CN117671614A - Evidence chain collection and display system and method based on multi-equipment linkage - Google Patents

Evidence chain collection and display system and method based on multi-equipment linkage Download PDF

Info

Publication number
CN117671614A
CN117671614A CN202311539274.3A CN202311539274A CN117671614A CN 117671614 A CN117671614 A CN 117671614A CN 202311539274 A CN202311539274 A CN 202311539274A CN 117671614 A CN117671614 A CN 117671614A
Authority
CN
China
Prior art keywords
early warning
target
evidence
linkage
track
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311539274.3A
Other languages
Chinese (zh)
Inventor
张丹普
杨剑锋
裴仪瑶
刘立明
程健鹏
王士飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Changfeng Science Technology Industry Group Corp
Original Assignee
China Changfeng Science Technology Industry Group Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Changfeng Science Technology Industry Group Corp filed Critical China Changfeng Science Technology Industry Group Corp
Priority to CN202311539274.3A priority Critical patent/CN117671614A/en
Publication of CN117671614A publication Critical patent/CN117671614A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/10Pre-processing; Data cleansing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G06V10/765Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Alarm Systems (AREA)

Abstract

The invention relates to a evidence chain acquisition and display system and method based on multi-equipment linkage, comprising a perception layer, a decision layer and a service layer, wherein the perception layer realizes signal access, cleaning and identification of a target of interest and provides data support for follow-up model algorithm reasoning; the decision layer realizes scene classification, and calls peripheral photoelectric equipment to carry out linkage video according to early warning results of different models; the service layer realizes early warning prompt, and performs evidence playback by combining the early warning target activity track, scene category and video result, and performs further confirmation and treatment by connecting with the terminal equipment. The invention can realize the complete evidence display of the early warning ship, better assist the staff on duty in completing the confirmation of the early warning information, and promote the efficiency of early warning treatment.

Description

Evidence chain collection and display system and method based on multi-equipment linkage
Technical Field
The invention relates to the technical field of signal processing, in particular to a system and a method for improving treatment efficiency by judging and determining whether an abnormal behavior exists in a target through a model algorithm and combining multiple devices to collect and display an evidence chain.
Background
The marine illegal ships are monitored and analyzed in real time, the existence of the illegal ships can be found in time, the occurrence of marine criminal activities such as illegal fishing, smuggling and piracy can be prevented, the marine ecological environment and resources are protected, and the seriousness and authority of the marine laws and regulations are maintained. Meanwhile, the method can be used for timely disposing the marine illegal ships, so that the method can play a role in frightening, prevent other people from imitating illegal behaviors, and maintain good marine order and social security. Therefore, monitoring and handling of illicit marine vessels is an important measure to ensure sustainable development of the ocean and human well-being.
With the wide application of artificial intelligence analysis, a target behavior detection model based on machine learning training is gradually applied to offshore law enforcement, and important auxiliary functions are started for real-time monitoring of offshore illegal behaviors and reducing the workload of operators on duty. At present, the target behavior detection is mainly a decision tree model based on expert experience, parameter optimization and algorithm updating of the model are closely related to the acquired sample data quantity, and meanwhile, how to analyze and explain the model performance is also a key problem to be solved in the field.
The current relevant departments can check the marine illegal ship early warning information mainly through a central retrieval monitoring camera or confirm through on-site law enforcement, the treatment efficiency is low, a large-scale data knowledge base is difficult to form, and the comprehensive performance of the model cannot be accurately evaluated. Therefore, a perfect evidence chain acquisition and display flow is constructed through multi-equipment linkage and multi-source signal fusion on the basis of the existing model algorithm, the flow and automation of early warning information treatment are improved, and the effectiveness of the model algorithm in the illegal behavior management and control process is enhanced.
Disclosure of Invention
Aiming at the defects, the invention provides a evidence chain acquisition and display system and method based on multi-equipment linkage, which are used for solving the problems of insufficient evidence and low treatment efficiency in the prior marine ship abnormal behavior early warning process, realizing clear and transparent early warning logic and complete and full evidence, and powerfully supporting related departments to perform law enforcement on illegal behaviors, thereby obtaining expected effects.
The technical scheme of the invention is as follows:
evidence chain collection display system based on multi-device linkage, its characterized in that: the system comprises a perception layer, a decision layer and a service layer;
the perception layer mainly realizes signal access, cleaning and recognition of a target of interest, filters out repeated and invalid data and provides data support for follow-up model algorithm reasoning;
the decision layer is mainly used for classifying scenes according to the models configured in the concerned area, and calling peripheral photoelectric equipment to carry out linkage and video recording by combining with the early warning results of different models to generate multi-source information data;
the service layer mainly carries out early warning prompt on early warning information generated by the decision layer, carries out evidence playback by combining an early warning target activity track, scene categories and video results, assists an operator on duty to confirm early warning information accuracy, and further confirms confirmed early warning information linkage terminal equipment.
In the system, the sensing layer comprises multi-source signal access and target fusion matching; the multi-source signal access is used for accessing information of radar, AIS and Beidou equipment, and accessing and storing target information in various sources are realized through proprietary protocol analysis and track compression; and performing space alignment and morphological matching on target data accessed in a time window by using the target fusion matching, determining whether the same target exists in signals of different sources, and storing the actual activity condition of the target by using a track fusion prediction algorithm.
In the system, the decision layer comprises a scene classification module, a model algorithm module and a photoelectric linkage module; the scene classification module classifies the early warning into typical scenes such as single-target track type, single-target area type, multi-target association type and the like according to a set early warning model, and adopts different visual display methods for early warning results of each scene; the model algorithm module comprehensively researches and judges the ship track in the area according to the service rules and the model training parameters, determines whether the ship has an abnormal track or not, has a large probability of illegal behaviors, and outputs an early warning result; and the photoelectric linkage module performs linkage video recording by using photoelectricity nearby the target position according to the early warning information to acquire video evidence associated with the early warning information.
In the system, the service layer comprises an early warning prompt module, an evidence playback module and a tail end linkage module; the early warning prompt module carries out sound and popup window prompt on a system interface according to units and departments associated with early warning information to help an on-duty person to notice sudden early warning conditions; the evidence playback module generates report descriptions of different categories according to early warning information and scene categories generated by the decision layer and by combining with archive information and historical tracks of the concerned targets, and displays an early warning evidence chain to an attendant by combining with functions of video evidence, track playback and the like, so as to assist the attendant to confirm whether further treatment is carried out; the terminal linkage module is a plurality of terminal devices using site sites, assists operators on duty to know site conditions, and uses sound waves, laser and calling machines to carry out remote treatment or calls surrounding law enforcement departments to carry out site treatment.
The evidence chain collection and display method based on multi-equipment linkage by adopting the system is characterized by comprising the following steps of:
s1, carrying out proprietary protocol analysis and track compression on a radar, an AIS and a Beidou signal through multi-source signal access to realize the access and efficient storage of track data of each target;
s2, performing space alignment and morphological matching on the target tracks obtained in the S1, and performing fusion association on the same targets in multiple signal sources, so that the number of the targets to be processed and repeated model judgment consumption are reduced;
s3, carrying out track analysis on the target extracted in the S2 through a set model algorithm, and outputting early warning information of abnormal behaviors;
s4, searching photoelectric equipment near the target of interest for linkage video according to the early warning information obtained in the S3, and determining a visual display method of the target through a scene classification model;
s5, prompting an attendant in the system in a sound and popup mode according to the early warning information obtained in the step S3;
s6, when staff uses the 'evidence playback' function of the system, the system acquires target tracks and file information to perform different types of visual processing according to the visual display method determined in the S4, and displays video;
and S7, the operator on duty confirms the accuracy of the early warning information according to the evidence chain result provided by the S6, and calls the terminal equipment to further confirm and treat.
The invention has the advantages that: compared with the prior art, the invention realizes the complete evidence display of the early warning ship, can better assist the staff on duty of the center to finish the confirmation of the early warning information, and improves the efficiency of early warning treatment.
Drawings
FIG. 1 is a system module frame diagram of the present invention;
FIG. 2 is a diagram showing single-target activity behavior evidence;
FIG. 3 is a diagram showing the evidence of activity behavior in an area;
FIG. 4 is a diagram of a multi-objective activity behavioral evidence presentation.
Detailed Description
As shown in fig. 1, the evidence chain collection and display system based on multi-device linkage provided by the invention comprises a perception layer, a decision layer and a service layer, wherein:
the perception layer mainly realizes signal access, cleaning and recognition of a target of interest, filters out repeated and invalid data and provides data support for follow-up model algorithm reasoning;
the decision layer is mainly used for classifying scenes according to the models configured in the concerned area, and calling peripheral photoelectric equipment to carry out linkage and video recording by combining with the early warning results of different models to generate multi-source information data;
the service layer mainly carries out early warning prompt on early warning information generated by the decision layer, carries out evidence playback by combining an early warning target activity track, scene categories and video results, assists an operator on duty to confirm early warning information accuracy, and further confirms confirmed early warning information linkage terminal equipment.
In the system, the sensing layer comprises multi-source signal access and target fusion matching; the multi-source signal access is used for accessing information of radar, AIS and Beidou equipment, and accessing and storing target information in various sources are realized through proprietary protocol analysis and track compression; and performing space alignment and morphological matching on target data accessed in a time window by using the target fusion matching, determining whether the same target exists in signals of different sources, and storing the actual activity condition of the target by using a track fusion prediction algorithm.
In the system, the decision layer comprises a scene classification module, a model algorithm module and a photoelectric linkage module; the scene classification module classifies the early warning into typical scenes such as single-target track type, single-target area type, multi-target association type and the like according to a set early warning model, and adopts different visual display methods for early warning results of each scene; the model algorithm module comprehensively researches and judges the ship track in the area according to the service rules and the model training parameters, determines whether the ship has an abnormal track or not, has a large probability of illegal behaviors, and outputs an early warning result; and the photoelectric linkage module performs linkage video recording by using photoelectricity nearby the target position according to the early warning information to acquire video evidence associated with the early warning information.
In the system, the service layer comprises an early warning prompt module, an evidence playback module and a tail end linkage module; the early warning prompt module carries out sound and popup window prompt on a system interface according to units and departments associated with early warning information to help an on-duty person to notice sudden early warning conditions; the evidence playback module generates report descriptions of different categories according to early warning information and scene categories generated by a decision layer and by combining file information and historical tracks of a concerned target, and combines the functions of video evidence, track playback and the like, so that an early warning evidence chain is displayed to an attendant to assist the attendant to confirm whether further treatment is carried out, a behavior evidence display mode diagram of single target activity is shown in FIG. 2, track, speed and angle information of the target are shown, and a evidence display diagram of target activity behavior in a region is shown in FIG. 3; FIG. 4 is a diagram showing the behavioral evidence of the invention for multiple targets. The terminal linkage module is a plurality of terminal devices using site sites, assists operators on duty to know site conditions, and uses sound waves, laser and calling machines to carry out remote treatment or calls surrounding law enforcement departments to carry out site treatment.
The evidence chain collection and display method based on multi-equipment linkage by adopting the system comprises the following steps:
s1, carrying out proprietary protocol analysis and track compression on a radar, an AIS and a Beidou signal through multi-source signal access to realize the access and efficient storage of track data of each target;
s2, performing space alignment and morphological matching on the target tracks obtained in the S1, and performing fusion association on the same targets in multiple signal sources, so that the number of the targets to be processed and repeated model judgment consumption are reduced;
s3, carrying out track analysis on the target extracted in the S2 through a set model algorithm, and outputting early warning information of abnormal behaviors;
s4, searching photoelectric equipment near the target of interest for linkage video according to the early warning information obtained in the S3, and determining a visual display method of the target through a scene classification model;
s5, prompting an attendant in the system in a sound and popup mode according to the early warning information obtained in the step S3;
s6, when staff uses the system evidence playback function, the system acquires target tracks and file information to perform different types of visual processing according to the visual display method determined in the S4, wherein the display mode is shown in figures 2-4, and video is displayed;
and S7, the operator on duty confirms the accuracy of the early warning information according to the evidence chain result provided by the S6, and calls the terminal equipment to further confirm and treat.

Claims (5)

1. Evidence chain collection display system based on multi-device linkage, its characterized in that: the system comprises a perception layer, a decision layer and a service layer;
the perception layer mainly realizes signal access, cleaning and recognition of a target of interest, filters out repeated and invalid data and provides data support for follow-up model algorithm reasoning;
the decision layer is mainly used for classifying scenes according to the models configured in the concerned area, and calling peripheral photoelectric equipment to carry out linkage and video recording by combining with the early warning results of different models to generate multi-source information data;
the service layer mainly carries out early warning prompt on early warning information generated by the decision layer, carries out evidence playback by combining an early warning target activity track, scene categories and video results, assists an operator on duty to confirm early warning information accuracy, and further confirms confirmed early warning information linkage terminal equipment.
2. The multi-device linkage-based evidence chain collection and display system according to claim 1, wherein: the sensing layer comprises multi-source signal access and target fusion matching; the multi-source signal access is used for accessing information of radar, AIS and Beidou equipment, and accessing and storing target information in various sources are realized through proprietary protocol analysis and track compression; and performing space alignment and morphological matching on target data accessed in a time window by using the target fusion matching, determining whether the same target exists in signals of different sources, and storing the actual activity condition of the target by using a track fusion prediction algorithm.
3. The multi-device linkage-based evidence chain collection and display system according to claim 1, wherein: the decision layer comprises a scene classification module, a model algorithm module and a photoelectric linkage module; the scene classification module classifies the early warning into typical scenes such as single-target track type, single-target area type, multi-target association type and the like according to a set early warning model, and adopts different visual display methods for early warning results of each scene; the model algorithm module comprehensively researches and judges the ship track in the area according to the service rules and the model training parameters, determines whether the ship has an abnormal track or not, has a large probability of illegal behaviors, and outputs an early warning result; and the photoelectric linkage module performs linkage video recording by using photoelectricity nearby the target position according to the early warning information to acquire video evidence associated with the early warning information.
4. The multi-device linkage-based evidence chain collection and display system according to claim 1, wherein: the service layer comprises an early warning prompt module, an evidence playback module and a tail end linkage module; the early warning prompt module carries out sound and popup window prompt on a system interface according to units and departments associated with early warning information to help an on-duty person to notice sudden early warning conditions; the evidence playback module generates report descriptions of different categories according to early warning information and scene categories generated by the decision layer and by combining with archive information and historical tracks of the concerned targets, and displays an early warning evidence chain to an attendant by combining with functions of video evidence, track playback and the like, so as to assist the attendant to confirm whether further treatment is carried out; the terminal linkage module is a plurality of terminal devices using site sites, assists operators on duty to know site conditions, and uses sound waves, laser and calling machines to carry out remote treatment or calls surrounding law enforcement departments to carry out site treatment.
5. The evidence chain collection and display method based on multi-equipment linkage adopts the evidence chain collection and display system based on multi-equipment linkage as claimed in any one of claims 1 to 4, and is characterized by comprising the following steps:
s1, carrying out proprietary protocol analysis and track compression on a radar, an AIS and a Beidou signal through multi-source signal access to realize the access and efficient storage of track data of each target;
s2, performing space alignment and morphological matching on the target tracks obtained in the S1, and performing fusion association on the same targets in multiple signal sources, so that the number of the targets to be processed and repeated model judgment consumption are reduced;
s3, carrying out track analysis on the target extracted in the S2 through a set model algorithm, and outputting early warning information of abnormal behaviors;
s4, searching photoelectric equipment near the target of interest for linkage video according to the early warning information obtained in the S3, and determining a visual display method of the target through a scene classification model;
s5, prompting an attendant in the system in a sound and popup mode according to the early warning information obtained in the step S3;
s6, when staff uses the 'evidence playback' function of the system, the system acquires target tracks and file information to perform different types of visual processing according to the visual display method determined in the S4, and displays video;
and S7, the operator on duty confirms the accuracy of the early warning information according to the evidence chain result provided by the S6, and calls the terminal equipment to further confirm and treat.
CN202311539274.3A 2023-11-17 2023-11-17 Evidence chain collection and display system and method based on multi-equipment linkage Pending CN117671614A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311539274.3A CN117671614A (en) 2023-11-17 2023-11-17 Evidence chain collection and display system and method based on multi-equipment linkage

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311539274.3A CN117671614A (en) 2023-11-17 2023-11-17 Evidence chain collection and display system and method based on multi-equipment linkage

Publications (1)

Publication Number Publication Date
CN117671614A true CN117671614A (en) 2024-03-08

Family

ID=90077960

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311539274.3A Pending CN117671614A (en) 2023-11-17 2023-11-17 Evidence chain collection and display system and method based on multi-equipment linkage

Country Status (1)

Country Link
CN (1) CN117671614A (en)

Similar Documents

Publication Publication Date Title
CN110996067A (en) Personnel safety real-time intelligent video monitoring system under high-risk operation environment based on deep learning
CN107888887A (en) A kind of video monitoring method for early warning and system for monitoring gas pipeline damage from third-party
CN115603466B (en) Ship shore power system based on artificial intelligence visual identification
CN112804489B (en) Intelligent construction site management system and method based on Internet +
CN102254394A (en) Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis
CN118072255B (en) Intelligent park multisource data dynamic monitoring and real-time analysis system and method
CN112530144B (en) Method and system for warning violation behaviors of thermal power plant based on neural network
CN112686130B (en) Wisdom fishing boat supervision decision-making system
CN105632115A (en) Offshore oilfield security system
CN117636169A (en) Forest patrol method and system
NL2037440A (en) A method, system, and medium for intelligent recognition of fishing activities based on image processing
CN115423225A (en) Fishing port operation management method and system based on big data
CN111027463A (en) Wall turning detection method based on video analysis
CN117992906A (en) Ship early warning method and system based on data fusion
CN118097423A (en) Rice disease early warning and preventing and controlling system and method based on artificial intelligence
CN117671614A (en) Evidence chain collection and display system and method based on multi-equipment linkage
CN117197726A (en) Important personnel accurate management and control system and method
CN115629567A (en) Multi-mode information management system, early warning method and storage medium for livestock and poultry farm
CN114354744A (en) Power cable external damage prevention monitoring method, system and device
CN117456471B (en) Perimeter security method, perimeter security system, terminal equipment and storage medium
Jones et al. Introducing NMMF WAMS, an open-source PAMGuard plug-in, and some pilot data for its use as a welfare acoustic monitoring system
CN117057451A (en) System and method suitable for predicting distribution of hairtail resources in north and south China sea
CN117998053A (en) Monitoring device access system based on data security
CN118486152A (en) Security alarm information data interaction system and method
CN117271971A (en) Early warning method, system and medium for threat organisms at water inlet of nuclear power station

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication