Abstract
In this paper, we propose a single SVM-based algorithm to classify moving objects inside videos and hence extract semantics features for further multimedia processing and content analysis. While standard SVM is a binary classifier and complicated procedures are often required to turn it into a multi-classifier, we introduce a new technique to map the output of a standard SVM directly into posterior probabilities of the moving objects via Sigmoid function. We further add a post-filtering framework to improve its performances of moving object classification by using a weighted mean filter to smooth the classification results. Extensive experiments are carried out and their results demonstrate that the proposed SVM-based algorithm can effectively classify a range of moving objects.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
References
Wender, S., Dietmayer, K.: An Adaptable Object Classification Framework. In: IEEE Intelligent Vehicles Symposium, pp. 150–155 (2006)
Lowe, D.: Distinctive Image Features from Scale-invariant Keypoints. International Journal of Computer Vision 60(1), 91–110 (2004)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR, vol. 1, pp. 886–893 (2005)
Viola, P., Jones, M., Snow, D.: Detecting Pedestrians Using Patterns of Motion and Appearance. In: ICCV, vol. 2, pp. 734–741 (2003)
Schneiderman, H., Kanade, T.: A Statistical Method for 3D Object Detection Applied for Faces and Cars. In: CVPR, vol. 1, pp. 746–751 (2000)
Burges, C.J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2(2), 121–167 (1998)
Zhang, H., Berg, A., Maire, M., Malik, J.: SVM-KNN: Discriminative Nearest Neighbor Classification for visual Category Recognition. In: CVPR, vol. 2, pp. 2126–2136 (2006)
Ravichandran, B., Gandhe, A., Smith, R., Mehra, R.: Robust Automatic Target Recognition Using Learning Classifier Systems. Information Fusion 8(3), 252–265 (2007)
Yang, T., Li, S.Z., Pan, Q., Li, J.: Real-time and Accurate Segmentation of Moving Objects in Dynamic Scene. In: Proceeding of the ACM 2nd international workshop on Video surveillance & sensor networks, pp. 136–143 (2004)
Dewan, M., Hossain, M.: Background Independent Moving Object Segmentation for Video Surveillance. IEICE Transactions on Communications E92-B(2), 585–598 (2009)
Hota, R.N., Venkoparao, V., Rajagopal, A.: Shape Based Object Classification for Automated Video Surveillance with Feature Selection. In: ICIT 2007, pp. 97–99 (2007)
Zhang, L., Li, S.Z., Yuan, X.T., Xiang, S.M.: Real-time Object Classification in Video Surveillance Based on Appearance Learning. In: CVPR 2007, pp. 1–8 (2007)
Lipton, A.J., Fujiyoshi, H., Patil, R.S.: Moving Target Classification and Tracking from Real-time Video. In: WACV 1998, pp. 8–14 (1998)
Berg, A., Berg, T., Malik, J.: Shape Matching and Object Recognition Using Low Distortion Correspondences. In: CVPR 2005, vol. 1, pp. 26–33 (2005)
Brown, L.M.: View Independent Vehicle/Person Classification. In: Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks, pp. 114–123 (2004)
Nguyen, H.T., Qiang, J., Smeulders, A.W.M.: Spatio-temporal Context for Robust Multitarget Tracking. IEEE Transaction on Pattern Analysis and Machine Intelligence 29(1), 52–64 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, Z., Jiang, J., Xiao, G. (2009). SVM-Based Classification of Moving Objects. In: Ślęzak, D., Grosky, W.I., Pissinou, N., Shih, T.K., Kim, Th., Kang, BH. (eds) Multimedia, Computer Graphics and Broadcasting. MulGraB 2009. Communications in Computer and Information Science, vol 60. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10512-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-10512-8_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10511-1
Online ISBN: 978-3-642-10512-8
eBook Packages: Computer ScienceComputer Science (R0)