Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation
This work addresses the problem of accurate, temporally consistent object segmentation in videos for computer vision applications, but it appears incremental as it builds on existing detection and tracking methods.
The paper tackles object-level video segmentation by combining frame-level object detection with tracking and motion cues to produce temporally consistent object tubes, overcoming issues like scenes with no motion and dominant camera motion. It reports results on four datasets: YouTube Objects, SegTrackv2, egoMotion, and FBMS, though no specific numbers are provided in the abstract.
We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of motion. For the final video segmentation, we combine this information with motion cues. The method overcomes the typical problems of weakly supervised/unsupervised video segmentation, such as scenes with no motion, dominant camera motion, and objects that move as a unit. In contrast to most tracking methods, it provides an accurate, temporally consistent segmentation of each object. We report results on four video segmentation datasets: YouTube Objects, SegTrackv2, egoMotion, and FBMS.