A novel algorithm to segment a primary object in a video sequence is proposed in this work. First, we generate candidate regions for the primary object using both color and motion edges. Second, we estimate initial primary object regions, by exploiting the recurrence property of the primary object. Third, we augment the initial regions with missing parts or reducing them by excluding noisy parts repeatedly. This augmentation and reduction process (ARP) identifies the primary object region in each frame. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on recent benchmark datasets.
Yeong Jun Koh and Chang-Su Kim, “Primary Object Segmentation in Videos Based on Region Augmentation and Reduction,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 3442-3450, Jul. 2017. [pdf] [supp]
Source code: 2017_CVPR_YJKOH_ARP.zip
Results on the DAVIS 2016 dataset: ARP_DAVIS.zip