Title :
Superpixel-driven level set tracking
Author :
Xue Zhou ; Xi Li ; Tat-Jun Chin ; Suter, David
Author_Institution :
Univ. of Electron. Sci. & Technol. of China, Chengdu, China
fDate :
Sept. 30 2012-Oct. 3 2012
Abstract :
In this paper, we propose a superpixel-driven method for level set tracking. In particular, by taking a superpixel-based speed function, the level set evolution is accelerated greatly. We define a mutual information based speed function using a superpixel-unit as the underlying representation, which captures the correlation of a superpixel with object/background. In order to enhance the robustness of our method, a shape prior is incorporated to constrain the contour evolution. Experimental results on a number of challenging sequences demonstrate the effectiveness and robustness of our method.
Keywords :
image representation; image sequences; object tracking; set theory; contour evolution; level set evolution; mutual information; shape prior; superpixel-based speed function; superpixel-driven level set tracking; superpixel-driven method; superpixel-unit; underlying representation; Accuracy; Force; Level set; Mutual information; Robustness; Shape; Tracking; Tracking; level set; mutual information; superpixel;
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2012.6466882