Multiple hypothesis video segmentation from superpixel flows

Authors:
Amelio Vazquez-Reina;Shai Avidan;Hanspeter Pfister;Eric Miller
Affiliations:
School of Engineering and Applied Sciences, Harvard University, MA and Department of Computer Science, Tufts University, MA;Adobe Systems Inc.;School of Engineering and Applied Sciences, Harvard University, MA;Department of Computer Science, Tufts University, MA
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Year:
2010

Citing 10
Cited 8

Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Video tooning

ACM SIGGRAPH 2004 Papers
Graph Cuts and Efficient N-D Image Segmentation

International Journal of Computer Vision
Object tracking: A survey

ACM Computing Surveys (CSUR)
Nonchronological Video Synopsis and Indexing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Track and cut: simultaneous tracking and segmentation of multiple objects with graph cuts

Journal on Image and Video Processing - Video Tracking in Complex Scenes for Surveillance Applications
Robust Higher Order Potentials for Enforcing Label Consistency

International Journal of Computer Vision
Video SnapCut: robust video object cutout using localized classifiers

ACM SIGGRAPH 2009 papers
Tracking as Segmentation of Spatial-Temporal Volumes by Anisotropic Weighted TV

EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Data clustering: 50 years beyond K-means

Pattern Recognition Letters

Probabilistic models for robot-based object segmentation

Robotics and Autonomous Systems
Active frame selection for label propagation in videos

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Streaming hierarchical video segmentation

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Occlusion handling in video segmentation via predictive feedback

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Partition cortical surfaces into supervertices: method and application

MeshMed'12 Proceedings of the 2012 international conference on Mesh Processing in Medical Image Analysis
Video segmentation with superpixels

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Multi-layer spectral clustering for video segmentation

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Robust object tracking using constellation model with superpixel

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multiple Hypothesis Video Segmentation (MHVS) is a method for the unsupervised photometric segmentation of video sequences. MHVS segments arbitrarily long video streams by considering only a few frames at a time, and handles the automatic creation, continuation and termination of labels with no user initialization or supervision. The process begins by generating several pre-segmentations per frame and enumerating multiple possible trajectories of pixel regions within a short time window. After assigning each trajectory a score, we let the trajectories compete with each other to segment the sequence. We determine the solution of this segmentation problem as the MAP labeling of a higher-order random field. This framework allows MHVS to achieve spatial and temporal long-range label consistency while operating in an on-line manner. We test MHVS on several videos of natural scenes with arbitrary camera and object motion.