Temporally Consistent Superpixels

Superpixel algorithms represent a very useful and in-creasingly popular preprocessing step for a wide range of computer vision applications, as they offer the potential to boost efficiency and effectiveness. In this regards, this paper presents a highly competitive approach for tempo-rally consistent superpixels for video content. The approach is based on energy-minimizing clustering utilizing a novel hybrid clustering strategy for a multi-dimensional feature space working in a global color subspace and local spatial subspaces. Moreover, a new contour evolution based strat-egy is introduced to ensure spatial coherency of the gener-ated superpixels. For a thorough evaluation the proposed approach is compared to state of the art supervoxel algo-rithms using established benchmarks and shows a superior performance. 1