DocumentCode
2605287
Title
Temporal slice analysis of image sequences
Author
Peng, Shou-Ling
Author_Institution
Dept. of Electr. Eng. & Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
fYear
1991
fDate
3-6 Jun 1991
Firstpage
283
Lastpage
288
Abstract
An early-processing algorithm to extract motion information from closely sampled image sequences is presented. This method outputs dense displacement field, based on the extraction of strips in slices taken from the image volume along the temporal dimension. The extracted strips provide estimates of the velocity component along the slice orientation. Because of the high sampling rate, the motion is assumed to be piecewisely translational. A voting scheme to estimate the position of FOE while extracting strips is proposed. The true velocity can then be calculated. Results on several real image sequences and a promising speedup from the parallel implementation on the Connection Machine are presented
Keywords
computer vision; computerised picture processing; Connection Machine; dense displacement field; early-processing algorithm; image sequences; motion information; parallel implementation; piecewisely translational; real image sequences; sampling rate; slice orientation; temporal dimension; temporal slice analysis; velocity component; voting scheme; Cameras; Data mining; Image analysis; Image motion analysis; Image sampling; Image sequence analysis; Image sequences; Intelligent robots; Intelligent systems; Strips;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on
Conference_Location
Maui, HI
ISSN
1063-6919
Print_ISBN
0-8186-2148-6
Type
conf
DOI
10.1109/CVPR.1991.139703
Filename
139703
Link To Document