Change search
ReferencesLink to record
Permanent link

Direct link
Online Learning for Fast Segmentation of Moving Objects
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
2012 (English)In: ACCV 2012, Springer Berlin/Heidelberg, 2012, 52-65 p.Conference paper (Other academic)
Abstract [en]

This work addresses the problem of fast, online segmentationof moving objects in video. We pose this as a discriminative onlinesemi-supervised appearance learning task, where supervising labelsare autonomously generated by a motion segmentation algorithm. Thecomputational complexity of the approach is signicantly reduced byperforming learning and classication on oversegmented image regions(superpixels), rather than per pixel. In addition, we further exploit thesparse trajectories from the motion segmentation to obtain a simplemodel that encodes the spatial properties and location of objects at eachframe. Fusing these complementary cues produces good object segmentationsat very low computational cost. In contrast to previous work,the proposed approach (1) performs segmentation on-the-y (allowingfor applications where data arrives sequentially), (2) has no prior modelof object types or `objectness', and (3) operates at signicantly reducedcomputational cost. The approach and its ability to learn, disambiguateand segment the moving objects in the scene is evaluated on a numberof benchmark video sequences.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2012. 52-65 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 7725
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-86211DOI: 10.1007/978-3-642-37444-9_5ISBN: 978-3-642-37443-2 (print)ISBN: 978-3-642-37444-9 (online)OAI: diva2:575721
11th Asian Conference on Computer Vision (ACCV 2012), 5-9 November 2012, Daejeon, Korea
Available from: 2012-12-11 Created: 2012-12-11 Last updated: 2014-12-05

Open Access in DiVA

fulltext(9059 kB)2474 downloads
File information
File name FULLTEXT01.pdfFile size 9059 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Ellis, LiamZografos, Vasileios
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 2474 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 299 hits
ReferencesLink to record
Permanent link

Direct link