Motion Segmentation Based on Integrated Region Layering and Motion Assignment

David Tweed, Andrew Calway

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

We describe a novel algorithm for segmenting image sequence frames into regions of pixels moving with coherent motion. It is based on fusing local grey level segmentations with motion estimates obtained using block and partial correlations. The key innovation is the method employed to assign motion labels to the grey level regions. This uses an explicit model of motion occlusion and uncovering based on boundary ownership which predicts the location of motion-compensated difference energy for a given labelling and depth ordering of adjacent regions. A significant advantage of the approach is that region layering is automatically generated with the best assignment. We incorporate the scheme into a global segmentation algorithm in which the local motion assignments are combined using a consistency criterion. This leads to layered sets of connected sub-regions representing the segmented motion regions within the frame. Results of experiments demonstrate that the approach is effective.
Translated title of the contributionMotion Segmentation Based on Integrated Region Layering and Motion Assignment
Original languageEnglish
Title of host publicationProceedings of Fourth Asian Conference on Computer Vision
Publication statusPublished - 2000

Bibliographical note

Other page information: 1002-1007
Conference Proceedings/Title of Journal: Proceedings of Fourth Asian Conference on Computer Vision
Other identifier: 1000448

Fingerprint Dive into the research topics of 'Motion Segmentation Based on Integrated Region Layering and Motion Assignment'. Together they form a unique fingerprint.

Cite this