Computer Vision, IEEE International Conference on (2011)
Nov. 6, 2011 to Nov. 13, 2011
Gang Zeng , Key Laboratory on Machine Perception, Peking University, China
Peng Wang , Key Laboratory on Machine Perception, Peking University, China
Jingdong Wang , Microsoft Research Asia, China
Rui Gan , Key Laboratory on Machine Perception, Peking University, China
Hongbin Zha , Key Laboratory on Machine Perception, Peking University, China
Over-segments (i.e. superpixels) have been commonly used as supporting regions for feature vectors and primitives to reduce computational complexity in various image analysis tasks. In this paper, we describe a structuresensitive over-segmentation technique by exploiting Lloyd's algorithm with a geodesic distance. It generates smaller superpixels to achieve lower under-segmentation in structure-dense regions with high intensity or color variation, and produces larger segments to increase computational efficiency in structure-sparse regions with homogeneous appearance. We adopt geometric flows to compute the geodesic distances amongst pixels, and in the segmentation procedure, the density of over-segments is automatically adjusted according to an energy functional that embeds color homogeneity, structure density and compactness constraints. Comparative experiments with the Berkeley database show that the proposed algorithm outperforms prior arts while offering a comparable computational efficiency with fast methods, such as TurboPixels.
Rui Gan, Gang Zeng, Peng Wang, Hongbin Zha and J. Wang, "Structure-sensitive superpixels via geodesic distance," 2011 IEEE International Conference on Computer Vision (ICCV 2011)(ICCV), Barcelona, 2011, pp. 447-454.