Hierarchically Structured Multi-View Features for Mobile Visual Search
2014 (English)Conference paper (Refereed)
This paper presents an approach for using hierarchically structured multi-view features for mobile visual search. We utilize a graph model to describe the feature correspondences between multi-view images. To add features of images from new viewpoints, we design a level raising algorithm and the associated multi-view geometric verification, which are based on the properties of the hierarchical structure. With this approach, features from new viewpoints can be recursively added in an incremental fashion. Additionally, we design a query matching strategy which utilizes the advantage of the hierarchical structure. The experimental results show that our structure of the multi-view feature database can efficiently improve the performance of mobile visual search.
Place, publisher, year, edition, pages
2014. 23-32 p.
, Data Compression Conference Proceedings, ISSN 1068-0314
Electrical Engineering, Electronic Engineering, Information Engineering Communication Systems
IdentifiersURN: urn:nbn:se:kth:diva-145041DOI: 10.1109/DCC.2014.43ScopusID: 2-s2.0-84903460945ISBN: 978-147993882-7OAI: oai:DiVA.org:kth-145041DiVA: diva2:715835
2014 Data Compression Conference, DCC 2014; Snowbird, UT; United States; 26 March 2014 through 28 March 2014
QC 201502022014-05-062014-05-062015-02-02Bibliographically approved