CN109766743A - A kind of intelligent bionic policing system - Google Patents
A kind of intelligent bionic policing system Download PDFInfo
- Publication number
- CN109766743A CN109766743A CN201811388309.7A CN201811388309A CN109766743A CN 109766743 A CN109766743 A CN 109766743A CN 201811388309 A CN201811388309 A CN 201811388309A CN 109766743 A CN109766743 A CN 109766743A
- Authority
- CN
- China
- Prior art keywords
- module
- pedestrian
- vehicle driver
- violation
- behavior
- 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.)
- Granted
Links
- 239000011664 nicotinic acid Substances 0.000 title claims abstract description 17
- 239000000203 mixture Substances 0.000 claims abstract description 38
- 230000003287 optical effect Effects 0.000 claims abstract description 7
- 230000006855 networking Effects 0.000 claims description 31
- 230000005540 biological transmission Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 230000003542 behavioural effect Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 10
- 230000000306 recurrent effect Effects 0.000 claims description 10
- 238000003786 synthesis reaction Methods 0.000 claims description 10
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 210000004218 nerve net Anatomy 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 49
- 238000007726 management method Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000283070 Equus zebra Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of intelligent bionic policing systems, including hardware components and software section, the hardware components are made of system hardware input interface and system hardware output interface, the hardware input interface is by video input module, signal lamp input module and acquisition input module composition, the system hardware output interface is by bionical output module, optical signal output module and image information output module composition, it is integrated into bionical police model, come to pedestrian, the road traffic law violation behavior of non-motor vehicle driver is effectively managed, reach the management effect of emulation police, realize the further improvement of road traffic order, promote the road traffic regulation consciousness of people.The bionical police model of this set software-driven has the function of intelligent bionic, alternative labor management, the daily management for realizing the round-the-clock road traffic law violation behavior to pedestrian and non motorized vehicle driver.
Description
Technical field:
The invention belongs to policing system technical field, in particular to a kind of intelligent bionic policing system.
Background technique:
Road traffic law violation behavior phenomenon is still generally existing in today, and to this phenomenon, domestic many cities still pass through people
Work is managed.With the development of society, there is an urgent need to a kind of new management methods to promote the efficiency of management and management effect.?
The artificial intelligence epoch of today, by intelligentized bionical management mode, realize to instantaneity road traffic law violation involved party into
The effective supervision and management of row, is the inexorable trend of current social development.
Summary of the invention:
The object of the invention is that providing a kind of intelligent bionic policing system to solve the above-mentioned problems, solve existing
Equipment there are the shortcomings that.
To solve the above-mentioned problems, the present invention provides a kind of technical solutions:
A kind of intelligent bionic policing system, including hardware components and software section, the hardware components are connect by system hardware input
Mouth and system hardware output interface composition, the hardware input interface is by video input module, signal lamp input module and acquisition
Input module composition, the system hardware output interface are exported by bionical output module, optical signal output module and image information
Module composition, the software section is by main execution module, video input module, convolutional neural networks module, Recognition with Recurrent Neural Network
Module, pedestrian and non motorized vehicle driver's number identification module, pedestrian and non motorized vehicle driver track synthesis module, Hang Renhe
Non-motor vehicle driver's behavior prediction module, pedestrian and non motorized vehicle driver's behavioral value module, signal lamp rule process mould
Block, violation or praise behavior processing module, violation or praise behavior display module, violation or praise behavior voice broadcast module,
Unlawful practice party's appearance acquisition module, networking identification module, violation praise behavior record module, networking data same
It walks module, real-time video transmission module and real-time video and saves timing removing module composition.
Preferably, the video input module is connect with convolutional neural networks module, the convolutional neural networks module
It is connect with Recognition with Recurrent Neural Network module, the Recognition with Recurrent Neural Network module and pedestrian and non motorized vehicle driver number identification module
Connection, the non-motor vehicle driver number identification module are connect with pedestrian and non motorized vehicle driver track synthesis module, institute
State non-motor vehicle driver track synthesis module respectively with pedestrian and non motorized vehicle driver's behavior prediction module and pedestrian and non-
The connection of vehicle driver behavioral value module, the pedestrian and non motorized vehicle driver behavior prediction module and pedestrian and non-machine
Motor-car driver's behavioral value module is connect with violation or praise behavior processing module, and the violation or praise behavior handle mould
Block is connect with signal lamp rule process module, and the signal lamp rule process module is connect with beacon signal input module, institute
State in violation of rules and regulations or praise behavior processing module respectively in violation of rules and regulations or praise behavior display module, violation or praise behavior voice broadcast mould
Block, unlawful practice party's appearance acquisition module are connected with real-time video transmission module, and the unlawful practice party appearance is adopted
Collect module to connect with networking identification module, the networking identification module connection and violation or praise behavior record module
Connection, the violation or praise behavior record module connection are connect with networking data synchronization module, the real-time video transmission mould
Block saves timing removing module with real-time video and connect.
Preferably, the video input module and acquisition input module by pedestrian detection camera, high speed pedestrian with
Non-motor vehicle driver detects camera preprocessing module and high speed pedestrian and non-motor vehicle driver detects camera and shoots mould
Block composition.
Preferably, the signal lamp input module is defeated by signal lamp analog signal parsing module, signal lamp analog signal
Enter module, computer, signal lamp and TTL and turns USB module composition composition.
Preferably, the optical signal output module shows that image dividing processing module and HD video are shown by HD video
Display screen composition.
Preferably, described image message output module is by gigabit switch, optical fiber receiver-transmitter module, the synchronous guarantor of networking data
Storing module and networking pedestrian and non-motor vehicle recognition of face detection module form.
Preferably, the violation or praise behavior video display module are made of computer and display screen, the violation
Or behavior voice broadcast module is praised to be made of computer and sound equipment, the unlawful practice party appearance acquisition module is by calculating
Machine and high-definition camera composition.
It is removed preferably, the real-time video transmission module, networking data synchronization module and real-time video save timing
Module is made of computer and central server, and the networking identification module is by computer, central server and center
Database composition.
Beneficial effects of the present invention: this project by machine learning model and practices phase on the basis of artificial intelligence technology
In conjunction with improved intelligent Neural Network model, and the research to training data, in conjunction with hardware design exploitation, imitation is handed over
The daily control of traffic and road behavior of logical police.Specifically, by intelligent monitoring and alarming, road traffic law violation information collection, face
Identification, intelligent voice prompt, intelligent sound prevention, intelligent sound praise, video capture, preset whistle are reminded, are manually cried out
The modes such as words, the exposure of the identity of road traffic law violation party, are integrated into bionical police model, thus to pedestrian, non-maneuver
The road traffic law violation behavior of vehicle driver is effectively managed, and the management effect of emulation police is reached, and realizes road traffic order
The further improvement of sequence promotes the road traffic regulation consciousness of people.The bionical police model of this set software-driven has intelligence imitative
Raw function, alternative labor management, the day for realizing the round-the-clock road traffic law violation behavior to pedestrian and non motorized vehicle driver
Often management.
Detailed description of the invention:
Detailed description will be given by the following detailed implementation and drawings by the present invention for ease of explanation,.
Fig. 1 is that whole system software and hardware combining modularization of the invention connects block diagram；
Fig. 2 is software algorithm flow diagram of the invention.
Specific embodiment:
As shown in Figs. 1-2, present embodiment uses following technical scheme: a kind of intelligent bionic policing system, including hardware
Part and software section, the hardware components are made of system hardware input interface and system hardware output interface, the hardware
Input interface is made of video input module, signal lamp input module and acquisition input module, the system hardware output interface
Be made of bionical output module, optical signal output module and image information output module, the software section by main execution module,
Video input module, convolutional neural networks module, Recognition with Recurrent Neural Network module, pedestrian and non motorized vehicle driver number identification mould
Block, pedestrian and non motorized vehicle driver track synthesis module, pedestrian and non motorized vehicle driver's behavior prediction module, pedestrian and non-
Behavior processing module, violation or praise are praised in vehicle driver behavioral value module, signal lamp rule process module, violation
Behavior display module, violation praise behavior voice broadcast module, unlawful practice party's appearance acquisition module, networking identity to know
Other module, violation praise behavior record module, networking data synchronization module, real-time video transmission module and real-time video to save
Module composition is removed in timing.
Wherein, the video input module is connect with convolutional neural networks module, the convolutional neural networks module with follow
The connection of ring neural network module, the Recognition with Recurrent Neural Network module and pedestrian and non motorized vehicle driver number identification module connect
It connects, the pedestrian and non motorized vehicle driver number identification module and pedestrian and non motorized vehicle driver track synthesis module connect
Connect, non-motor vehicle driver track synthesis module respectively with pedestrian and non motorized vehicle driver's behavior prediction module and pedestrian
Connected with non-motor vehicle driver's behavioral value module, the pedestrian and non motorized vehicle driver behavior prediction module and pedestrian and
Non-motor vehicle driver's behavioral value module is connect with violation or praise behavior processing module, at the violation or praise behavior
Reason module is connect with signal lamp rule process module, and the signal lamp rule process module and beacon signal input module connect
Connect, the violation or praise behavior processing module respectively in violation of rules and regulations or praise behavior display module, violation or praise behavior voice
Broadcasting module, unlawful practice party's appearance acquisition module are connected with real-time video transmission module, the unlawful practice party
Appearance acquisition module is connect with networking identification module, the networking identification module connection and violation or praise behavior note
Module connection is recorded, the violation or praise behavior record module connection are connect with networking data synchronization module, the real-time video
Transmission module saves timing removing module with real-time video and connect.
Wherein, the video input module and acquisition input module are by pedestrian detection camera, high speed pedestrian and non-machine
Motor-car driver detects camera preprocessing module and high speed pedestrian and non-motor vehicle driver detects camera shooting module group
At.
Wherein, the signal lamp input module inputs mould by signal lamp analog signal parsing module, signal lamp analog signal
Block, computer, signal lamp and TTL turn USB module composition composition, and the level conversion convenient for inputting beacon signal is that USB can
The end TX of USB is become high level output to computer when particularly as being input 5V voltage by the form of transmission.
Wherein, the optical signal output module module shows that image dividing processing module and HD video are shown by HD video
Display screen composition, convenient for showing video in real time on outdoor big display screen.
Wherein, described image message output module module is by gigabit switch, optical fiber receiver-transmitter module, the synchronous guarantor of networking data
Storing module and networking pedestrian and non-motor vehicle recognition of face detection module form,.
Wherein, the violation or praise behavior video display module are made of computer and display screen, the violation or table
Behavior voice broadcast module is raised to be made of computer and sound equipment, the unlawful practice party appearance acquisition module by computer and
High-definition camera composition, convenient for the unlawful practice captured to be identified with red block, praise behavior marked by blue box
Know, and is the violation captured or the praise corresponding voice of behavior and is broadcasted on sound equipment.
Wherein, the real-time video transmission module, networking data synchronization module and real-time video save timing and remove module
It is made of computer and central server, the networking identification module is by computer, central server and central data
Library composition, collected appearance is connect by network transmission into central database, is compared and sentences with the data in database
Determine the specific identity information of appearance.
Each module embodiment mode of software is as follows:
Main execution module: main packet: nothing
Main class: nothing
Primary function: main () is without input, no output；
Video input module:
Main packet: video_capture
Main class: video_capture
Primary function: _ _ init__ (id): input: int, output: video_capture class
The number of id corresponding to camera needed for inputting can be obtained video_capture class corresponding to the camera
Primary function: read (): input: nothing exports float array
Obtain the current time picture of itself class
Primary function: release (): input: nothing, output: nothing
Close the resource occupation of itself class；
Convolutional neural networks module:
Main packet: conv_net
Main class: conv_net, bbox
Primary function: _ _ init__ (net_model): input: model file, output: nothing
Model file needed for inputting produces corresponding conv_net class
Primary function: result (input): input: float array exports float array
Obtain the calculated characteristic value of convolutional neural networks corresponding to the current time picture of itself class；
Recognition with Recurrent Neural Network module:
Main packet: relative_net
Main class: relative_net
Primary function: _ _ init__ (net_model): input: model file, output: nothing
Model file needed for inputting produces corresponding relative_net class
Primary function: result (input): input: float array exports bbox class
Obtain the calculated current goal region pair of Recognition with Recurrent Neural Network corresponding to the current time picture of itself class
The bbox class object answered；
Pedestrian and non motorized vehicle driver's number identification module:
Main packet: tracker
Main class: track, tracker
Primary function: _ _ init__ (): input: nothing, output: nothing
Create track and tracker class
Primary function: predict (): input: nothing, output: bbox class
Obtain the bbox predicted value of later moment in time corresponding to the previous moment bbox of itself class
Primary function: update (bbox): input: bbox class, output: track class
Bbox in tracker class is updated, and exports corresponding track class；
Pedestrian and non motorized vehicle driver track synthesis module:
Main packet: tracker_mix
Main class: track_mix, tracker_mix, tracking
Primary function: _ _ init__ (): input: nothing, output: nothing
Create track_mix and tracker_mix class
Primary function: update (track): input: track class, output: track_mix class
Track in tracker_mix class is updated, and exports corresponding track_mix class
Primary function: tracking (): input: nothing, output: tracking class
Track in tracker_mix class is called and obtains the track of reference numeral people；
Pedestrian and non motorized vehicle driver's behavior prediction module:
Main packet: predict_net
Main class: predict_net, action
Primary function: _ _ init__ (net_model): input: model file, output: nothing
Model file needed for inputting produces corresponding predict_net class
Primary function: result (tracking): input: tracking class exports action class
Obtain the behavior type that neural computing corresponding to the track of the current number people of itself class goes out；
Pedestrian and non motorized vehicle driver's behavioral value module:
Main packet: action_detection
Main class: action_detection, action
Primary function: _ _ init__ (): input: nothing, output: nothing
Create action_detection class
Primary function: detection (track): input: track class, output: track_mix class
Track in tracker_mix class is updated, and exports corresponding track_mix class
Primary function: tracking (tracking): input: tracking class exports action class
Obtain behavioral value result corresponding to the track of the current number people of itself class；
Signal lamp rule process module:
Main packet: traffic_light_deal
Main class: traffic_light_deal, traffic_light_status
Primary function: _ _ init__ (com_id): input: string, output: nothing
Traffic_light_deal class is created by corresponding com value
Primary function: deal (): input: nothing, output: traffic_light_status class
Rs 232 serial interface signal in itself class is read out, and is converted to the corresponding traffic_light_ of output according to actual needs
Status class；
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
In violation of rules and regulations or praise behavior processing module:
Main packet: action_deal
Main class: action_deal, deal_result
Primary function: _ _ init__ (): input: nothing, output: nothing
Create action_deal class
Primary function: deal (traffic_light_status, action): input: traffic_light_status class,
Action class, output: deal_result class
The processing result for the pedestrian is judged according to the action of current signal light situation and current pedestrian；
In violation of rules and regulations or praise behavior display module:
Main packet: deal_show
Main class: deal_show
Primary function: _ _ init__ (): input: nothing, output: nothing
Create deal_show class
Primary function: show (frame, bbox): input: float array, bbox class, output: nothing
Current video picture affix personage's frame is display together on screen
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
In violation of rules and regulations or praise behavior voice broadcast module:
Main packet: sound_output
Main class: sound_output
Primary function: _ _ init__ (com_id): input: string, output: nothing
Sound_output class is created by corresponding com value
Primary function: play (deal_result): input: deal_result class, output: nothing
The behavior of required casting is played on corresponding sound equipment
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
Unlawful practice party's appearance acquisition module:
Main packet: face_shot
Main class: face_shot
Primary function: _ _ init__ (com_id): input: string, output: nothing
Face_shot class is created by corresponding com value
Primary function: shot (bbox): input: bbox class, output: nothing
The appearance of people in corresponding frame is shot and editing comes out
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
Networking identification module:
Main packet: on_net_detection
Main class: on_net_detection, callback
Primary function: _ _ init__ (url): input: string, output: nothing
Face_shot class is created by corresponding url value
Primary function: upload (picture, callback): input: float array, callback class, output: nothing
The picture taken is uploaded, and upload result is learnt by callback
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
In violation of rules and regulations or praise behavior record module:
Main packet: deal_result_save
Main class: deal_result_save
Primary function: _ _ init__ (): input: nothing, output: nothing
Create deal_result_save class
Primary function: save (deal_result, fp): input: deal_result class, file class, output: nothing
Corresponding behavior is recorded, and is saved under specified directory
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
Networking data synchronization module:
Main packet: deal_result_update
Main class: deal_result_update, callback
Primary function: _ _ init__ (url): input: string, output: nothing
Deal_result_update class is created by corresponding url value
Primary function: update (deal_result, callback): input: deal_result class, callback class, output:
Nothing
Corresponding behavior is uploaded on given server, and upload result is learnt by callback
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
Real-time video transmission module:
Main packet: video_transmit
Main class: video_transmit, video_transmit_server
Primary function: _ _ init__ (ip): input: string, output: nothing
Video_transmit class is created by corresponding ip value
Primary function: play (): input: nothing, output: float array
The desktop of host on corresponding ip is transferred to server end
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class；
Real-time video saves timing and removes module:
Main packet: video_save_and_clear
Main class: video_save_and_clear
Primary function: _ _ init__ (): input: nothing, output: nothing
Create video_save_and_clear class
Primary function: save_and_clear (video, fp, time): input: float array, file class, int, output: nothing
Corresponding video is saved in designated position, sets erasing time, adjusts back and deletes when to the time
Primary function: release (): input: nothing exports nothing
Close the resource occupation of itself class.
It is specific: a kind of intelligent bionic policing system, in use, pedestrian and non motorized vehicle is driven by video input module
It sails people's behavior to be filmed, step is only shooting video herein, not any video processing, then convolutional neural networks module
Feature extraction in image is come out, judges that the object of current location is that pedestrian and non motorized vehicle is driven according to the feature of extraction
People is sailed, Recognition with Recurrent Neural Network module will be corresponding by extracting feature progress context in convolutional neural networks module, to judge
Whether the pedestrian and non motorized vehicle driver in present image is pedestrian and non motorized vehicle driver, theoretically directly passes through convolution
Neural network is the same to judge whether it is pedestrian and non motorized vehicle driver, but since pedestrian and non motorized vehicle driver exists
It blocks and the problems such as angular transformation, therefore the picture before being added can effectively solve this problem, by picture before
To reach better effect in the reflection to current image of other features, then pedestrian and non motorized vehicle number identification module will be by rolling up
Product neural network output result be compared with previous width picture, comparison pedestrian and non motorized vehicle driver position to it is similar
Degree, to obtain pedestrian and non motorized vehicle driver in previous width picture in the position of next picture piece, and by front and back image
In same people indicated with same number, then pedestrian and non motorized vehicle driver track synthesis module by the pedestrian of same number and
Non-motor vehicle driver is attached in the position where every figure, to obtain the movement rail of pedestrian and non motorized vehicle driver
Mark, pedestrian and non motorized vehicle driver's behavior prediction module are refreshing with full connection by the motion profile of pedestrian and non motorized vehicle driver
The rule obtained after network carries out pre-training, that is, the motion profile for meeting certain rule will obtain corresponding prediction in this module
Output, pedestrian and non motorized vehicle driver's behavioral value module is by the motion profile of pedestrian and non motorized vehicle driver and specific
Condition be compared, such as judge pedestrian and non motorized vehicle driver whether in region, judge that pedestrian and non motorized vehicle is driven
It sails people whether to pass by certain line etc., in violation of rules and regulations or praises behavior processing module by concrete behavior or predictive behavior and the rule that pre-sets
It compares, for example, if then determining that it is rushed when the pedestrian and non motorized vehicle driver in red light across zebra stripes enters line
Red light, such, the input of beacon signal is converted to specific event by signal lamp rule process module, such as signal is defeated
Enter a high level and represent current red light, of this sort conversion, beacon signal input module inputs beacon signal
Level conversion is the form that USB can be transmitted, and when particularly as being input 5V voltage, the end TX of USB is become high level output to meter
Calculation machine, in violation of rules and regulations or praise behavior video display module the unlawful practice captured is identified with red block, praise behavior by
Blue box is identified, while video is shown in real time on outdoor big display screen, violation or praise behavior voice broadcast mould
Block is by the violation captured or praises the corresponding voice of behavior and broadcasts on sound equipment, and unlawful practice party's appearance acquires mould
The front of the party identified by red block is carried out capture shooting with high-definition camera by block, by computer after the completion of picture catching
Its appearance is acquired, real-time video transmission module by with reddish blue frame video connect by network transmission to central server with
Just it carries out manual review and verifies, networking identification module connects collected appearance by network transmission to central database
In, the specific identity information of appearance is compared and determined with the data in database, in violation of rules and regulations or praises behavior record module will
In violation of rules and regulations or the picture of the corresponding pedestrian detection camera interception of behavior and the picture of high-definition camera front shooting interception is praised to connect
By network transmission to central database to give over to criminal record, networking data synchronization module will to upload successful picture, video etc. from
It is removed in computer, real-time video, which saves timing, which removes module, to remove from central database more than the video for saving duration.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention, the technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention, the claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (8)
1. a kind of intelligent bionic policing system, including hardware components and software section, it is characterised in that: the hardware components are by being
System hardware input interface and system hardware output interface composition, the hardware input interface are defeated by video input module, signal lamp
Enter module and acquisition input module composition, the system hardware output interface by bionical output module, optical signal output module and
Image information output module composition, the software section by main execution module, video input module, convolutional neural networks module,
Recognition with Recurrent Neural Network module, pedestrian and non motorized vehicle driver's number identification module, pedestrian and non motorized vehicle driver track are closed
At module, pedestrian and non motorized vehicle driver's behavior prediction module, pedestrian and non motorized vehicle driver's behavioral value module, signal
Lamp rule process module, violation praise behavior processing module, violation or praise behavior display module, violation or praise behavior language
Behavior record mould is praised in sound broadcasting module, unlawful practice party's appearance acquisition module, networking identification module, violation
Block, networking data synchronization module, real-time video transmission module and real-time video save timing and remove module composition.
2. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: the video input module and volume
Product neural network module connection, the convolutional neural networks module are connect with Recognition with Recurrent Neural Network module, the circulation nerve net
Network module is connect with pedestrian and non motorized vehicle driver's number identification module, the non-motor vehicle driver number identification module with
Pedestrian and non motorized vehicle driver track synthesis module connection, non-motor vehicle driver track synthesis module respectively with pedestrian
Connected with non-motor vehicle driver's behavior prediction module with pedestrian and non motorized vehicle driver's behavioral value module, the pedestrian and
Non-motor vehicle driver's behavior prediction module and pedestrian and non motorized vehicle driver's behavioral value module are gone with violation or praise
For processing module connection, the violation or praise behavior processing module are connect with signal lamp rule process module, the signal lamp
Rule process module is connect with beacon signal input module, the violation or praise behavior processing module respectively in violation of rules and regulations or table
It raises behavior display module, violation or praises behavior voice broadcast module, unlawful practice party's appearance acquisition module and regard in real time
The connection of frequency transmission module, the unlawful practice party appearance acquisition module are connect with networking identification module, the networking
Identification module connection in violation of rules and regulations or praise behavior record module connect, the violation or praise behavior record module connect and
The connection of networking data synchronization module, the real-time video transmission module save timing removing module with real-time video and connect.
3. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: the video input module and adopt
Collect input module and camera preprocessing module and height are detected by pedestrian detection camera, high speed pedestrian and non-motor vehicle driver
Fast pedestrian and non-motor vehicle driver detect camera shooting module composition.
4. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: the signal lamp input module by
Signal lamp analog signal parsing module, signal lamp analog signal input module, computer, signal lamp and TTL turn USB module composition
Composition.
5. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: the optical signal output module mould
Block shows that image dividing processing module and HD video display screen form by HD video.
6. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: described image message output module
It is examined by gigabit switch, optical fiber receiver-transmitter module, the synchronous preserving module of networking data and networking pedestrian and non-motor vehicle recognition of face
Survey module composition.
7. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: behavior view is praised in the violation
Frequency display module is made of computer and display screen, and the violation or praise behavior voice broadcast module are by computer and sound equipment group
At the unlawful practice party appearance acquisition module is made of computer and high-definition camera.
8. a kind of intelligent bionic policing system according to claim 1, it is characterised in that: the real-time video transmission mould
Block, networking data synchronization module and real-time video save timing removing module and are made of computer and central server, described
Networking identification module is made of computer, central server and central database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811388309.7A CN109766743B (en) | 2018-11-21 | 2018-11-21 | Intelligent bionic police system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811388309.7A CN109766743B (en) | 2018-11-21 | 2018-11-21 | Intelligent bionic police system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109766743A true CN109766743A (en) | 2019-05-17 |
| CN109766743B CN109766743B (en) | 2024-05-17 |
Family
ID=66449637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811388309.7A Active CN109766743B (en) | 2018-11-21 | 2018-11-21 | Intelligent bionic police system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109766743B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321823A (en) * | 2019-06-24 | 2019-10-11 | 杭州诚道科技股份有限公司 | Zebra stripes based on deep learning give precedence to the illegal secondary detection method of pedestrian |
| CN110796360A (en) * | 2019-10-24 | 2020-02-14 | 吉林化工学院 | Fixed traffic detection source multi-scale data fusion method |
| CN114023088A (en) * | 2021-11-03 | 2022-02-08 | 江苏尤特斯新技术有限公司 | Intelligent street-crossing signal lamp system and illegal behavior evidence-obtaining and warning method |
| CN114093172A (en) * | 2021-11-03 | 2022-02-25 | 中科智城(广州)信息科技有限公司 | Pedestrian passing method based on image recognition, terminal and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376246A (en) * | 2018-02-05 | 2018-08-07 | 南京蓝泰交通设施有限责任公司 | A kind of identification of plurality of human faces and tracking system and method |
-
2018
- 2018-11-21 CN CN201811388309.7A patent/CN109766743B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108376246A (en) * | 2018-02-05 | 2018-08-07 | 南京蓝泰交通设施有限责任公司 | A kind of identification of plurality of human faces and tracking system and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321823A (en) * | 2019-06-24 | 2019-10-11 | 杭州诚道科技股份有限公司 | Zebra stripes based on deep learning give precedence to the illegal secondary detection method of pedestrian |
| CN110796360A (en) * | 2019-10-24 | 2020-02-14 | 吉林化工学院 | Fixed traffic detection source multi-scale data fusion method |
| CN114023088A (en) * | 2021-11-03 | 2022-02-08 | 江苏尤特斯新技术有限公司 | Intelligent street-crossing signal lamp system and illegal behavior evidence-obtaining and warning method |
| CN114093172A (en) * | 2021-11-03 | 2022-02-25 | 中科智城(广州)信息科技有限公司 | Pedestrian passing method based on image recognition, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109766743B (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766743A (en) | A kind of intelligent bionic policing system | |
| CN103106250B (en) | Video monitoring intellectual analysis search method and system thereof | |
| US8457401B2 (en) | Video segmentation using statistical pixel modeling | |
| CN105027550B (en) | For handling visual information with the system and method for detecting event | |
| CN104506804B (en) | Motor vehicle abnormal behaviour monitoring device and its method on a kind of through street | |
| CN101631237B (en) | Video monitoring data storing and managing system | |
| CN104094279A (en) | Large-range-first cross-camera visual target re-identification method | |
| CN105975956A (en) | Infrared-panorama-pick-up-head-based abnormal behavior identification method of elderly people living alone | |
| CN100555348C (en) | Intelligent video monitoring system of bank self-aid apparatus | |
| CN101799876A (en) | Video/audio intelligent analysis management control system | |
| CN109063667B (en) | Scene-based video identification mode optimization and pushing method | |
| CN101635835A (en) | Intelligent video monitoring method and system thereof | |
| CN106559645B (en) | Monitoring method, system and device based on camera | |
| CN106203513A (en) | A kind of based on pedestrian's head and shoulder multi-target detection and the statistical method of tracking | |
| CN101835034A (en) | Crowd characteristic counting system | |
| CN109543631A (en) | A kind of fire image detection alarm method based on machine learning | |
| CN108769598A (en) | Across the camera video method for concentration identified again based on pedestrian | |
| CN108256447A (en) | A kind of unmanned plane video analysis method based on deep neural network | |
| CN104463125A (en) | DSP-based automatic face detecting and tracking device and method | |
| CN116153092B (en) | Tunnel traffic safety monitoring method and system | |
| CN107920223A (en) | A kind of object behavior detection method and device | |
| CN110290346A (en) | A kind of acquisition methods of the bidding video based on intelligent video analysis | |
| Tung et al. | Large-scale object detection of images from network cameras in variable ambient lighting conditions | |
| CN112749681A (en) | Violation detection method based on edge equipment and deep learning | |
| CN116597394A (en) | Railway foreign matter intrusion detection system and method based on deep learning |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221115 Address after: 223001 Intersection of Jingshi Road and Huaihe East Road, Huaiyin District, Huai'an City, Jiangsu Province Applicant after: Jiangsu Bitou Technology Co.,Ltd. Address before: No. 100, Huaihai North Road, Qinghe District, Huai'an City, Jiangsu Province 223001 Applicant before: Wang Mingzhi |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |