Time filter

Source Type

Li B.,Traffic Management Research Institute of Ministry of Public Security | Feng C.,Traffic Management Research Institute of Ministry of Public Security | Zhu Z.,Traffic Management Research Institute of Ministry of Public Security | Miao J.,Traffic Management Research Institute of Ministry of Public Security
ICTE 2015 - Proceedings of the 5th International Conference on Transportation Engineering | Year: 2015

Traffic flow parameters detection is one of the most critical parts of the intelligent traffic management system in currently. With the continuous development of computer vision and image processing analysis technology constantly development, video detection technology in the traffic parameters testing is more and more attention. Video automatic detection technology utilization of computer vision, image processing and analysis, pattern recognition technology, compared with traditional detection technology induction loop detector, microwave radar detector and magnetometer detector, etc. The video automatic detection has many advantages, such as simple installation, convenient maintenance, not to harm the roadbed, low cost, high accuracy, and wide monitoring area. Firstly, the image sequence can be acquired through the video automatic detection equipment mounted over the road, and then two 2D spatial-temporal images, a panoramic view image and an epipolar plane image, are formed for each lane in this article. By using the methods of constructing a general epipolar plane image model, to reflect the vehicle surface characteristics and movement characteristics of the driveway. Then put forward the texture Canny texture edge detection algorithm of image based on Gabor filter, according to the texture edge detection of three steps: normalization processing, filtering processing and edge texture detection, analyzes the edge texture detection algorithm of epipolar plane image, and provides normalized epipolar plane image, presented the specific calculation method and formula of Canny texture edge detection based on Gabor filter. Finally, according to the graphics after processing, examines traffic flow parameters detection for traffic volume, vehicle speeds and lane occupancy and analyzes summary of the whole algorithm. © ASCE.


Zou T.,Changsha University | Zou T.,Changsha University of Science and Technology | Hu L.,Changsha University | Hu L.,Changsha University of Science and Technology | And 3 more authors.
Forensic Science International | Year: 2015

In order to analyzing the uncertainty in accident reconstruction, based on the theory of extreme value and the convex model theory, the uncertainty analysis problem is turn to an extreme value problem. In order to calculate the range of the dependent variable, the extreme value in the definition domain and on the boundary of the definition domain are calculated independently, and then the upper and lower bound of the dependent variable can be given by these obtained extreme values. Based on such idea and through analyzing five numerical cases, a simple algorithm for calculating the range of an accident reconstruction result was given; appropriate results can be obtained through the proposed algorithm in these cases. Finally, a real world vehicle-motorcycle accident was given, the range of the reconstructed velocity of the vehicle was calculated by employing the Pc-Crash, the response surface methodology and the new proposed algorithm, the range was [66.1-67.3] km/h. This research will provide another choice for uncertainty analysis in accident reconstruction. © 2015 Elsevier Ireland Ltd.


Wang M.,Key Laboratory of Ministry of Public Security for Road Traffic Safety | Jiang L.,Key Laboratory of Ministry of Public Security for Road Traffic Safety | Lu W.,Key Laboratory of Ministry of Public Security for Road Traffic Safety | Fang A.,Traffic Management Research Institute of Ministry of Public Security
Proceedings of 2015 IEEE International Conference on Progress in Informatics and Computing, PIC 2015 | Year: 2015

Feature extraction and recognition of a vehicle is always a popular research spot in the intelligent transportation system (ITS) area. Based on this technology, many applications, such as the license plate recognition, brand recognition, driving behavior understanding and so on, can be realized to improve the transportation management-control level. Unlike normal task-oriented vehicle recognition methods, a new feature extraction and recognition framework based on a component-model for vehicles is introduced in this paper, which extracts features from vehicle components with a coarse-to-fine mechanism. This kind of deep learned visual feature can be used for vehicle detection, license plate recognition and brand recognition. Furthermore, a component dataset including 110 different brands of vehicles is built up for evaluation. The proposed method obtained a good performance in the experimental result, which is significant for the practical application. © 2015 IEEE.


Lu W.,Traffic Management Research Institute of Ministry of Public Security | Lu W.,Nanjing University of Science and Technology | Jiang L.,Traffic Management Research Institute of Ministry of Public Security | Jiang L.,Nanjing University of Science and Technology | And 3 more authors.
Proceedings of 2015 IEEE International Conference on Progress in Informatics and Computing, PIC 2015 | Year: 2015

Unmanned Aerial Vehicles (UAVs) or the so-called drones are frequently used in various areas. However, their usage in Intelligent Transportation System (ITS) is limited. This paper demonstrates an air-ground integrated system for ITS, which consists of a drone in the sky side and a Closed-Circuit Television (CCTV) at roadside. Specifically, the space mapping between drone vision and CCTV vision is analyzed. At first, the drone GPS position is adjusted according to an open source map database. Then the camera parameters of CCTV are estimated according to drone visions. Finally, drone visions are projected into East-North-Up (ENU) space, while the CCTV visions are mapped into ENU space via Inverse Perspective Mapping (IPM). As a result, the mapping of air-ground integrated system is achieved. The experimental results verify the space mapping in an air-ground integrated system. © 2015 IEEE.


PubMed | Traffic Management Research Institute of ministry of Public Security and Hunan University of Science and Technology
Type: | Journal: Forensic science international | Year: 2015

In order to analyzing the uncertainty in accident reconstruction, based on the theory of extreme value and the convex model theory, the uncertainty analysis problem is turn to an extreme value problem. In order to calculate the range of the dependent variable, the extreme value in the definition domain and on the boundary of the definition domain are calculated independently, and then the upper and lower bound of the dependent variable can be given by these obtained extreme values. Based on such idea and through analyzing five numerical cases, a simple algorithm for calculating the range of an accident reconstruction result was given; appropriate results can be obtained through the proposed algorithm in these cases. Finally, a real world vehicle-motorcycle accident was given, the range of the reconstructed velocity of the vehicle was calculated by employing the Pc-Crash, the response surface methodology and the new proposed algorithm, the range was [66.1-67.3] km/h. This research will provide another choice for uncertainty analysis in accident reconstruction.

Loading Traffic Management Research Institute of Ministry of Public Security collaborators
Loading Traffic Management Research Institute of Ministry of Public Security collaborators