Occlusion boundary detection and figure/ground assignment from optical flow

Authors:
P. Sundberg;T. Brox;M. Maire;P. Arbelaez;J. Malik
Affiliations:
Univ. of California at Berkeley, Berkeley, CA, USA;Univ. of Freiburg, Freiburg, Germany;California Inst. of Technol., Pasadena, CA, USA;Univ. of California at Berkeley, Berkeley, CA, USA;Univ. of California at Berkeley, Berkeley, CA, USA
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 5

Fast adaptive edge-aware mask generation

Proceedings of Graphics Interface 2012
Nested pictorial structures

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Efficient closed-form solution to generalized boundary detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
2.1 depth estimation of frames in image sequences using motion occlusions

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Video segmentation with superpixels

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical flow. This detector outperforms the state-of-the-art on the benchmark of Stein and Hebert, improving average precision from .58 to .72. Moreover, the optical flow on and near occlusion boundaries allows us to assign a depth ordering to the adjacent regions. To evaluate performance on this edge-based figure/ground labeling task, we introduce a new video dataset that we believe will support further research in the field by allowing quantitative comparison of computational models for occlusion boundary detection, depth ordering and segmentation in video sequences.