Detachable Object Detection with Efficient Model Selection

We describe a computationally efficient scheme to perform model selection while simultaneously segmenting a short video stream into an unknown number of detachable objects. Detachable objects are regions of space bounded by surfaces that are surrounded by the medium other than for their region of su...

Full description

Saved in:
Bibliographic Details
Published inEnergy Minimization Methods in Computer Vision and Pattern Recognition pp. 191 - 204
Main Authors Ayvaci, Alper, Soatto, Stefano
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg
SeriesLecture Notes in Computer Science
Subjects
Graph Cuts
Layers
Motion Segmentation
Object Detection
Occlusion
Ordering Constraints
Video Segmentation
Online AccessGet full text

Cover

More Information
Summary:We describe a computationally efficient scheme to perform model selection while simultaneously segmenting a short video stream into an unknown number of detachable objects. Detachable objects are regions of space bounded by surfaces that are surrounded by the medium other than for their region of support, and the region of support changes over time. These include humans walking, vehicles moving, etc. We exploit recent work on occlusion detection to bootstrap an energy minimization approach that is solved with linear programming. The energy integrates both appearance and motion statistics, and can be used to seed layer segmentation approaches that integrate temporal information on long timescales.
Bibliography:Research supported by ARO 56765, ONR N000140810414, AFOSR FA95500910427.
ISBN:3642230938
9783642230936
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-642-23094-3_14