Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/64590
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Accelerated hypothesis generation for multi-structure robust fitting |
Author: | Chin, T. Yu, J. Suter, D. |
Citation: | Proceedings of the European Conference on Computer Vision (ECCV 2010), held in Crete, Greece 5-11 Sept 2010: pp.533-546 |
Publisher: | Springer-Verlag Berlin |
Publisher Place: | Germany |
Issue Date: | 2010 |
Series/Report no.: | Lecture Notes in Computer Science |
ISBN: | 3642155545 9783642155543 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | European Conference on Computer Vision (2010 : Crete, Greece) |
Editor: | Daniilidis, K. Maragos, P. Paragios, N. |
Statement of Responsibility: | Tat-Jun Chin, Jin Yu and David Suter |
Abstract: | Random hypothesis generation underpins many geometric model fitting techniques. Unfortunately it is also computationally expensive. We propose a fundamentally new approach to accelerate hypothesis sampling by guiding it with information derived from residual sorting. We show that residual sorting innately encodes the probability of two points to have arisen from the same model and is obtained without recourse to domain knowledge (e.g. keypoint matching scores) typically used in previous sampling enhancement methods. More crucially our approach is naturally capable of handling data with multiple model instances and excels in applications (e.g. multi-homography fitting) which easily frustrate other techniques. Experiments show that our method provides superior efficiency on various geometric model estimation tasks. Implementation of our algorithm is available on the authors' homepage. © 2010 Springer-Verlag. |
Rights: | Copyright status unknown |
DOI: | 10.1007/978-3-642-15555-0_39 |
Description (link): | http://www.ics.forth.gr/eccv2010/intro.php |
Published version: | http://dx.doi.org/10.1007/978-3-642-15555-0_39 |
Appears in Collections: | Aurora harvest Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.