Tracking as Repeated Figure/Ground Segmentation

@article{Ren2007TrackingAR,
  title={Tracking as Repeated Figure/Ground Segmentation},
  author={Xiaofeng Ren and Jitendra Malik},
  journal={2007 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2007},
  pages={1-8}
}
Tracking over a long period of time is challenging as the appearance, shape and scale of the object in question may vary. We propose a paradigm of tracking by repeatedly segmenting figure from background. Accurate spatial support obtained in segmentation provides rich information about the track and enables reliable tracking of non-rigid objects without drifting. Figure/ground segmentation operates sequentially in each frame by utilizing both static image cues and temporal coherence cues, which… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 133 CITATIONS, ESTIMATED 87% COVERAGE

Click Carving: Segmenting Objects in Video with Point Clicks

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Computer Vision – ECCV 2012

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Video Object Segmentation and Tracking: A Survey

VIEW 18 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

BUAA-PRO: A Tracking Dataset with Pixel-Level Annotation

VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Human machine collaboration for foreground segmentation in images and videos

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Robust Deformable and Occluded Object Tracking With Dynamic Graph

  • IEEE Transactions on Image Processing
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Supervoxel-Consistent Foreground Propagation in Video

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Active Frame Selection for Label Propagation in Videos

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Structured Visual Tracking with Dynamic Graph

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Visual tracking via online manifold regularization

  • ICIMCS
  • 2010
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 11 Highly Influenced Citations

  • Averaged 12 Citations per year over the last 3 years

  • 4% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 34 REFERENCES

Learning and Matching Line Aspects for Articulated Objects

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 1 EXCERPT

OBJ CUT

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 1 EXCERPT

Online selection of discriminative tracking features

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2003
VIEW 1 EXCERPT

Sastry . 3 d tracking = classification + interpolation

A. Blake
  • 2003

Similar Papers

Loading similar papers…