Efficient Representation of Local Geometry for Large Scale Object Retrieval (2009)
| Citations: | 77 - 7 self |
BibTeX
@MISC{Perd'och09efficientrepresentation,
author = {Michal Perd'och and et al.},
title = {Efficient Representation of Local Geometry for Large Scale Object Retrieval},
year = {2009}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor – local geometry is stored for each feature detected in each image and requires storage larger than the inverted file and term frequency and inverted document frequency weights together. We propose a novel method for learning discretized local geometry representation based on minimization of average reprojection error in the space of ellipses. The representation requires only 24 bits per feature without drop in performance. Additionally, we show that if the gravity vector assumption is used consistently from the feature description to spatial verification, it improves retrieval performance and decreases the memory footprint. The proposed method outperforms state of the art retrieval algorithms in a standard image retrieval benchmark.
Keyphrases
local geometry large scale object retrieval efficient representation art retrieval algorithm art method gravity vector assumption discretized local geometry representation retrieval performance inverted file average reprojection error spatial verification memory footprint object retrieval relative pose spatial extent standard image retrieval benchmark limiting factor local geometry inverted document frequency weight visual word large scale problem feature description novel method term frequency
