A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis

F. Galasso, Naveen Shankar Nagaraja, T. Cardenas, Thomas Brox, B. Schiele
IEEE International Conference on Computer Vision (ICCV), Dec 2013
Abstract: Video segmentation research is currently limited by the lack of a benchmark dataset that covers the large variety of subproblems appearing in video segmentation and that is large enough to avoid overfitting. Consequently, there is little analysis of video segmentation which generalizes across subtasks, and it is not yet clear which and how video segmentation should leverage the information from the still-frames, as previously studied in image segmentation, alongside video specific information, such as temporal volume, motion and occlusion. In this work we provide such an analysis based on annotations of a large video dataset, where each video is manually segmented by multiple per sons. Moreover, we introduce a new volume-based metric that includes the important aspect of temporal consistency, that can deal with segmentation hierarchies, and that reflects the tradeoff between over-segmentation and segmentation accuracy.

Other associated files : vsb100_iccv13_new.pdf [2MB]  

Images and movies


See also

The published version had different BPR values due to thicker boundaries. See the original paper here - [pdf].
Check our bug report for details.

Supplementary Material [pdf]

BibTex reference

  author       = "F. Galasso and N.S. Nagaraja and T.J. Cardenas and T. Brox and B.Schiele",
  title        = "A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis",
  booktitle    = "IEEE International Conference on Computer Vision (ICCV)",
  month        = "Dec",
  year         = "2013",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2013/NB13"

Other publications in the database