CN110599776A - Traffic data processing system - Google Patents
Traffic data processing system Download PDFInfo
- Publication number
- CN110599776A CN110599776A CN201910977127.1A CN201910977127A CN110599776A CN 110599776 A CN110599776 A CN 110599776A CN 201910977127 A CN201910977127 A CN 201910977127A CN 110599776 A CN110599776 A CN 110599776A
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- face
- image
- information
- 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
Classifications
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Abstract
The invention discloses a traffic data processing system, which comprises a face acquisition module and a vehicle information base, wherein the face acquisition module is connected with an image comparison module, the image comparison module is connected with a criminal face image acquisition base for comparison, the vehicle information base extracts vehicle information, the manual decision module transmits the information to a vehicle inspection module, and the vehicle inspection module transmits the vehicle information to a route planning module; the invention collects and transmits the images of the personnel in the vehicle to the image comparison module through the image collection device for information comparison and extraction, the manual decision module effectively combines the machine and the people, reduces the possibility of recognition errors of the machine, the vehicle inspection module carries out on-site interception on the vehicle and carries out the fastest capture on the suspicious personnel in connection with the nearest police place, and the suspicious personnel are prevented from escaping by taking the vehicle due to the search of police arrangement data.
Description
Technical Field
The invention relates to the field of traffic data management, in particular to a traffic data processing system.
Background
In recent years, various identification systems are continuously designed and manufactured along with the continuous development of science and technology, the number of accompanying crimes is also continuously increased, criminals often escape in a mode of leaving the scene most quickly after committing a crime, wherein the vehicle taking or driving is the best mode, the existing traffic data processing system cannot perform face matching on persons who shoot the interior of the vehicle one by one, only can monitor the existing traffic road conditions, the function of capturing can only identify the vehicle, and the crimes often escape when the criminals are in good opportunity, so that huge resistance is brought to capturing work.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
The present invention is directed to a traffic data processing system to solve the above problems.
In order to achieve the purpose, the invention provides the following technical scheme: a traffic data processing system comprises a face acquisition module and a vehicle information base, wherein the face acquisition module is connected with an image comparison module, the image comparison module is connected with a face image acquisition base of a criminal, the image comparison module judges similarity after comparing with faces of the criminal in the face image acquisition base of the criminal, the vehicle information base transmits extracted vehicle information to a manual decision module, the manual decision module transmits the information to a vehicle inspection module, and the vehicle inspection module transmits the vehicle information to a route planning module;
the face acquisition module uses a road section camera to shoot the face of a person in the vehicle to acquire a face image, and then transmits face image acquisition information to the image comparison module of the control center;
the image comparison module compares the face image acquired by the face acquisition module with the face of the criminal in the criminal face image acquisition library through a face recognition technology, and calculates and outputs a result of similarity;
the vehicle information base is used for extracting vehicle information shot by the road section camera, namely identifying the vehicle through the color and the mark characteristics of the vehicle and transmitting the vehicle information to the manual decision module;
the manual decision module is used for deciding the vehicle information sent by the vehicle information base and the face information acquired by the face acquisition module;
the route planning module is used for simulating a vehicle traveling route of a criminal, and automatically planning an optimal intercepting route and a catching route;
the vehicle inspection module is used for displaying suspected vehicle information in real time on a toll station or a front-end LED screen, intercepting the suspected vehicle information on the toll station, and controlling a road section camera to carry out real-time detection and information transmission.
Preferably, the face acquisition module comprises a high-definition camera and a photo cutting device, and the photo cutting device only acquires faces.
Preferably, the face acquisition module performs denoising processing on the image through a wavelet denoising technology, and the wavelet denoising technology method reserves most of wavelet coefficients containing signals and can better keep image details.
Preferably, the image comparison module adopts a face recognition method of elastic image matching, so that the influence of expression change on face recognition can be effectively overcome.
Preferably, the image comparison module calculates the image comparison information, outputs whether the similarity is greater than sixty percent, extracts the vehicle information when the similarity is greater than sixty percent, and cancels data storage when the similarity is less than sixty percent.
Preferably, the manual decision module is used for judging the image contrast of the plurality of groups of criminals and the vehicle information sent back and determining the information to be wanted.
Preferably, the route planning module judges the possibility of vehicle traveling through the possibility of traveling of the route map, and plans the optimal blocked route.
Compared with the prior art, the invention has the following beneficial effects: the invention transmits the collected figure of the personnel in the vehicle to the figure comparison device by the image collection device, when the face figure is cut, the cut image is compared with the image in the face collecting library of the criminal, thereby enlarging the detection range of the trace of the criminal, meanwhile, the added manual decision-making module effectively combines the machine with the person, thereby not only improving the capture speed of criminals to the maximum extent, but also reducing the situation of recognition errors of the machine caused by some objective reasons, the vehicle inspection module can perform on-site interception under the condition of identifying available vehicles and simultaneously contact the nearest police place to capture suspicious personnel at the highest speed, so that the suspicious personnel are prevented from running by taking the airplane due to the search of police arrangement data, meanwhile, the route planning module greatly reduces the problem that the capturing speed is slowed down due to road conditions.
Drawings
Fig. 1 is a schematic structural diagram of a traffic data processing system according to an embodiment of the present invention.
Fig. 2 is a flow chart of a face acquisition module.
Detailed Description
As shown in fig. 1, a traffic data processing system of the present invention includes a face acquisition module and a vehicle information base, in order to realize the facial acquisition of the personnel in the vehicle, the facial acquisition module is electrically connected with the image comparison module, in order to realize the face comparison of the personnel in the vehicle, an image comparison module is connected with a face image acquisition library of criminals, in order to determine the picture information, the image comparison module is used for judging the similarity after comparing with the face of the criminal in the criminal face image acquisition library, in order to extract the vehicle information, extracting vehicle information from a vehicle information base, and in order to determine a computer calculation result, transmitting the extracted vehicle information to a manual decision module by using the vehicle information base, transmitting the information to a vehicle inspection module by using the manual decision module, and transmitting the vehicle information to a route planning module by using the vehicle inspection module;
in order to realize the face acquisition of personnel in the vehicle, the face acquisition module is used for shooting the face of the personnel in the vehicle by using a road section camera to acquire a face image, and then the face image acquisition information is transmitted to an image comparison module of a control center;
in order to determine whether the image acquisition is a criminal, the image comparison module compares the face image acquired by the face acquisition module with the face of the criminal in the criminal face image acquisition library through a face recognition technology, and calculates and outputs a result of similarity;
in order to know the vehicle information, the vehicle information base is used for extracting the vehicle information shot by the road section camera, namely the vehicle is identified through the color and the mark characteristics of the vehicle, and the vehicle information is transmitted to the manual decision module;
in order to determine the accuracy of computer calculation, the artificial decision module is used for deciding the vehicle information sent by the vehicle information base and the face information acquired by the face acquisition module;
in order to facilitate the investigation of the vehicle, the route planning module is used for simulating the vehicle traveling route of a criminal, and automatically planning an optimal intercepting route and a pursuing route;
in order to catch criminals, the vehicle checking module is used for displaying suspect vehicle information on a toll station or a front-end LED screen in real time, intercepting the suspect vehicle information on the toll station, and controlling a road section camera to perform real-time detection and information transmission.
Preferably, the face acquisition module comprises a high-definition camera and a photo cutting device, and the photo cutting device only acquires faces.
Through the scheme: the face of a person in the vehicle can be collected, and the contrast detection of interference pictures of other environmental factors in the pictures can be reduced.
As shown in fig. 2, the face acquisition module performs denoising processing on the image through a wavelet denoising technology, which retains most of wavelet coefficients containing signals and can better retain image details; the image denoising in the wavelet analysis mainly comprises 3 steps of (1) performing wavelet decomposition on an image signal. (2) And carrying out threshold quantization on the high-frequency coefficient subjected to hierarchical decomposition. (3) The image signal is reconstructed using two-dimensional wavelets.
Through the scheme: can be effectual carry out edulcoration processing to the picture for the more clear contrast of being convenient for of image.
Preferably, the image comparison module adopts a face recognition method matched with an elastic image, so that the influence of expression change on face recognition can be effectively overcome.
Through the scheme: the elastic image matching method defines a distance with certain invariance to the normal human face deformation in a two-dimensional space, and adopts an attribute topological graph to represent the human face, wherein any vertex of the topological graph comprises a feature vector which is used for recording the information of the human face near the position of the vertex. The method combines the gray characteristic and the geometric factor, can allow the image to have elastic deformation during comparison, has good effect on overcoming the influence of expression change on recognition, and does not need a plurality of samples to train for a single person.
Preferably, the image comparison module calculates the image comparison information, outputs whether the similarity is greater than sixty percent, extracts the vehicle information when the similarity is greater than sixty percent, and cancels data storage when the similarity is less than sixty percent.
Through the scheme: the information processing method and the information processing device can effectively screen the information, and prevent criminals from being separated from detection and pursuit due to too low similarity.
Preferably, the manual decision module is used for judging the image contrast of the plurality of groups of criminals and the vehicle information sent back and determining the information to be wanted.
Through the scheme: the compared multiple groups of information can be judged and confirmed manually, and errors in computer calculation can be prevented.
Preferably, the route planning module judges the possibility of vehicle traveling according to the traveling possibility of the route map, and plans the optimal blocked route.
Through the scheme: can effectual quick arrest criminal personnel, prevent that criminal personnel from escaping.
As shown in fig. 2, for the steps of the image acquisition process: s1, firstly, photographing personnel in the vehicle through a road section camera, and then acquiring a human face image in the picture;
s2, processing the image, firstly, denoising the image by a wavelet denoising technology, carrying out median filtering, and carrying out the following processing force process: and replacing the value of a certain point in the image with the median value of the neighborhood of the point to achieve the filtering effect. Let f (x, y) represent the gray value of the image pixel, and the median filter with the filter window W is defined as: the function of the median filter is implemented by using the mediafilt 2 function in the (x, y) ═ Med { G (x, y) }, (x, y) ∈ WMATLAB, which is specifically as follows:
I＝medfilt２(J,[xy])
I＝medfilt２(J)
I＝medfilt２(J,[xy])
image J is median filtered and the boundary is replaced by a 0 representing black, then the edge median is the value of [ x, y ]/2.
S3, face recognition, feature extraction, and Principal Component Analysis (PCA) algorithm, which is a multivariate statistical analysis method for analyzing the sample data by using the feature vector to achieve the purpose of reducing dimension. I.e. high-dimensional eigenvectors are transformed into low-dimensional vectors by the eigenvector matrix, this method only loses some secondary information and the primary information is preserved. The PCA decomposes and maps data in a measurement space to a low-dimensional feature space by means of a Karhunen Gloeve transform;
s4, storing a large number of face features in a face training test library for storing the features;
and S5, comparing the acquired face image with a large number of features stored in a face training test library to determine the identity information of the image acquiring person.
The working principle is as follows: shooting persons in a vehicle through a high-definition camera in a face acquisition module, cutting facial images of the persons in the vehicle through a face cutting device, storing image data shot by the high-definition camera into a memory card through a storage module after face acquisition, transmitting facial information to an image comparison module through a data transmission device after the acquired image data, calling a criminal face image acquisition library when the facial image data passes through the image comparison module, starting an image comparison system to estimate the similarity through a face feature recognition device and a face feature comparison device, directly abandoning the image data when the similarity is lower than 60%, switching to a manual decision module through a picture receiving device when the similarity reaches more than 60%, and further comparing the images through a decision starting device, whether the arresting is carried out or not is decided manually, after the arresting is decided, basic data of the vehicle is called from a vehicle database, a GPS positioning system is started to call specific information of the vehicle, the vehicle is monitored in real time, a vehicle inspection module is started to display information of the suspected vehicle in real time on a toll gate or a front-end LED screen and intercept the information at the toll gate, a route planning module is started to plan a fastest route reaching the scene according to the current road condition, so that the arresting speed of criminals can be increased to the maximum extent, the condition of recognition errors of the machine caused by some objective reasons can be reduced, the vehicle inspection module can carry out scene blocking under the condition that the vehicle can be recognized, simultaneously the suspicious personnel can be arrested at the fastest speed by contacting with the nearest police, and the situation that the suspicious personnel run away from the machine due to the finding of police arrangement data is avoided, meanwhile, the route planning module greatly reduces the problem that the capturing speed is slowed down due to road conditions.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that various changes, modifications and substitutions can be made without departing from the spirit and scope of the invention as defined by the appended claims. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A traffic data processing system comprises a face acquisition module and a vehicle information base, and is characterized in that the face acquisition module is electrically connected with an image comparison module, the image comparison module is electrically connected with a face image acquisition base of a criminal, the image comparison module judges similarity after comparing with faces of the criminal in the face image acquisition base of the criminal, the vehicle information base transmits extracted vehicle information to a manual decision module, the manual decision module transmits the information to a vehicle inspection module, and the vehicle inspection module transmits the vehicle information to a route planning module;
the face acquisition module uses a road section camera to shoot the face of a person in the vehicle to acquire a face image, and then transmits face image acquisition information to the image comparison module of the control center;
the image comparison module compares the face image acquired by the face acquisition module with the face of the criminal in the criminal face image acquisition library through a face recognition technology, and calculates and outputs a result of similarity;
the vehicle information base is used for extracting vehicle information shot by the road section camera, namely identifying the vehicle through the color and the mark characteristics of the vehicle and transmitting the vehicle information to the manual decision module;
the manual decision module is used for deciding the vehicle information sent by the vehicle information base and the face information acquired by the face acquisition module;
the route planning module is used for simulating a vehicle traveling route of a criminal, and automatically planning an optimal intercepting route and a catching route;
the vehicle inspection module is used for displaying suspected vehicle information in real time on a toll station or a front-end LED screen, intercepting the suspected vehicle information on the toll station, and controlling a road section camera to carry out real-time detection and information transmission.
2. The traffic data processing system of claim 1, wherein the face capture module comprises a high definition camera and a photo cropping device that captures only the face.
3. The traffic data processing system of claim 1, wherein the face capture module denoises the image using wavelet denoising.
4. The traffic data processing system of claim 1, wherein the image comparison module employs a face recognition method of elastic image matching.
5. The traffic data processing system of claim 1, wherein the image comparison module calculates image comparison information, outputs whether the similarity is greater than sixty percent, extracts vehicle information when the similarity is greater than sixty percent, and cancels data storage when the similarity is less than sixty percent.
6. The traffic data processing system of claim 1, wherein the human decision module is configured to determine and check the information of the image contrast of the criminals and the vehicle information sent back.
7. The traffic data processing system of claim 1, wherein the route planning module determines the likelihood of vehicle travel and plans an optimal blocked route based on the likelihood of vehicle travel through the route map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977127.1A CN110599776A (en) | 2019-10-15 | 2019-10-15 | Traffic data processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977127.1A CN110599776A (en) | 2019-10-15 | 2019-10-15 | Traffic data processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110599776A true CN110599776A (en) | 2019-12-20 |
Family
ID=68867284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910977127.1A Pending CN110599776A (en) | 2019-10-15 | 2019-10-15 | Traffic data processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110599776A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090226047A1 (en) * | 2008-03-04 | 2009-09-10 | Chi-Chang Yu | Apparatus and Method of Processing Image and Human Face Detection System using the smae |
| CN103077611A (en) * | 2013-01-06 | 2013-05-01 | 山东鼎讯智能交通科技有限公司 | Road vehicle recording system with face identification and safety belt detection functions |
| CN103699677A (en) * | 2013-12-31 | 2014-04-02 | 河海大学常州校区 | Criminal track map drawing system and method based on face recognition |
| CN106326240A (en) * | 2015-06-18 | 2017-01-11 | 中兴通讯股份有限公司 | An object moving path identifying method and system |
| CN109409212A (en) * | 2018-09-12 | 2019-03-01 | 中国人民解放军国防科技大学 | Face recognition method based on cascade BGP |
| CN109886204A (en) * | 2019-02-25 | 2019-06-14 | 武汉烽火众智数字技术有限责任公司 | A kind of Multidimensional Awareness system based on the application of big data police service |
| CN110135236A (en) * | 2019-03-21 | 2019-08-16 | 云南路普斯数据科技有限公司 | A kind of video face identification method based on wavelet transformation and neural network algorithm |
| CN110321804A (en) * | 2019-06-11 | 2019-10-11 | 福建亿安智能技术有限公司 | One kind is combined based on face and electronic Car license recognition and carries out identity authentication method |
-
2019
- 2019-10-15 CN CN201910977127.1A patent/CN110599776A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090226047A1 (en) * | 2008-03-04 | 2009-09-10 | Chi-Chang Yu | Apparatus and Method of Processing Image and Human Face Detection System using the smae |
| CN103077611A (en) * | 2013-01-06 | 2013-05-01 | 山东鼎讯智能交通科技有限公司 | Road vehicle recording system with face identification and safety belt detection functions |
| CN103699677A (en) * | 2013-12-31 | 2014-04-02 | 河海大学常州校区 | Criminal track map drawing system and method based on face recognition |
| CN106326240A (en) * | 2015-06-18 | 2017-01-11 | 中兴通讯股份有限公司 | An object moving path identifying method and system |
| CN109409212A (en) * | 2018-09-12 | 2019-03-01 | 中国人民解放军国防科技大学 | Face recognition method based on cascade BGP |
| CN109886204A (en) * | 2019-02-25 | 2019-06-14 | 武汉烽火众智数字技术有限责任公司 | A kind of Multidimensional Awareness system based on the application of big data police service |
| CN110135236A (en) * | 2019-03-21 | 2019-08-16 | 云南路普斯数据科技有限公司 | A kind of video face identification method based on wavelet transformation and neural network algorithm |
| CN110321804A (en) * | 2019-06-11 | 2019-10-11 | 福建亿安智能技术有限公司 | One kind is combined based on face and electronic Car license recognition and carries out identity authentication method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103824070B (en) | A kind of rapid pedestrian detection method based on computer vision | |
| KR100974293B1 (en) | METHOD AND SYSTEM FOR AUTOMATED FACE DETECTION and Recognition | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| CN107016322B (en) | Method and device for analyzing followed person | |
| CN110414441B (en) | Pedestrian track analysis method and system | |
| CN110781798B (en) | Vehicle-mounted suspect locking system based on raspberry group and face recognition | |
| CN112396658B (en) | Indoor personnel positioning method and system based on video | |
| CN109711318B (en) | Multi-face detection and tracking method based on video stream | |
| WO2019114145A1 (en) | Head count detection method and device in surveillance video | |
| CN109359577B (en) | System for detecting number of people under complex background based on machine learning | |
| CN104881643B (en) | A kind of quick remnant object detection method and system | |
| CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
| CN108986472A (en) | One kind turns around vehicle monitoring method and device | |
| KR20170015639A (en) | Personal Identification System And Method By Face Recognition In Digital Image | |
| CN111753651A (en) | Subway group abnormal behavior detection method based on station two-dimensional crowd density analysis | |
| KR101092472B1 (en) | Video indexing system using surveillance camera and the method thereof | |
| Chumuang et al. | Face detection system for public transport service based on scale-invariant feature transform | |
| CN111091110A (en) | Wearing identification method of reflective vest based on artificial intelligence | |
| CN107368770A (en) | A kind of frequent customer's automatic identifying method and system | |
| RU2315352C2 (en) | Method and system for automatically finding three-dimensional images | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| CN111950499A (en) | Method for detecting vehicle-mounted personnel statistical information | |
| CN110599776A (en) | Traffic data processing system | |
| CN113743380B (en) | Active tracking method based on video image dynamic monitoring | |
| CN110598716A (en) | Personnel attribute identification method, device and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |