Open Access Open Access  Restricted Access Subscription or Fee Access

Vehicle Detection System using SVM Classification and HAAR Filter

Colins Antony, E. Konguvel

Abstract


Vehicle detection is very much important in avoiding accidents and for traffic monitoring. Various features such as colors, edges are used for vehicle detection. Gaussian mixture models(GMM) is used for background removal .The method of detection consists of training phase and detection phase. In both the training phase and detection phase we are using the same features for extraction. Afterwards the extracted features are used to classify whether it is a vehicle pixel or a non vehicle pixel using SVM. To improve the detection we are using the haar features. Detection in this approach is solenly based on pixels.

Keywords


GMM, HAAR, SVM, EM, Color Transform

Full Text:

PDF

References


Cai. L, Ge. C, Zhao.MY and Yang. M (2009) „Fast tracking of object contour based oncolor and texture‟ Int. J. Pattern Recognit Artif‟ Intell.,Volume. 23,no. 7, pp. 1421-1438

Jianguang Lou, Tieniu Tan, Weiming Hu, Hao Yang, And Steven J. Maybank (2005)„ 3-D Model Based Vehicle Tracking‟ IEEE Transactions On Image Processing, Volume 14 no. 10,pp. 1561–1569.

Luo - Wei Tsai, Jun-Wei Hsieh, And Kao-Chin Fan (2007.) „Vehicle Detection Using Normalized Color And Edge Map‟ IEEE Trans. Image Process., Volume 16, no. 3, pp.850–864.

Manjunathi B.S And W.Y. Ma (1996) „Texture Features for browsing and retrieval of image data „IEEE Trans. Pattern Anal. Mach. Intell., Volum. 18, no. 8 pp. 837–842

Yamaguchi K, Watanabe A and Naito T(2008) „Road region estimation using a sequence of monocular images‟ in Proc. 19th Int. Conf. Pattern Recognit., 2008, pp. 1–4.

F. Canny, ―A computational approach to edge detection,ᴧ IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-8, no. 6, pp. 679– 698, Nov. 1986.

Zehang Sun, George Bebis and Ronald Miller, ―Quantized Wavelet Features and Support Vector Machines for On -Road Vehicle Detection, Computer Vision Laboratory, Department of Computer Science, University of Nevada

C. Papageorgiou and T. Poggio, ―A trainable system for object detection, " International Journal of Computer Vision, vol. 38, no. 1,pp. 15-33, 2000.

Jon Arróspide And Luis Salgado(2013) „Log-VehicleVerification‟ IEEE transactions on image processing, Volume. 22, no. 6.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.