DocumentCode :
3056554
Title :
Edge-preserving directional regularization technique for disparity estimation of stereoscopic images
Author :
Mi-Hyun Kim ; Kwang-Hoon Sohn
Author_Institution :
Dept. of Radio Commun. Eng., Yonsei Univ., Seoul, South Korea
fYear :
1999
fDate :
22-24 June 1999
Firstpage :
376
Lastpage :
377
Abstract :
This paper presents a new disparity estimation method using an edge-preserving directional regularization technique. This method smooths disparity vectors in smooth regions and preserves edges in object boundaries without oversmoothing. Very close matches between a left image and a right image are obtained as well as improved coding efficiency.
Keywords :
edge detection; image coding; smoothing methods; stereo image processing; coding efficiency; disparity estimation; disparity vectors; edge preservation; edge-preserving directional regularization technique; left image; object boundaries; right image; smooth regions; stereoscopic images; Biomedical imaging; Cost function; Entropy; Humans; Image coding; Image reconstruction; Layout; Manufacturing industries; Radio communication; Video compression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Consumer Electronics, 1999. ICCE. International Conference on
Conference_Location :
Los Angeles, CA, USA
Print_ISBN :
0-7803-5123-1
Type :
conf
DOI :
10.1109/ICCE.1999.785421
Filename :
785421
Link To Document :
بازگشت