DocumentCode
1393903
Title
Multibody Structure-from-Motion in Practice
Author
Ozden, Kemal Egemen ; Schindler, Konrad ; Van Gool, Luc
Author_Institution
ESAT-PSI/VISICS, Univ. of Leuven, Leuven, Belgium
Volume
32
Issue
6
fYear
2010
fDate
6/1/2010 12:00:00 AM
Firstpage
1134
Lastpage
1141
Abstract
Multibody structure from motion (SfM) is the extension of classical SfM to dynamic scenes with multiple rigidly moving objects. Recent research has unveiled some of the mathematical foundations of the problem, but a practical algorithm which can handle realistic sequences is still missing. In this paper, we discuss the requirements for such an algorithm, highlight theoretical issues and practical problems, and describe how a static structure-from-motion framework needs to be extended to handle real dynamic scenes. Theoretical issues include different situations in which the number of independently moving scene objects changes: Moving objects can enter or leave the field of view, merge into the static background (e.g., when a car is parked), or split off from the background and start moving independently. Practical issues arise due to small freely moving foreground objects with few and short feature tracks. We argue that all of these difficulties need to be handled online as structure-from-motion estimation progresses, and present an exemplary solution using the framework of probabilistic model-scoring.
Keywords
computer vision; image motion analysis; image segmentation; multibody structure from motion; multiple rigidly moving object; real dynamic scenes handling; static structure from motion framework; structure from motion estimation; Structure-from-motion; affine degeneracy.; model selection; motion segmentation; scale ambiguity;
fLanguage
English
Journal_Title
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher
ieee
ISSN
0162-8828
Type
jour
DOI
10.1109/TPAMI.2010.23
Filename
5396339
Link To Document