A GPU-Accelerated Two Stage Visual Matching

Hannes Fassold, Harald Stiegler, Jakub Rosnery, Marcus Thaler, Werner Bailer
CBMI 2015



Download Download (PDF)   View View   Source Source   



We propose a two stage visual matching pipeline including a first step using VLAD signatures for filtering results, and a second step which reranks the top results using raw matching of SIFT descriptors. This enables adjusting the tradeoff between high computational cost of matching local descriptors and the insufficient accuracy of compact signatures in many application scenarios. We describe GPU accelerated extraction and matching algorithms for SIFT, which result in a speedup factor of at least 4. The VLAD filtering step reduces the number of images/frames for which the local descriptors need to be matched, thus speeding up retrieval by an additional factor of 12-13 without sacrificing mean average precision of full raw descriptor matching.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: