Pedestrian Detection Based on Bag-of-Visual-Words and SVM Method

Abstract:

We propose a pedestrian detection approach based on bag-of-visual-words and SVM method. The image feature extraction and representation are extremely challenging tasks in pedestrian detection approach, which could impact the performance of pedestrian detection. In this paper, we propose that visual vocabulary is built by clustering SIFT features of image to visual words. Classification is taken using the support vector machine (SVM), for SVM having good non-linear function learning and generalization capability solid. Numerical experiments in the evaluation of INRIATREC pedestrian data sets and the action movies demonstrate that our method shows better performance.

• Periodical: Applied Mechanics and Materials (Volume 678)
• Pages: 189-192
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.678.189
• Online since: October 2014
• Authors: Jun Li, Yuan Jiang Liao, Hong Mei Zhang
• Keywords: Bag-of-Visual-Words, Pedestrian Detection, SIFT, SVM

References

[1] C. G. M. Snoek, B. Huurnink, et al: Adding Semantics to Detectors for Video Retrieval. Journal of IEEE TRANSACTIONS ON MULTIMEDIA, vol. 9, no. 5, pp.975-986, (2007).

DOI: 10.1109/tmm.2007.900156

[2] X. Yuan, X. Y. Wei, Y. D. Song: Pedestrian Detection for Counting Applications Using a Top-View Camera. IEICE TRANSACTIONS on Information and Systems, Vol. E94-D, no. 6, pp.1269-1277, (2011).

DOI: 10.1587/transinf.e94.d.1269

[3] R. Benenson, M. Mathias, et al: Pedestrian detection at 100 frames per second. Conference on Computer Vision and Pattern Recognition (CVPR),  pp.2903-2910, (2012).

DOI: 10.1109/cvpr.2012.6248017

[4] Y. W. Xu, X. B. Cao, H. Qiao. An Efficient Tree Classifier Ensemble-Based Approach for Pedestrian Detection. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 41, no. 1, pp.107-117, (2011).

DOI: 10.1109/tsmcb.2010.2046890

[5] Benenson R, Mathias M, Timofte R, et al: Pedestrian detection at 100 frames per second. Computer Vision and Pattern Recognition, 2012 IEEE Conference on. IEEE, 2012: 2903-2910.

DOI: 10.1109/cvpr.2012.6248017

[6] N. Dalal, B. Triggs: Histogram of oriented gradient for human detection. In CVPR, (2005).

[7] P. Dollár, Z. Tu Perona, and S. Belongie: Integral channel features. In BMVC, (2009).

[8] S. Bauer, U. Brunsmann, and S. Schlotterbeck-Macht: FPGA Implementation of a HOG-based Pedestrian Recognition System. presented at the Tagungsband zum Workshop der Multiprojekt-Chip-Gruppe (MPC Workshop), Karlsruhe, 2009, p.49-58S.

[9] Maji, A.C. Berg, and J. Malik: Classification using intersection kernel SVMs is efficient. In CVPR, (2008).

[10] Cheng Hong，Zheng Nan-Ning，Qin Jun-Jie: Pedestrian detection using sparse Gabor filter and support vector machine. In: Proceedings of IEEE Intelligent Vehicles Symposium. Vienna，Austria，2005: 583-587.

DOI: 10.1109/ivs.2005.1505166

[11] M. Szaras，A. Yoshizawa，M. Yamamoto，J. Ogata: Pedestrian detection with convolutional neural networks. In: Proceedings of IEEE Intelligent Vehicles Symposium. Las Vegas，Nevada. IEEE，2005: 224-229.

DOI: 10.1109/ivs.2005.1505106

[12] P. Dollar, C. Wojek, B. Schiele, and P. Perona Pedestrian Detection: An Evaluation of the State of the Art. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012; 34 (4): 743.

DOI: 10.1109/tpami.2011.155

[13] D. G. Lowe : Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, vol. 60, no. 2, pp.91-110, (2004).

DOI: 10.1023/b:visi.0000029664.99615.94

[14] F. F. Li, P Perona: A Bayesian Hierarchical Model for Learning Natural Scene Categories. In Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition, 2005. 524–531.

DOI: 10.1109/cvpr.2005.16

[15] J. Yang, Y. G. Jiang, et al: Evaluating Bag-of-Visual-Words Representations in Scene Classification. In ACM Multimedia Information Retrieval (MIR), 2007. 197-206.

DOI: 10.1145/1290082.1290111

[16] C. W. Hsu, C. C. Chang, and C. J. Lin: A Practical Guide to Support Vector Classification. Available at http: /www. csie. ntu. edu. tw/ cjlin.