English

Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation

Computer Vision and Pattern Recognition 2016-08-11 v1

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.

Keywords

Cite

@article{arxiv.1608.03066,
  title  = {Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation},
  author = {Benjamin Drayer and Thomas Brox},
  journal= {arXiv preprint arXiv:1608.03066},
  year   = {2016}
}
R2 v1 2026-06-22T15:16:36.792Z