Video Segmentation with Just a Few Strokes

As the use of videos is becoming more popular in com-puter vision, the need for annotated video datasets in-creases. Such datasets are required either as training data or simply as ground truth for benchmark datasets. A par-ticular challenge in video segmentation is due to disocclu-sions, which hamper frame-to-frame propagation, in con-junction with non-moving objects. We show that a com-bination of motion from point trajectories, as known from motion segmentation, along with minimal supervision can largely help solve this problem. Moreover, we integrate a new constraint that enforces consistency of the color distri-bution in successive frames. We quantify user interaction effort with respect to segmentation quality on challenging ego motion videos. We compare our approach to a diverse set of algorithms in terms of user effort and in terms of per-formance on common video segmentation benchmarks. 1