Home
Uni-Logo
 

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.


Other associated files : 1608.03066v1.pdf [9MB]  

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"
}

Other publications in the database