Depth Map Generation for 2D-to-3D Conversion by Short-Term Motion Assisted Color Segmentation

摘要: This paper presented a novel depth map generation method - the short-term motion assisted color segmentation, which combines pictorial, monocular and binocular cues of human vision. The proposed utilizes motion/edge registration technique to avoid jitter error in common segmentation. And motion/image segment adaptation algorithm matches connected components with segments. Even for static scene, component is still working generation. experimental results show that image segmentation improves quality smoothness both spatial temporal domain.