Abstract
Pedestrian protection system (PPS) in the advanced driver assistance system (ADAS) to improve traffic safety, has become an important research area. The major challenge in PPS is to develop a reliable on-board pedestrian detection system. Compared to the pedestrian detection on static images, on-board pedestrian detection is facing some new difficulties, such as high real-time demand, wide range of illumination variation and so on. In order to deal with these challenges, we presented a method in this paper by combining the road surface extraction technique and the histogram of oriented gradient (HOG) feature based classification, so that the search regions are only limited within the extracted road surface. Experiment results show that this method can remarkably reduce the false alarm rate, improve the detection speed, and significantly improve the small pedestrian detection rate.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
CVC-02 dataset: http://www.cvc.uab.es/adas/site/
References
Papageorgiou C, Poggio T (2000) A trainable system for object detection. Int J Comput Vision 38:15–33
Tran D, Forsyth D (2007) Configuration estimates improve pedestrian finding. Adv Neural Inform Process 644:1529–1536
Dalal N, Triggs B (2005) Histogram of oriented gradient for human detection. Comput Vision Pattern Recogn 1:886–893
Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multi-scale, deformable part model. Computer vision and pattern recognition, Chicago, pp 1–8
Wu B, Nevatia R (2007) Cluster boosted tree classifier for multi-view, multi-pose object detection. In: International conference on computer vision, Los Angeles, pp 1–8
Dollár P, Babenko B, Belongie S, Perona P (2008) Multiple component learning for object detection. In: European conference on computer vision, vol 5303, Marseille, France, pp 211–224
Finlayson G, Hordley S, Lu C, Drew M (2006) On the removal of shadows from images. IEEE Trans Pattern Anal Mach Intell 28:59–68
Finlayson G, Hordley S, Drew M (2002) Removing shadows from images. In: Proceedings European conference on computer vision, Comenhagen, Denmark, pp 129–132
Alvarez JMA, Ĺopez AM (2011) Road detection based on illuminant invariance. IEEE Trans Intell Transport Syst 12(1):184–193
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Heng, H., Xiong, H. (2014). Pedestrian Detection Based on Road Surface Extraction in Pedestrian Protection System. In: Wang, W. (eds) Mechatronics and Automatic Control Systems. Lecture Notes in Electrical Engineering, vol 237. Springer, Cham. https://doi.org/10.1007/978-3-319-01273-5_88
Download citation
DOI: https://doi.org/10.1007/978-3-319-01273-5_88
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-01272-8
Online ISBN: 978-3-319-01273-5
eBook Packages: EngineeringEngineering (R0)