Mobile 3D visual search using the Helmert transformation of stereo features

Author

Haopeng Li ; Flierl, Markus

Author_Institution

Sch. of Electr. Eng., KTH R. Inst. of Technol., Stockholm, Sweden

fYear

2013

fDate

15-18 Sept. 2013

Firstpage

3470

Lastpage

3474

Abstract

This paper presents a scheme for mobile 3D visual search that facilitates mobile recognition of 3D objects. We use a multi-view approach to extract the 3D geometric information of the query objects and integrate it into SIFT descriptors. To meet a given transmission bandwidth, we use a rate-constrained quad-tree representation for feature selection and encoding. With this approach, we are able to progressively match the query features against the stereo features in the database and implement a robust geometric verification with the Helmert transformation. The experimental results show that our proposed approach to mobile 3D visual search outperforms JPEG and single-view SIFT-based search.

Keywords

feature extraction; feature selection; image coding; image matching; image retrieval; mobile computing; object recognition; stereo image processing; transforms; tree data structures; 3D geometric information extraction; 3D object mobile recognition; Helmert transformation; JPEG; SIFT descriptors; encoding; feature selection; mobile 3D visual search; multiview approach; query feature matching; query object; rate-constrained quad-tree representation; robust geometric verification; scale-invariant feature transforms; single-view SIFT-based search; stereo features; 3D geometric verification; Helmert transformation; Mobile visual search;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2013 20th IEEE International Conference on

Conference_Location

Melbourne, VIC

Type

conf

DOI

10.1109/ICIP.2013.6738716

Filename

6738716