CN114390156A - Rail transit video analysis control box, system and method - Google Patents
Rail transit video analysis control box, system and method Download PDFInfo
- Publication number
- CN114390156A CN114390156A CN202210002246.7A CN202210002246A CN114390156A CN 114390156 A CN114390156 A CN 114390156A CN 202210002246 A CN202210002246 A CN 202210002246A CN 114390156 A CN114390156 A CN 114390156A
- Authority
- CN
- China
- Prior art keywords
- video analysis
- video
- identification result
- control box
- intelligent
- 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
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 109
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000004891 communication Methods 0.000 claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 9
- 238000012806 monitoring device Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 3
- 206010010947 Coordination abnormal Diseases 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000004927 fusion Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/414—Specialised client platforms, e.g. receiver in car or embedded in a mobile appliance
- H04N21/41422—Specialised client platforms, e.g. receiver in car or embedded in a mobile appliance located in transportation means, e.g. personal vehicle
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Alarm Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to the technical field of rail transit correlation, and provides a rail transit video analysis control box, a rail transit video analysis control system and a rail transit video analysis control method. Track traffic video analysis control box includes: the intelligent core board and the intelligent carrier board; the intelligent core board is connected with the first communication interface, acquires video information and audio information, performs intelligent security scene identification to obtain an identification result, and sends the identification result to the central server; wherein, the identification result is a scene needing to be alarmed; the intelligent carrier plate is connected with the intelligent core board and used for protecting the control box, acquiring the recognition result and the running state of the intelligent core board and giving an alarm based on the recognition result and the running state. So, track traffic video analysis control box can directly carry out security protection scene intelligent identification after obtaining the video, obtains the recognition result, reduces the volume of sending data to central server, and ductility when reducing terminal data analysis and response production avoids leading to the staff to deal with the delay because of the system feedback is untimely.
Description
Technical Field
The invention relates to the technical field of rail transit correlation, in particular to a rail transit video analysis control box, a rail transit video analysis control system and a rail transit video analysis control method.
Background
The track video monitoring system is mainly deployed in stations, parking lots and vehicle sections, and transmits video images of the line to a subway control center for monitoring, so that the track video monitoring system becomes an important means for guaranteeing the safety of track traffic driving organizations and maintaining the bus taking order of the stations and the safety of passengers.
The prior applied track traffic video monitoring system belongs to a central centralized processing type framework, and the following problems exist when the monitored object is analyzed and processed by centralized computing resources. In the aspect of system architecture, mass video data are all transmitted to a computing center for processing, so that the terminal data analysis and response generate time delay, and the processing delay of workers can be caused due to untimely system feedback.
Disclosure of Invention
The embodiment of the invention provides a rail transit video analysis control box, a rail transit video analysis control system and a rail transit video analysis control method, which are used for solving the problems that massive video data are transmitted to a computing center to be processed, so that the terminal data analysis and response generate time delay, and the processing delay of workers can be caused by untimely system feedback.
In a first aspect, an embodiment of the present invention provides a rail transit video analysis control box, including: the intelligent core board comprises a shell, an intelligent core board and an intelligent carrier board;
the shell is provided with a first communication interface;
the intelligent core board and the intelligent carrier board are arranged inside the shell;
the intelligent core board is connected with the first communication interface, obtains video information and audio information, carries out intelligent security scene identification based on the video information and the audio information to obtain an identification result, and sends the identification result to a central server through the first communication interface; wherein the identification result is a scene needing to be alarmed;
the intelligent carrier plate is connected with the intelligent core board and used for protecting the rail transit video analysis control box, acquiring the recognition result and the running state of the intelligent core board and giving an alarm based on the recognition result and the running state.
Preferably, the smart core board comprises: the system comprises an audio and video information decoding module, a central processing unit and a graphic processor;
the central processor is respectively connected with the audio and video information decoding module and the graphic processor;
the audio and video information decoding module is used for acquiring the video information and the audio information and decoding the video information and the audio information to obtain an original code stream;
the central processing unit is used for processing the original code stream to obtain high-order tensor data of video information and audio information;
the image processor is used for inputting the high-order tensor data into a preset neural network model to obtain a primary output low-order tensor;
the central processing unit is used for clustering the preliminary output low-order tensor to obtain image classification characteristics and audio classification characteristics based on timestamps; fusing image classification features and audio classification features based on the timestamp, and identifying based on a preset rule to obtain an identification result; the image classification features include: video passenger abnormal behavior characteristics, station abnormal environment characteristics, abnormal light brightness characteristics and large passenger flow characteristics; the audio classification features include: a sound abnormal tone feature, an abnormal loudness feature, a loudness change rate feature, and a delay time feature;
preferably, the smart carrier includes: the device comprises a micro control unit, a wireless communication module and a protection device;
the micro control unit is in communication connection with the intelligent core board and is used for acquiring the running state and the over-temperature state of the intelligent core board and controlling a preset fan and an alarm unit based on the running state and the over-temperature state;
the wireless communication module is used for sending the identification result of the intelligent core board to a mobile station terminal
The protection device includes: overcurrent safety device, pin electrostatic protection device, two-way voltage level converter.
Preferably, the alarm unit includes an indicator lamp and a sound unit.
Preferably, the intelligent core board and the intelligent carrier board are in communication connection through a USB communication module and/or a UART communication module.
In a second aspect, an embodiment of the present invention provides a track traffic video analysis control system, including: the system comprises a central server and a plurality of groups of track video monitoring systems; each group of track video monitoring system comprises: the track video monitoring device, the switch and the track traffic video analysis control box provided by the embodiment of the invention;
the track video monitoring device is used for acquiring audio information and video information and sending the audio information and the video information to the switch;
the switch sends the audio information and the video information to the rail transit video analysis control box;
the rail transit video analysis control box identifies the audio information and the video information to obtain an identification result, and sends the identification result to the switch;
and the switch sends the identification result to the central server.
Preferably, the track traffic video analysis control box is further configured to send a first control instruction to the controlled terminal based on the identification result, so as to control the controlled terminal to perform information broadcasting and event processing.
The controlled terminal includes: platform door, automatic escalator, vertical elevator, floodgate machine, broadcasting equipment and display screen.
Preferably, the method further comprises the following steps: a mobile station service terminal;
and the track traffic video analysis control box is also used for sending an identification result to the mobile station service terminal.
Preferably, the track video monitoring system further comprises: a manual console;
the manual control console is used for controlling the control instruction input by the staff so as to control the rail transit controlled terminal
And the track traffic video analysis control box is also used for sending an identification result to the mobile station service terminal.
Preferably, the track traffic video analysis control box is further used for acquiring a manual identifier fed back by an employee;
the rail transit video analysis control box is used for sending a second control instruction to the controlled terminal to control the controlled terminal to broadcast information and process events when the artificial identification is used for representing that the identification result is an emergency; when the artificial identification is used for representing that the identification result is wrong, recording the wrong identification result;
and the wrong recognition result and the corresponding artificial identification are used for retraining a module for intelligently recognizing the security scene in the track traffic video analysis control box.
In a third aspect, an embodiment of the present invention provides a rail transit video analysis control method, which is applied to a rail transit video analysis control box of a rail transit video analysis control system provided in an embodiment of the present invention, where the rail transit video analysis control method includes:
acquiring video information and audio information;
based on the video information and the audio information, performing intelligent identification on a security scene to obtain an identification result;
sending the identification result to the central server through a first communication interface; wherein the identification result is a scene needing to be alarmed;
sending the identification result to a mobile station service terminal through a wireless communication module; and the identification result is a scene needing alarming and emergency treatment.
Optionally, the method further includes:
based on the identification result, sending a control instruction to a controlled terminal in the rail transit video analysis control system to control the controlled terminal to broadcast information and process events;
wherein the controlled terminal includes: platform doors, escalators, vertical elevators, gates, broadcasting equipment and display screens;
and sending the identification result to a preset mobile station service terminal.
In the rail transit video analysis control box provided by the embodiment of the invention, the intelligent core board is connected with the first communication interface to acquire video information and audio information, performs intelligent security scene identification based on the video information and the audio information to obtain an identification result, and sends the identification result to the central server through the first communication interface; wherein the identification result is a scene needing to be alarmed; the intelligent carrier plate is connected with the intelligent core board and used for protecting the rail transit video analysis control box, acquiring the recognition result and the running state of the intelligent core board and giving an alarm based on the recognition result and the running state. So, track traffic video analysis control box can be directly after obtaining the video, directly carries out security protection scene intelligent recognition, obtains the identification result, avoids sending video information and audio information to central server, reduces data transmission's volume, and ductility when reducing terminal data analysis and response production avoids delaying because of the untimely staff's that leads to handles because of system feedback.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a track traffic video analysis control box according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a track traffic video analysis control system according to an embodiment of the present invention;
fig. 3 is a flow chart of station video analysis edge calculation of the rail transit video analysis control system according to the embodiment of the present invention;
fig. 4 is a schematic flowchart of a track traffic video analysis control method according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating a track traffic video analysis control method according to another embodiment of the present invention.
Reference numerals:
1: an intelligent core board; 11: an audio and video information decoding module; 12: a central processing unit;
13: a graphics processor; 2: an intelligent carrier plate; 21: a micro control unit;
22: a wireless communication module; 23: a protection device; 3: a central server;
4: a track video monitoring system; 5: a track video monitoring device; 6: a switch;
7: track traffic video analysis control box.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The track video monitoring system is mainly deployed in stations, parking lots and vehicle sections, and transmits video images of the line to a subway control center for monitoring, so that the track video monitoring system becomes an important means for guaranteeing the safety of track traffic driving organizations and maintaining the bus taking order of the stations and the safety of passengers. However, the track video monitoring system is limited by the self framework and the application shortage of the new technology, so that some problems occur during further intelligent upgrading and optimization, and even certain restrictions are generated on the aspect of supporting track traffic safety guarantee.
The prior applied track traffic video monitoring system belongs to a central centralized processing type framework, and the following problems exist when the monitored object is analyzed and processed by centralized computing resources. On the aspect of system architecture, mass video data are transmitted to a computing center for processing, so that the analysis and response of terminal data are time-delayed, and when high risk levels such as fighting, crowding and trampling, track falling and other events occur, the handling delay of workers can be caused by untimely system feedback. In the aspect of system functions, the traditional rail transit video monitoring system mainly collects and transmits video image data due to the fact that front-end camera equipment is weak in intelligent analysis capacity, and generally does not have the functions of behavior detection, large article leaving detection, platform boarding and alighting people number statistical analysis and the like, stations can only analyze feedback and work personnel through a system center to achieve station safety inspection, and the problems of low safety operation management efficiency, untimely management and poor flexibility exist. In order to solve the problem, the embodiment of the invention provides a rail transit video analysis control box. Fig. 1 is a schematic structural diagram of a track traffic video analysis control box according to an embodiment of the present invention, and as shown in fig. 1, the track traffic video analysis control box includes: the intelligent core board comprises a shell, an intelligent core board 1 and an intelligent carrier board 2;
the shell is provided with a first communication interface; the intelligent core board 1 and the intelligent carrier board 2 are arranged inside the shell; the intelligent core board 1 is connected with the first communication interface, acquires video information and audio information, performs intelligent security scene identification based on the video information and the audio information to obtain an identification result, and sends the identification result to a preset central server through the first communication interface; wherein the identification result is a scene needing to be alarmed;
the intelligent carrier plate 2 is connected with the intelligent core board 1 and used for protecting the rail transit video analysis control box, acquiring a recognition result and the running state of the intelligent core board 1 and giving an alarm based on the recognition result and the running state.
In a specific use process, the rail transit video analysis control box is connected with the switch through a first communication interface; video information and audio information that track video monitoring system gathered are obtained through first communication interface, directly carry out security protection scene intelligent recognition to video information and audio information, obtain the identification result, later send the identification result to central server through the switch, thus, track traffic video analysis control box can be directly after obtaining the video, directly carry out security protection scene intelligent recognition, obtain the identification result, avoid sending video information and audio information to central server, reduce data transmission's volume, ductility when reducing terminal data analysis and response production, avoid leading to the staff to deal with the delay because of the system feedback is not in time.
Wherein, intelligence core board 1 includes: the system comprises an audio and video information decoding module 11, a central processing unit 12 and a graphic processor 13;
the central processing unit is used for processing the original code stream to obtain high-order tensor data of video information and audio information;
the image processor is used for inputting the high-order tensor data into a preset neural network model to obtain a primary output low-order tensor;
the central processing unit is used for clustering the preliminary output low-order tensor to obtain image classification characteristics and audio classification characteristics based on timestamps;
the image classification features include: video passenger abnormal behavior characteristics, station abnormal environment characteristics, abnormal light brightness characteristics and large passenger flow characteristics;
the audio classification features include: a sound abnormal tone feature, an abnormal loudness feature, a loudness change rate feature, and a delay time feature;
fusing image classification features and audio classification features based on the timestamp, and identifying based on a preset rule to obtain an identification result;
specifically, the method comprises the following steps: the feature fusion rules are as follows:
as shown in the above table, fusing image classification features and audio classification features based on timestamps includes: fusing passenger behavior characteristics with sound tone characteristics; fusing passenger behavior characteristics and sound tone characteristics; fusing passenger behavior characteristics with sound loudness; fusing passenger behavior characteristics and loudness change rate characteristics; fusion of passenger behavior characteristics with sound delay time; fusing station environment characteristics and sound tone characteristics; fusing station environment characteristics and sound tone characteristics; fusing station environmental characteristics and sound loudness; fusing station environment characteristics and loudness change rate characteristics; fusing station environmental characteristics and sound delay time; fusing the light brightness characteristic and the sound tone characteristic; fusing the light brightness characteristic and the sound tone characteristic; fusing the brightness characteristic of light and the loudness of sound; fusing the light brightness characteristic and the loudness change rate characteristic; fusing the light brightness characteristic with the sound delay time; fusing a large passenger flow characteristic and a sound tone characteristic; fusing the characteristics of the large passenger flow and the characteristics of the sound timbre; fusing the characteristics of the large passenger flow and the loudness of sound; fusing the characteristics of the large passenger flow and the characteristics of the loudness change rate; fusing the characteristics of the large passenger flow and the sound delay time; in summary, the fusion quantity is the product of the quantity of the audio abnormal features and the quantity of the image classification features. For example, if the number of audio abnormality features is N and the number of image classification features is M, there are (N × M) kinds of fusions.
Furthermore, any k features of the (N + M) features can be selected for fusion. For example, referring to table N above, N is 5; m is 4; k takes a value from 2 to (N + M); for example, k may be 3; when k is 3, the feature to be fused may be any three of the above-mentioned 9 features.
The intelligent carrier plate 2 comprises: a micro control unit 21, a wireless communication module 22 and a protection device 23;
the micro control unit 21 is in communication connection with the intelligent core board 1, and is configured to acquire an operating state and an over-temperature state of the intelligent core board 1, and control a preset fan and an alarm unit based on the operating state and the over-temperature state; the wireless communication module 22 is configured to send the recognition result of the intelligent core board 1 to the mobile station service terminal, and the protection device 23 includes: overcurrent safety device, pin electrostatic protection device, two-way voltage level converter. The alarm unit comprises an indicator light and a sound production unit.
Specifically, a micro control unit MCU in an intelligent carrier plate adopts a mainstream mixed signal ARM Cortex-M4 processor STM32F303CBT6 series with a DSP and an FPU as a development platform, communicates with an intelligent core plate through a USB and a UART, receives instructions of the intelligent core plate through a DMA-UART module, and comprises a system running state, an over-temperature state and the like, the MCU controls the color and sound alarm of a fan and an indicator lamp according to the states, and can send control box information and video scene alarm information to a mobile station service terminal through a wireless communication module (WTM); in JWIS, TPS25200DRVR electronic fuse realizes the overcurrent protection of USB; SP3012-06UTG is an ESD protection device protecting each pin from electrostatic damage; the TXB0108PWR is provided with an 8-bit bidirectional voltage level converter with automatic direction induction and +/-15kV ESD protection, so that level unification between JWIC and JWIS is realized, and stable and reliable communication is ensured.
Fig. 2 is a schematic structural diagram of a track traffic video analysis control system according to an embodiment of the present invention; referring to his 2, a track traffic video analysis control system includes: the system comprises a central server 3 and a plurality of groups of track video monitoring systems 4; each group of track video monitoring systems 4 includes: the track video monitoring device 5, the switch 6 and the track traffic video analysis control box 7 provided by the embodiment of the invention;
the track video monitoring device 5 is used for acquiring audio information and video information and sending the audio information and the video information to the switch 6; the switch 6 sends the audio information and the video information to the rail transit video analysis control box 7; the rail transit video analysis control box 7 is used for identifying the audio information and the video information to obtain an identification result and sending the identification result to the switch 6; the switch 6 sends the identification result to the central server.
So set up, through at edge end video analysis, avoided carrying out the analysis of concentrating a large amount of video data transmission to station server, can realize video analysis near the equipment end to the accessible is wired, wireless multiple mode carries out information transmission, has improved track traffic video monitoring scene analysis's real-time, intelligent. Through the video analysis at the edge end, the construction and maintenance cost of the track traffic video monitoring system using the video analysis server is reduced. Through the intelligent video analysis of all kinds of scenes of edge end realization, and through the feature fusion of video and audio frequency, help promoting track traffic's safety guarantee ability, improve station operation management efficiency.
Specifically, the track traffic video analysis control box 7 is further configured to send a first control instruction to the controlled terminal based on the identification result, so as to control the controlled terminal to perform information broadcasting and event processing.
The controlled terminal includes: platform door, automatic escalator, vertical elevator, floodgate machine, broadcasting equipment and display screen.
Track traffic video analysis control system still includes: a mobile station service terminal;
the track traffic video analysis control box 7 is further configured to send the identification result to the mobile station service terminal.
So set up, can make relevant staff in time acquire the state of track traffic to in time handle.
The track video monitoring system 4 further comprises: a manual console; the manual control console is used for controlling the rail transit controlled terminal by a control instruction input by an employee; the track traffic video analysis control box 7 is further configured to send the identification result to the mobile station service terminal.
It should be noted that, in actual use, the system may have misjudgment, and at this time, manual intervention is required.
Further, the track traffic video analysis control box 7 is also used for acquiring a manual identifier fed back by an employee; the rail transit video analysis control box 7 is configured to send a second control instruction to the controlled terminal to control the controlled terminal to perform information broadcasting and event processing when the artificial identifier is an identifier for representing that the identification result is an emergency; when the artificial identification is used for representing that the identification result is wrong, recording the wrong identification result;
and the wrong recognition result and the corresponding artificial identification are used for retraining a module for intelligently recognizing the security scene in the rail transit video analysis control box 7.
It should be noted that the manual identifier may be obtained through manual control, or may be obtained based on the mobile station service terminal.
In summary, the embodiment of the present invention provides a track traffic video analysis control box 7 and a system, where the track traffic video analysis control box 7 is a track traffic security protection intelligent control box based on a high-performance, low-cost, and low-power microprocessor of NVIDIA Carmel ARM, and the control box hardware is composed of a JWIC (intelligent core board 1) and a JWIS (intelligent carrier board 2). Various video AI analysis algorithms are integrated and operated in the JWIC, and various video scenes can be quickly analyzed and processed at the edge terminal according to scene definition abnormal events. The JWIS is communicated with the JWIC to realize the functions of monitoring the state of the equipment, wirelessly transmitting data, and arranging sound and light alarm equipment. The intelligent control box for the rail transit security based on the edge calculation can replace a traditional video analysis server, and the real-time performance and the intelligence of the rail transit video monitoring are effectively improved.
The specific working flow of the rail transit video analysis control system provided by the embodiment of the invention is shown in fig. 3: and step 101, after acquiring a video stream and an audio stream, a station camera transmits the video stream and the audio stream to a rail transit video analysis control box based on edge calculation through a switch. And 102, transmitting the video stream and the Audio stream to a CPU through a JWIC (Java virtual interface) interface (GBE), and transmitting the video stream and the Audio stream to an Audio and video information decoding module (Audio & video decoder) through an internal DMA (direct memory access) for decoding to obtain an original code stream. And 103, preprocessing the original code stream by the CPU, wherein the preprocessing comprises processes of Resize, Crop, normalization, standardization and the like, tensor data suitable for deep neural network input are obtained, and preprocessing the audio code stream by the CPU comprises MFCC, MEL and the like, and audio features are obtained. And 104, inputting tensor data into the GPU, and obtaining a preliminary output tensor by the data through a neural network model preloaded by the GPU, such as target detection, abnormal audio detection and the like. And 105, transmitting the primary output tensor back to the CPU again, carrying out tensor clustering on the primary output tensor to obtain an image classification result based on the timestamp, simultaneously adding audio features based on the timestamp to fuse the image, and classifying the identified scenes based on a management method and station customization requirements. And step 106, carrying out data packing on the image grading and classification results, packaging the image grading and classification results into an Http data stream, sending the Http data stream to a mobile station service terminal based on the special wireless B-trunk/5G for rail transit, or sending the Http data stream to a central server side based on CAN/RS485 for alarm information confirmation, and simultaneously sending out sound and light alarm by the equipment. And 107, if the alarm information is accurate, further constructing a knowledge graph about the alarm scene disposal process and linkage. According to the station scene risk level, on one hand, the alarm information is released through a PIS system and broadcasting through a mobile terminal station APP and a server terminal, and on the other hand, a PIS screen, a platform door or broadcasting equipment which is closest to the position of the event scene is selected according to the video analysis result to release the information; such as serious risk events like fire, terrorist attack, flood and the like, and equipment emergency cooperative linkage control is realized through linkage event related equipment such as platform doors, escalators, vertical elevators, gates, videos and the like; and on the other hand, manual intervention and treatment of the station are simultaneously adopted. And step 108, if the alarm information is inaccurate, manually marking, and storing the scene as a knowledge base for the GPU neural network model to continue training and optimizing.
The embodiment of the invention also provides a rail transit video analysis control method, which is applied to a rail transit video analysis control box, wherein the rail transit video analysis control box is arranged in one-to-one correspondence with the rail video monitoring devices, and referring to fig. 4, the rail transit video analysis control method comprises the following steps:
optionally, the track traffic video analysis control method further includes:
Wherein the controlled terminal includes: platform doors, escalators, vertical elevators, gates, broadcasting equipment and display screens;
and step 205, sending the identification result to a preset mobile station service terminal.
The specific implementation process of the method provided by the embodiment of the present invention and the related description of the track traffic video analysis control box and the track traffic video analysis control system provided by the embodiment of the present invention are not repeated herein.
Fig. 5 is a flowchart illustrating a track traffic video analysis control method according to another embodiment of the present invention. Referring to fig. 5, the track traffic video analysis control method provided in the embodiment of the present invention specifically includes: a plurality of cameras (camera 1 to camera N) collect videos; the rail transit video analysis control box acquires a video;
303, training and primarily classifying video features and audio features by the GPU through a preloaded neural network;
wherein step 302 and step 303 are executed cooperatively.
307, emitting an audible and visual alarm through the equipment;
wherein, the step 308 can be performed by the urban rail transit special wireless B-trunC/5G.
wherein step 309 may be performed by a wired RS 485/CAN.
313, realizing emergency cooperative linkage control of equipment through linkage event related equipment such as platform doors, escalators, vertical elevators, gates, videos and the like, for serious risk events such as fire, terrorist attacks, floods and the like;
and step 314, on the other hand, simultaneously adopting station manual intervention and treatment.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes commands for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A rail transit video analysis control box, characterized by comprising: the intelligent core board comprises a shell, an intelligent core board and an intelligent carrier board;
the shell is provided with a first communication interface;
the intelligent core board and the intelligent carrier board are arranged inside the shell;
the intelligent core board is connected with the first communication interface, video information and audio information are obtained, intelligent security scene identification is carried out on the basis of the video information and the audio information, an identification result is obtained, and the identification result is sent to a preset central server through the first communication interface; wherein the identification result is a scene needing to be alarmed;
the intelligent carrier plate is connected with the intelligent core board and used for protecting the rail transit video analysis control box, acquiring a recognition result and the running state of the intelligent core board and giving an alarm based on the recognition result and the running state;
wherein, intelligence core board includes: the system comprises an audio and video information decoding module, a central processing unit and a graphic processor;
the central processor is respectively connected with the audio and video information decoding module and the graphic processor;
the audio and video information decoding module is used for acquiring the video information and the audio information and decoding the video information and the audio information to obtain an original code stream;
the central processing unit is used for processing the original code stream to obtain high-order tensor data of video information and audio information;
the image processor is used for inputting the high-order tensor data into a preset neural network model to obtain a primary output low-order tensor;
the central processing unit is used for clustering the preliminary output low-order tensor to obtain image classification characteristics and audio classification characteristics based on the timestamp, fusing the image classification characteristics and the audio classification characteristics based on the timestamp, and identifying based on a preset rule to obtain an identification result; the image classification features include: video passenger abnormal behavior characteristics, station abnormal environment characteristics, abnormal light brightness characteristics and large passenger flow characteristics; the audio classification features include: a sound abnormal tone feature, an abnormal loudness feature, a loudness change rate feature, and a delay time feature;
the intelligence support plate includes: the device comprises a micro control unit, a wireless communication module and a protection device;
the micro control unit is in communication connection with the intelligent core board and is used for acquiring the running state and the over-temperature state of the intelligent core board and controlling a preset fan and an alarm unit based on the running state and the over-temperature state;
the wireless communication module is used for sending the identification result of the intelligent core board to a mobile station terminal;
the protection device includes: an over-current fuse, a pin electrostatic protection device, and a bi-directional voltage level shifter.
2. The track traffic video analysis control box according to claim 1, characterized in that the alarm unit comprises an indicator light and a sound emitting unit.
3. The track traffic video analysis control box according to claim 1, wherein the intelligent core board and the intelligent carrier board are communicatively connected through a USB communication module and/or a UART communication module.
4. A rail transit video analysis control system, characterized by comprising: the system comprises a central server and a plurality of groups of track video monitoring systems; each group of track video monitoring system comprises: a track video monitoring device, a switch and a track traffic video analysis control box according to any one of claims 1 to 3;
the track video monitoring device is used for acquiring audio information and video information and sending the audio information and the video information to the switch;
the switch sends the audio information and the video information to the rail transit video analysis control box;
the rail transit video analysis control box identifies the audio information and the video information to obtain an identification result, and sends the identification result to the switch;
and the switch sends the identification result to the central server.
5. The track traffic video analysis and control system according to claim 4, wherein the track traffic video analysis and control box is further configured to send a first control instruction to the controlled terminal based on the recognition result to control the controlled terminal to perform information broadcasting and event processing;
the controlled terminal includes: platform door, automatic escalator, vertical elevator, floodgate machine, broadcasting equipment and display screen.
6. The track traffic video analysis control system according to claim 5, further comprising: a mobile station service terminal;
and the track traffic video analysis control box is also used for sending an identification result to the mobile station service terminal.
7. The track traffic video analysis and control system according to claim 4, wherein the track video monitoring system further comprises: a manual console;
the manual control console is used for controlling the control instruction input by the staff so as to control the rail transit controlled terminal
And the track traffic video analysis control box is also used for sending an identification result to the mobile station service terminal.
8. The track traffic video analysis and control system according to claim 4, wherein the track traffic video analysis and control box is further configured to obtain a manual identification fed back by an employee;
the rail transit video analysis control box is used for sending a second control instruction to the controlled terminal to control the controlled terminal to broadcast information and process events when the artificial identification is used for representing that the identification result is an emergency; when the artificial identification is used for representing that the identification result is wrong, recording the wrong identification result;
and the wrong recognition result and the corresponding artificial identification are used for retraining a module for intelligently recognizing the security scene in the track traffic video analysis control box.
9. A rail transit video analysis control method applied to the rail transit video analysis control box of the rail transit video analysis control system as claimed in claim 6, the rail transit video analysis control method comprising:
acquiring video information and audio information;
based on the video information and the audio information, performing intelligent identification on a security scene to obtain an identification result;
sending the identification result to the central server through a first communication interface; wherein the identification result is a scene needing to be alarmed;
sending the identification result to a mobile station service terminal through a wireless communication module; and the identification result is a scene needing alarming and emergency treatment.
10. The track traffic video analysis and control method according to claim 9, further comprising:
based on the identification result, sending a control instruction to a controlled terminal in the rail transit video analysis control system to control the controlled terminal to broadcast information and process events;
wherein the controlled terminal includes: platform doors, escalators, vertical elevators, gates, broadcasting equipment and display screens;
and sending the identification result to a preset mobile station service terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210002246.7A CN114390156A (en) | 2022-01-04 | 2022-01-04 | Rail transit video analysis control box, system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210002246.7A CN114390156A (en) | 2022-01-04 | 2022-01-04 | Rail transit video analysis control box, system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114390156A true CN114390156A (en) | 2022-04-22 |
Family
ID=81200639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210002246.7A Pending CN114390156A (en) | 2022-01-04 | 2022-01-04 | Rail transit video analysis control box, system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114390156A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115379286A (en) * | 2022-10-24 | 2022-11-22 | 通号通信信息集团有限公司 | Intelligent video analysis box, intelligent video analysis system and method |
CN115767040A (en) * | 2023-01-06 | 2023-03-07 | 松立控股集团股份有限公司 | 360-degree panoramic monitoring automatic cruise method based on interactive continuous learning |
CN116409348A (en) * | 2023-04-03 | 2023-07-11 | 北京全路通信信号研究设计院集团有限公司 | Rail transit flexible grouping platform door safety protection and linkage control method |
-
2022
- 2022-01-04 CN CN202210002246.7A patent/CN114390156A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115379286A (en) * | 2022-10-24 | 2022-11-22 | 通号通信信息集团有限公司 | Intelligent video analysis box, intelligent video analysis system and method |
CN115767040A (en) * | 2023-01-06 | 2023-03-07 | 松立控股集团股份有限公司 | 360-degree panoramic monitoring automatic cruise method based on interactive continuous learning |
CN116409348A (en) * | 2023-04-03 | 2023-07-11 | 北京全路通信信号研究设计院集团有限公司 | Rail transit flexible grouping platform door safety protection and linkage control method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114390156A (en) | Rail transit video analysis control box, system and method | |
CN109747682B (en) | Rail transit weak current integration system | |
CN101795395B (en) | System and method for monitoring crowd situation | |
CN109451040A (en) | Internet of things networking system and network-building method based on edge calculations | |
CN109801420B (en) | Multi-concurrent face recognition access control system based on classification algorithm and recognition method thereof | |
CN203849870U (en) | Wireless network-based traffic flow monitoring and signal lamp intelligent control system | |
CN109283897A (en) | A kind of wisdom power plant comprehensively monitoring center intelligent monitoring implementation method | |
CN104038952A (en) | Emergency prediction method and system | |
CN103067514A (en) | Cloud computing resource optimization method and cloud computing resource optimization system used for video mointoring and analysis system | |
CN214704896U (en) | AI-based video snapshot device for dangerous actions of intelligent construction site | |
CN106529787A (en) | Subway energy management system based on face detection technology | |
CN111160537B (en) | Crossing traffic police force resource scheduling system based on ANN | |
CN106710253A (en) | High-reliability intelligent intersection traffic control system and control method | |
CN111815275A (en) | Road transportation integrated system | |
CN117392852B (en) | Cloud computing resource scheduling optimization system oriented to big data analysis | |
CN217849510U (en) | Rail transit video analysis control box and system | |
CN109740663A (en) | A kind of dredging abortion system and method based on depth AI algorithm | |
CN116128678A (en) | Intelligent campus emergency response system | |
CN113470797A (en) | Intelligent hospital management system | |
CN112053550A (en) | Networking type pedestrian monitoring and guiding system | |
NL2031721B1 (en) | Intelligent hospital management system | |
CN110867086A (en) | Urban road construction traffic organization management system | |
CN111008922A (en) | Hui-Zhi-an comprehensive management and public security robot and operation method thereof | |
CN109711650A (en) | A kind of police strength scheduling system based on visualization technique | |
CN202043236U (en) | Real-time monitoring system for vehicle-mounted passenger flow based on 3G (third generation) network video transmission |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |