Title :
Pedestrian detection in nighttime driving
Author :
Tian, Q.M. ; Luo, Y.P. ; Hu, D.C.
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
This paper presents an approach for pedestrian detection in the nighttime driving with a normal camera. Bright objects in the video are extracted with an adaptive thresholding segmentation algorithm. Then, the size, position, and shape of each object are analyzed to judge whether it is a pedestrian. A tracking module is used to verify the result at last. Experimental results show that the proposed method can detect 71.26% pedestrians.
Keywords :
automated highways; cameras; feature extraction; image segmentation; object detection; video signal processing; adaptive thresholding segmentation algorithm; image recognition; nighttime driving; pedestrian detection; support vector machine; tracking module; Cameras; Feedforward neural networks; Head; Infrared detectors; Neural networks; Object detection; Pattern recognition; Phase detection; Roads; Shape;
Conference_Titel :
Image and Graphics (ICIG'04), Third International Conference on
Conference_Location :
Hong Kong, China
Print_ISBN :
0-7695-2244-0
DOI :
10.1109/ICIG.2004.111
