DocumentCode
1655745
Title
Stereo-based preprocessing for human shape localization in unstructured environments
Author
Broggi, A. ; Fascioli, A. ; Fedriga, I. ; Tibaldi, A. ; Rose, M. Del
Author_Institution
Dipt. di Ingegneria dell´´informazione, Parma Univ., Italy
fYear
2003
Firstpage
410
Lastpage
415
Abstract
This paper describes the research activities for the localization of human shapes using visual information carried on at the University of Parma, Italy, in the frame of a common project with the TACOM Department of US Army. The paper proposes the application of a stereoscopic technique as a preprocessing for the localization of humans in generic unstructured environments. Each row of the left image is matched with the epipolar row of the right image. This creates a map of each object in the scene as well as the slope of the road. Preliminary results have proved to be promising.
Keywords
computer vision; feature extraction; image matching; object recognition; stereo image processing; traffic engineering computing; Parma university; TACOM department; epipolar row; feature extraction; generic unstructured environments; human shape localization; image matching; road slope; stereo based preprocessing; stereoscopic technique; visual information; Automotive engineering; Humans; Layout; Navigation; Plasma welding; Remotely operated vehicles; Roads; Robots; Shape; Vehicle detection;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Vehicles Symposium, 2003. Proceedings. IEEE
Print_ISBN
0-7803-7848-2
Type
conf
DOI
10.1109/IVS.2003.1212946
Filename
1212946
Link To Document