Title :
An Approach to On-Road Vehicle Detection, Description and Tracking
Author :
Chumerin, Nikolay ; Van Hulle, Marc M.
Author_Institution :
K.U.Leuven, Leuven
Abstract :
We present an approach to detecting independently moving objects (IMOs) in stereo video sequences acquired by onboard cameras on a moving vehicle. The proposed approach is based on the processing of two independent information streams: an independent motion detection stream and an object recognition stream. Fusion of these streams outputs allows our system to segment IMOs, track them, and even estimate some of their properties.
Keywords :
image fusion; image segmentation; image sequences; motion estimation; object recognition; optical tracking; road vehicles; stereo image processing; traffic engineering computing; video signal processing; image fusion; image segmentation; independently moving object detection; object recognition stream; on-road vehicle motion detection; onboard camera; optical tracking; stereo video sequence; Cameras; Convolution; Image motion analysis; Kernel; Motion detection; Object detection; Object recognition; Streaming media; Vehicle detection; Video sequences;
Conference_Titel :
Machine Learning for Signal Processing, 2007 IEEE Workshop on
Conference_Location :
Thessaloniki
Print_ISBN :
978-1-4244-1566-3
Electronic_ISBN :
1551-2541
DOI :
10.1109/MLSP.2007.4414317
