A Novel Fast Pedestrian Detection Method

Abstract:

This paper presents novel pedestrian detection approach in video streaming, which could process frames rapidly. The method is based on cascades of HOG-LBP (Histograms of Oriented Gradients-Local Binary Pattern), but combines non-negative factorization to reduce the length of the feature, aiming at realizing a more efficient way of detection, remedying the slowness of the original method. Experiments show our method can process faster than HOG and HOG-LBP, and more accurate than HOG, which has better performance in pedestrian detection in video streaming.

• Periodical: Applied Mechanics and Materials (Volumes 738-739)
• Pages: 538-541
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.738-739.538
• Online since: March 2015
• Authors: Fu Qiang Zhou, Yan Li*
• Keywords: HOG-LBP, Non-Negative Factorization, Pedestrian Detection

References

[1] N. Dalal and B. Triggs, Histograms of oriented gradients for human detection, IEEE Conference on Computer Vision and Pattern Recognition, p.886–893, (2005).

DOI: 10.1109/cvpr.2005.177

[2] X. Wang, T.X. Han, and S. Yan, An HOG-LBP Human Detector with Partial Occlusion Handling, IEEE International Conference on Computer Vision, p.1–8, (2009).

DOI: 10.1109/iccv.2009.5459207

[3] T. Ojala, M. Pietikainen, T. Maenpaa Multiresolution gray-scale and rotation invariant texture classification with local binary patterns., IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, p.971–987, (2002).

DOI: 10.1109/tpami.2002.1017623

[4] J. Xu, Q. Wu and J. Zhang, Z. Tang. Fast and Accurate Human Detection Using a Cascade of Boosted MS-LBP Features. IEEE Signal Processing Letter, Vol. 19, Issue 10, pp.676-679, (2012).

DOI: 10.1109/lsp.2012.2210870

[5] C. B. Zeng, H. D. Ma, and A. Ming, Fast human detection using mi-svm and a cascade of HOG-LBP features, [C], in Proceeding of the International Conference on. Image Processing (ICIP), pp.3845-3848, Hong Kong, (2010).

DOI: 10.1109/icip.2010.5654100

[6] Y. Zhang, H. Sun, K. Ji. Multi-view pedestrian classification algorithm via non-negative least square [J]. Journal of Shaanxi Normal University (Natural Science Edition), 2014, 4: 10-11.

[7] Y. Mu, S. Yan, Y. Liu, , T. Huang, B. Zhou,: Discriminative Local Binary Patterns for Human Detection in Personal Album. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, p.1–8 (2008).

DOI: 10.1109/cvpr.2008.4587800

[8] D D Lee and S H. Seung: Learning the parts of objects by nonnegative matrix factorization [J]. Nature, 1999, 401: 788-791.

DOI: 10.1038/44565

[9] R. Sun, J. Chen and J. Gao, Fast Pedestrian Detection Based on Saliency Detection and HOG-NMF Features Journal of Electronics & Information Technology, pp.1921-1924, (2013).

DOI: 10.3724/sp.j.1146.2012.01700

[10] L. Li, Y. Zhang. A Survey on Algorithms of Non-Negative Matrix Factorization[J]. Chinese Journal of Electronics, 2008, vol. 36 No. 4: 737-743.

[11] P. Doll´ar, C. Wojek, B. Schiele, and P. Perona, Pedestrian detection: A benchmark, IEEE Conference on Computer Vision and Pattern Recognition, p.304–311, (2009).

DOI: 10.1109/cvpr.2009.5206631