DocumentCode :
327741
Title :
An MPEG-processor-based robot vision system for real-time detection of moving objects by a moving observer
Author :
Stoffler, N.O. ; Schnepf, Zoltan
Author_Institution :
Lab. for Process Control & Real-Time Syst., Tech. Univ. Munchen, Germany
Volume :
1
fYear :
1998
fDate :
16-20 Aug 1998
Firstpage :
477
Abstract :
Describes a PC-based vision system that can be used to detect moving objects from a mobile robot. An image processing board equipped with an MPEG motion estimation processor calculates a sparse but robust optic flow in real-time. An algorithm to evaluate this kind of optic flow has been realized in software. It determines relevant motion parameters and a simple scene interpretation in terms of moving object regions. The image processing board and the algorithm are presented in some detail; the performance of the system is demonstrated by experiments
Keywords :
image segmentation; image sensors; image sequences; mobile robots; motion estimation; object detection; robot vision; MPEG-processor-based robot vision system; PC-based vision system; image processing board; mobile robot; moving objects; moving observer; real-time detection; scene interpretation; sparse robust optic flow; Image motion analysis; Image processing; Machine vision; Mobile robots; Motion estimation; Object detection; Real time systems; Robot vision systems; Robustness; Software algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
ISSN :
1051-4651
Print_ISBN :
0-8186-8512-3
Type :
conf
DOI :
10.1109/ICPR.1998.711185
Filename :
711185
Link To Document :
بازگشت