Citation

Wang G, Liu Q. Sensors (Basel) 2015; 15(12): 32188-32212.

Affiliation

School of Software Engineering, South China University of Technology, No. 382 Waihuan East Rd., Guangzhou 510006, China. liuqiong@scut.edu.cn.

Copyright

(Copyright © 2015, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s151229874

PMID

26703611

Abstract

Far-infrared pedestrian detection approaches for advanced driver-assistance systems based on high-dimensional features fail to simultaneously achieve robust and real-time detection. We propose a robust and real-time pedestrian detection system characterized by novel candidate filters, novel pedestrian features and multi-frame approval matching in a coarse-to-fine fashion. Firstly, we design two filters based on the pedestrians' head and the road to select the candidates after applying a pedestrian segmentation algorithm to reduce false alarms. Secondly, we propose a novel feature encapsulating both the relationship of oriented gradient distribution and the code of oriented gradient to deal with the enormous variance in pedestrians' size and appearance. Thirdly, we introduce a multi-frame approval matching approach utilizing the spatiotemporal continuity of pedestrians to increase the detection rate. Large-scale experiments indicate that the system works in real time and the accuracy has improved about 9% compared with approaches based on high-dimensional features only.

Language: en