DocumentCode :
2387158
Title :
Affine parameter estimation with gradual segmentation
Author :
Sobue, Takahiko ; Hamada, Nozomu
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Kanagawa, Japan
Volume :
2
fYear :
1996
fDate :
26-29 Nov 1996
Firstpage :
775
Abstract :
We propose an extraction method of the structural motion information for compact image representation. The advanced motion analysis needs segmentation and motion velocity information. Conventional segmentation methods by using edge detection with high-pass filtering tend to fall into over-segmentation. The morphological filter is used to obtain edge information avoiding the selection of small oscillation. In the filtering process, various sizes of structural element (SE) makes possible gradual segmentation with respect to the object size. Then in each divided region, the simultaneous equations of motion velocity are solved to get the affine parameter (AP) which can describe the object´s movement of translation, rotation, expansion and reduction. If the intensity error in a region is larger than the threshold, a smaller structural element is used to segment the region. This enables one to get affine motion parameters without the waste of over-segmentation
Keywords :
feature extraction; filtering theory; image representation; image segmentation; mathematical morphology; motion estimation; parameter estimation; affine parameter estimation; compact image representation; edge detection; expansion; extraction method; gradual segmentation; high-pass filtering; image region; intensity error; morphological filter; motion analysis; motion velocity; motion velocity information; object size; reduction; rotation; simultaneous equations; structural element size; structural motion information; translation; Artificial intelligence; Filters; Image coding; Image edge detection; Image motion analysis; Image segmentation; Motion analysis; Parameter estimation; Shape; Transform coding;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON '96. Proceedings., 1996 IEEE TENCON. Digital Signal Processing Applications
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-3679-8
Type :
conf
DOI :
10.1109/TENCON.1996.608443
Filename :
608443
Link To Document :
بازگشت