Exploring Prior Knowledge for Pedestrian Detection

Yi Yang, Zhenhua Wang and Fuchao Wu

Abstract

In this paper, we aim to explore the role of prior knowledge for pedestrian detection. The main idea is to integrate human body priors into the design of features. To this end, we propose the symmetric features and cross-channel features so as to capture the specific information of human body. Experimental results demonstrate that our detector achieves state-of-the-art performance. What’s more, the evaluation results on 'scale' subsets of Caltech-USA show that our detector performs best at medium scale and therefore has great potential to be integrated into real-world applications.

Session

Search and Detection

Files

PDF iconExtended Abstract (PDF, 1238K)
PDF iconPaper (PDF, 2M)

DOI

10.5244/C.29.176
https://dx.doi.org/10.5244/C.29.176

Citation

Yi Yang, Zhenhua Wang and Fuchao Wu. Exploring Prior Knowledge for Pedestrian Detection. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 176.1-176.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_176,
	title={Exploring Prior Knowledge for Pedestrian Detection},
	author={Yi Yang and Zhenhua Wang and Fuchao Wu},
	year={2015},
	month={September},
	pages={176.1-176.12},
	articleno={176},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.176},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.176}
}