3D Object Localization Using Local Shape Features

Author

Islam, Md Saiful ; Sluzek, Andrzej

Author_Institution

Sch. of Comput. Eng., NTU, Singapore

fYear

2006

fDate

5-8 Dec. 2006

Firstpage

1

Lastpage

6

Abstract

This paper proposes a method to localize a 3D object in cluttered environment. Model of the object is represented by local shape features, computed from some reference images. Localization is performed by stereo images captured simultaneously by a pair of calibrated cameras. First the object is recognized in both images, using the local shape features. Then common features are used for reconstruction of the 3D position of the object. The proposed localization method is robust to different kinds of geometric and photometric transformations in addition to cluttering, partial occlusions and background changes. The accuracy and efficiency of the method is good enough for many practical applications

Keywords

computer vision; feature extraction; image reconstruction; image representation; object detection; object recognition; stereo image processing; 3D object localization; 3D object position reconstruction; cameras; cluttered environment; geometric transformation; local shape features; object recognition; object representation; partial occlusions; photometric transformation; stereo images; visual detection; Cameras; Data mining; Feature extraction; Image recognition; Multidimensional systems; Object detection; Object recognition; Rendering (computer graphics); Shape; Stereo vision; local shape; moment invariants; object localization; relative scale; visual detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Automation, Robotics and Vision, 2006. ICARCV '06. 9th International Conference on

Conference_Location

Singapore

Print_ISBN

1-4244-0341-3

Electronic_ISBN

1-4214-042-1

Type

conf

DOI

10.1109/ICARCV.2006.345221

Filename

4150278