Urban Road Congestion Recognition Using Multi-Feature Fusion of Traffic Images
DOI: 10.23977/jaip.2016.11002 | Downloads: 103 | Views: 6439
Hua Cui 1, Pannong Li 1, Zefa Wei 1, Xinxin Song 1, Lu Guo 1
1 School of Information Engineering, Chang’an University, Xi’an 710064, China
Corresponding AuthorLu Guo
Traffic congestions happen more and more frequently on the current urban roads. Detecting the congestion rapidly and effectively can avoid the second damages. In this paper, we use the traffic images as data source instead of the videos to detect traffic congestions, which have the advantages of low cost and big probability to be applied widely. Firstly, the interest region of the traffic images are calibrated manually, and then the image features in the interest region are abstracted, including the sift corner, gray histogram variance, gray level co-occurrence matrix of energy and contrast. Finally, BP neural network is used to realize image multi-feature fusion, and to classify the traffic condition described by the traffic images. The simulation results show that the method can recognize the traffic condition with the accuracy of 95%.
KEYWORDSTraffic condition recognition, Image processing, Feature extraction, Sift corner, BP neural network
CITE THIS PAPER
Lu, G. , Hua, C. , Pannong, L. , Zefa, W. and Xinxin, S. (2016) Urban Road Congestion Recognition Using Multi-Feature Fusion of Traffic Images. Journal of Artificial Intelligence Practice (2016) 1: 20-24.
 H.Payne. Development and Testing of incident-detection algorithm: research methodology and detailed results.Washington,Federal Highway Administration, US, Department of Transportation, vol. 2 (1976).
 M.Liepins,Vehicle detection using non-invasive magnetic wireless sensor network. Telecommunications Forum (TELFOR) (2013), p. 601-604.
 J.Bai, Research of Traffic condition Identification Based on Probe Vehicle. Intelligence Information Processing and Trusted Computing, 2010 International Symposium (2001), p.309-311.
 L.Xu, Reserch on Traffic congestion detection using real-time video. Applied Mechanics and Materials, vol. 241-244 (2013), p. 2100-2106.
 S.G.Park, GGO Nodule Volume-Preserving Nonrigid Lung Registration Using GLCM Texture Analysis.Biomedical Engineering, IEEE Transactions, vol. 58 (2011), issue. 10, p.2885-2894.
 H.Jeon, Grey-level context-driven histogram equalisation, IET image proceeding,Vol. 10 (2016), issue.5, p. 349-358.
 L.C.Chiu , Fast SIFT Design for Real-Time Visual Feature Extraction,IEEE Transactions on Image Processing, Vol:22 (2013), Issue: 8, p. 3158-3167.
 F.Z.Zhang, Ensemble detection model for profile injection attacks in collorative recomender systems based on BP neural network, IET Information Security, vol. 9 (2015), issue. 1 , p.24-31.