Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation
Technical Report , arxiv:1608.03066, 2016
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 o-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.
Images and movies
BibTex reference
@TechReport{DB16b, author = "B.Drayer and T.Brox", title = "Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation", institution = "arxiv:1608.03066", month = " ", year = "2016", url = "http://lmb.informatik.uni-freiburg.de/Publications/2016/DB16b" }