2017 IEEE Conference on Computer Vision and Pattern Recognition

Contour-Constrained Superpixels
for Image and Video Processing

Se-Ho Lee
Korea University

Won-Dong Jang
Korea University

Chang-Su Kim
Korea University


A novel contour-constrained superpixel (CCS) algorithm is proposed in this work. We initialize superpixels and regions in a regular grid and then refine the superpixel label of each region hierarchically from block to pixel levels. To make superpixel boundaries compatible with object contours, we propose the notion of contour pattern matching and formulate an objective function including the contour constraint. Furthermore, we extend the CCS algorithm to generate temporal superpixels for video processing. We initialize superpixel labels in each frame by transferring those in the previous frame and refine the labels to make superpixels temporally consistent as well as compatible with object contours. Experimental results demonstrate that the proposed algorithm provides better performance than the state-of-the-art superpixel methods.

Supplementary Video



  • Se-Ho Lee, Won-Dong Jang, and Chang-Su Kim, "Contour-constrained superpixels for image and video processing," In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, pp. 5863-5871, Jul. 2017. [pdf] [Supplementary video]

  • Download

  • Source code: CVPR17_CCS_SHLee.zip