DocumentCode :
3037117
Title :
Joint Geometric Verification and Ranking Using Multi-view Vocabulary Trees for Mobile 3D Visual Search
Author :
Mars, David Ebri ; Hanwei Wu ; Haopeng Li ; Flierl, Markus
Author_Institution :
Sch. of Electr. Eng., KTH R. Inst. of Technol., Stockholm, Sweden
fYear :
2015
fDate :
7-9 April 2015
Firstpage :
459
Lastpage :
459
Abstract :
This paper proposes multi-view vocabulary trees for mobile 3D visual search. We generate hierarchically structured multi-view features and construct a multi-view vocabulary tree from the multi-view images. As the 3D geometry information is incorporated in the multi-view vocabulary tree, it allows us to design an algorithm for fast 3D geometric verification at low computational complexity. With that, we devise an iterative algorithm that accomplishes jointly matching and geometric verification. The experimental results show that our joint approach to matching and verification improves the recall-data rate performance as well as the subjective ranking results for mobile 3D visual search.
Keywords :
computational complexity; image matching; iterative methods; mobile computing; trees (mathematics); 3D geometric verification; 3D geometry information; computational complexity; hierarchically structured multiview features; iterative algorithm; jointly matching; mobile 3D visual search; multiview images; multiview vocabulary trees; recall-data rate performance; subjective ranking; Data compression; Joints; Mobile communication; Search problems; Three-dimensional displays; Visualization; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Data Compression Conference (DCC), 2015
Conference_Location :
Snowbird, UT
ISSN :
1068-0314
Type :
conf
DOI :
10.1109/DCC.2015.82
Filename :
7149322
Link To Document :
بازگشت