Title :
Image sequence segmentation using 3-D structure tensor and curve evolution
Author :
Zhang, Jun ; Gao, Jianbo ; Liu, Weisong
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Wisconsin Univ., Milwaukee, WI, USA
fDate :
5/1/2001 12:00:00 AM
Abstract :
We describe a novel approach for image sequence segmentation. It contains three parts: global motion compensation, robust frame differencing, and curve evolution. It is computationally efficient, does not require dense-field motion estimation, and is insensitive to noise and global/background motion. It works for black-and-white and color image sequences. The efficacy of this approach is demonstrated on both TV and surveillance image sequences
Keywords :
image colour analysis; image segmentation; image sequences; motion compensation; video signal processing; 3D structure tensor; TV image sequences; black-and-white image sequences; color image sequences; computationally efficient method; curve evolution; global motion compensation; global/background motion; image sequence segmentation; noise; object based video compression; robust frame differencing; surveillance image sequences; Background noise; Color; Image segmentation; Image sequences; Motion compensation; Motion estimation; Noise robustness; Surveillance; TV; Tensile stress;
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
