A method for detection of known objects in visual search tasks

Author

Sluzek, Andrzej

Author_Institution

Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore

fYear

2008

fDate

21-24 Sept. 2008

Firstpage

214

Lastpage

219

Abstract

The paper outlines a novel method for visual detection of known objects in images of arbitrary contents. The major improvement over the existing techniques using keypoint detectors (e.g. Harris-Plessey, SIFT) is that the areas around pre-detected keypoints are approximated by various geometric patterns. Matching can be, therefore, done by comparing local geometric and colour structures of keypoints and by testing the geometric consistency over sets of matched keypoint pairs. The method can be used primarily for vision-guided search in mobile autonomous devices. The paper presents the mathematical foundations of the method and illustrates its performances for exemplary problems.

Keywords

mobile robots; object detection; robot vision; visual servoing; geometric patterns; known object detection; mobile autonomous devices; vision-guided search; visual search tasks; Detectors; Image analysis; Image databases; Image matching; Information retrieval; Machine vision; Object detection; Spatial databases; Testing; Visual databases; Radon transform; geometric patterns; image matching; keypoints; moments;

fLanguage

English

Publisher

ieee

Conference_Titel

Cybernetics and Intelligent Systems, 2008 IEEE Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-1673-8

Electronic_ISBN

978-1-4244-1674-5

Type

conf

DOI

10.1109/ICCIS.2008.4670873

Filename

4670873