Citation

Liu S, Luo Y, Yang S. J. Inform. Sci. Eng. 2007; 23(1): 271-283.

Copyright

(Copyright © 2007, Institute of Information Science, Academia Sinica)

DOI

unavailable

PMID

unavailable

Abstract

With the increase of requirement for improving the safety of night driving, auto- matic pedestrian detection has received more and more attraction. This paper mainly in- troduces a pedestrian detection method in infrared images. Base on the properties of in- frared images, we present a two-step pedestrian detection method including pedestrian candidate selection and validation. The first step is localization of pedestrian candidate, which is to detect warm objects with specific size and aspect ratio. Then, the validation process is based on template matching, which uses multiscale representation and Dy- namic Programming for matching deformed and possible occluded contour. The superi- ority of the proposed shape matching algorithm to the conventional methods is due to the use of hierarchy of segmented representation. It can adjust automatically while the quan- tity of noise and deformation changes, which improves the accuracy of pedestrian detec- tion. Experimental results have confirmed the effectiveness of the proposed method.

Available:
http://www.iis.sinica.edu.tw/page/jise/2007/200701_16.pdf