DocumentCode :
2383610
Title :
The study of the detection of pedestrian and bicycle using image processing
Author :
Zhijun Qui ; Yao, Danya ; Zhang, Yi ; Ma, Daosong ; Liu, Xinyu
Volume :
1
fYear :
2003
fDate :
12-15 Oct. 2003
Firstpage :
340
Abstract :
Besides vehicle both pedestrian and bicycle are two primary components in urban traffic flow. Video object tracking is an important method of information detection in ITS. This system implements an approach for detecting pedestrians and bicycles in urban traffic scenes by means of feature-based reason on visual data. In the video traffic monitoring system, matching method is often used to find the position of the moving object in the image sequence. This paper tried to propose an improved algorithm of corner feature extraction, an algorithm of position matching using motion matching and a method for traffic object classification. Experiment results were followed for verification.
Keywords :
edge detection; feature extraction; image classification; image matching; image sequences; object detection; road traffic; road vehicles; tracking; traffic information systems; ITS; bicycle detection; feature based reason; feature extraction algorithm; image processing; image sequence; information detection; intelligent information systems; motion matching; object position finding; pedestrian detection; position matching algorithm; traffic object classification; urban traffic flow; video object tracking; video traffic monitoring system; Bicycles; Cameras; Communication system traffic control; Computer vision; Feature extraction; Image processing; Monitoring; Object detection; Roads; Target tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Transportation Systems, 2003. Proceedings. 2003 IEEE
Print_ISBN :
0-7803-8125-4
Type :
conf
DOI :
10.1109/ITSC.2003.1251974
Filename :
1251974
Link To Document :
بازگشت