On the application of a modified self-organizing neural network to estimate stereo disparity

Venkatesh, Y.V.; Raja Kumar, S.; Jaya Kumar, A.

Please use this identifier to cite or link to this item: http://hdl.handle.net/2289/3668

Full metadata record

DC Field	Value	Language
dc.contributor.author	Venkatesh, Y.V.	-
dc.contributor.author	Raja Kumar, S.	-
dc.contributor.author	Jaya Kumar, A.	-
dc.date.accessioned	2008-11-28T11:19:22Z	-
dc.date.available	2008-11-28T11:19:22Z	-
dc.date.issued	2007-10	-
dc.identifier.citation	IEEE Transactions on Image Processing, 2007, Vol.16, p2822	en
dc.identifier.issn	1057-7149	-
dc.identifier.uri	http://hdl.handle.net/2289/3668	-
dc.description	Open Access.	en
dc.description.abstract	We propose a modified self-organizing neural network to estimate the disparity map from a stereo pair of images. Novelty consists of the network architecture and of dispensing with the standard assumption of epipolar geometry. Quite distinct from the existing algorithms which, typically, involve area- and/or feature-matching, the network is first initialized to the right image, and then deformed until it is transformed into the left image, or vice versa, this deformation itself being the measure of disparity. Illustrative examples include two classes of stereo pairs: synthetic and natural (including random-dot stereograms and wire frames) and distorted. The latter has one of the following special characteristics: one image is blurred, one image is of a different size, there are salient features like discontinuous depth values at boundaries and surface wrinkles, and there exist occluded and half-occluded regions. While these examples serve, in general, to demonstrate that the technique performs better than many existing algorithms, the above-mentioned stereo pairs (in particular, the last two) bring out some of its limitations, thereby serving as possible motivation for further work.	en
dc.language.iso	en	en
dc.publisher	IEEE	en
dc.relation.uri	http://dx.doi.org/10.1109/TIP.2007.906772	en
dc.rights	2007 IEEE. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Raman Research Institute's's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.	en
dc.subject	Correspondence problem	en
dc.subject	nonepipolar	en
dc.subject	occlusion	en
dc.subject	self-organizing map (SOM)	en
dc.subject	stereo disparity estimation	en
dc.subject	stereo-pair analysis	en
dc.title	On the application of a modified self-organizing neural network to estimate stereo disparity	en
dc.type	Article	en
Appears in Collections:	Research Papers (SCM)

Files in This Item:

File	Description	Size	Format
2007 IEEE Trans. Image Processing V16 p2822.pdf	Open Access	1.25 MB	Adobe PDF	View/Open

Show simple item record