviors of the dynamic situation target set based on a preset abnormal behavior model and output abnormal behavior alarm information. The processing module is used to identify the target execution type and hull number in the photoelectric video stream corresponding to the fused target object, generate a target identification result, and match the target identification result with the ship database to update or add target file information. The processing module is used to generate photoelectric guidance commands based on the azimuth parameters of the locked target, send them to the photoelectric evidence collection device through the data processing module, control the photoelectric evidence collection device to perform target tracking and video acquisition, and return the video stream in real time for display and identification analysis; The output module is used to perform time correlation and integration of the navigation radar information, the ship automatic identification system information, photoelectric video data, the target recognition result and the abnormal behavior alarm information, generate law enforcement evidence chain record, and output a playback and exportable evidence collection report based on the evidence template.

9. An electronic device, characterized in that, The device includes a processor, a communication bus, a user interface, a network interface, and a memory. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The communication bus is used to enable communication between the components within the electronic device. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1-7.

Images