DocumentCode
2552466
Title
An Approach to On-Road Vehicle Detection, Description and Tracking
Author
Chumerin, Nikolay ; Van Hulle, Marc M.
Author_Institution
K.U.Leuven, Leuven
fYear
2007
fDate
27-29 Aug. 2007
Firstpage
265
Lastpage
269
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;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning for Signal Processing, 2007 IEEE Workshop on
Conference_Location
Thessaloniki
ISSN
1551-2541
Print_ISBN
978-1-4244-1566-3
Electronic_ISBN
1551-2541
Type
conf
DOI
10.1109/MLSP.2007.4414317
Filename
4414317
Link To Document