liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
High-speed View Matching using Region Descriptors
Linköping University, Department of Electrical Engineering, Computer Vision.
2010 (English)Independent thesis Advanced level (degree of Master (Two Years)), 30 credits / 45 HE creditsStudent thesisAlternative title
Vymatchning i realtid med region-deskriptorer (Swedish)
Abstract [en]

This thesis treats topics within the area of object recognition. A real-time view matching method has been developed to compute the transformation between two different images of the same scene. This method uses a color based region detector called MSCR and affine transformations of these regions to create affine-invariant patches that are used as input to the SIFT algorithm. A parallel method to compute the SIFT descriptor has been created with relaxed constraints so that the descriptor size and the number of histogram bins can be adjusted. Additionally, a matching step to deduce correspondences and a parallel RANSAC method have been created to estimate the undergone transformation between these descriptors. To achieve real-time performance, the implementation has been targeted to use the parallel nature of the GPU with CUDA as the programming language. Focus has been put on the architecture of the GPU to find the best way to parallelize the different processing steps. CUDA has also been combined with OpenGL to be able to use the hardware accelerated anisotropic sampling method for affine transformations of regions. Parts of the implementation can also be used individually from either Matlab or by using the provided C++ library directly. The method was also evaluated in terms of accuracy and speed. It was shown that our algorithm has similar or better accuracy at finding correspondences than SIFT when the 3D geometry changes are large but we get a slightly worse result on images with flat surfaces.

Place, publisher, year, edition, pages
2010. , 77 p.
Keyword [en]
Object Recognition, Region, RANSAC, MSCR, MSER, SIFT, GPU, CUDA
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-58843ISRN: LiTH-ISY-EX--10/4356--SEOAI: diva2:345932
2010-08-20, Algoritmen, Linköping University, 10:15 (English)
Available from: 2010-09-16 Created: 2010-08-28 Last updated: 2011-03-18Bibliographically approved

Open Access in DiVA

fulltext(13296 kB)586 downloads
File information
File name FULLTEXT02.pdfFile size 13296 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Lind, Anders
By organisation
Computer Vision
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 586 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

Total: 883 hits
ReferencesLink to record
Permanent link

Direct link