Estimate the Size of the Moving Vehicle LWH Based on Machine Vision

Abstract:

The main content of this paper is based on the estimate of LWH(length width and height) dimensions of a machine vision moving vehicle. The information of a vehicle’s length width and height is an important parameter to monitor Road. To achieve non-contact rapid detection of the parameter of a moving vehicle’s size, can effectively improve the efficiency of the road monitoring and provide effective technical means for China's road transport management department. First get the vehicle in sequences image and extract the vehicle from background. Then, we transform the two-dimensional image to three-dimensional image with a simple projection model for getting the parameters of the length, width and height of the vehicle. Experiments show that the accuracy of the test results of this algorithm is relatively high.

• Periodical: Applied Mechanics and Materials (Volumes 716-717)
• Pages: 1631-1635
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.716-717.1631
• Online since: December 2014
• Authors: Jie Wang*, Tong Qiang Li
• Keywords: Image Processing, Image Projection Model, Three-Dimensional Characters

References

[1] SUETENS P, FU P, HANSON A. J. Computational strategies for object recognition [J] / ACM Computing Surveys, 1992, 24(1), pp.52-62.

DOI: 10.1145/128762.128763

[2] ZH L W, LI S W, LI L ZH. 3d object recognition and pose estimation using kernel pca [C]. Proceedings of the Third International Conference on Machine Learning and Cybernetics. Shanghai, China, 2004: 3258-3262.

DOI: 10.1109/icmlc.2004.1378598

[3] JUN H, ZHAO W X, FANG Z S, et. al. View-based 3d object recognition using wavelet multi-scale singular value decomposition and support vector machine[C]. Beijing: Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition. 2007: 1428-1432.

DOI: 10.1109/icwapr.2007.4421659

[4] PONTIL M, VERRI A. Support vector machines for 3d object recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(6): 637-646.

DOI: 10.1109/34.683777

[5] H. Jun, W. Xi-Zhao, Z. Su-Fang, et. al. View-based 3d object recognition using wavelet multistage singular-value decomposition and support vector machine. Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition. Beijing, China, 2007: 1428-1432.

DOI: 10.1109/icwapr.2007.4421659

[6] D. Roth, M. H. Yang, N. Ahuja. Learning to recognize three- dimensional objects. Neural Computation, 2002, 14(5): 1071-1103.

DOI: 10.1162/089976602753633394

[7] Jazayeri A, Cai H, Zheng J Y. Vehicle detection and tracking in car video based on motion model [J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 12(2): 583-595.

DOI: 10.1109/tits.2011.2113340

[8] Atev S, Papanikolopoulos N. Multi-view 3D vehicle tracking with a constrained filter[C]. IEEE International Conference on., 2008: 2277-2282.

DOI: 10.1109/robot.2008.4543553