Learning Informative SIFT Descriptors for Attentive Object Detection

Gerald Fritz, Christin Seifert, Lucas Paletta, Horst Bischof

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

With the emerging sensor technologies in mobile devices, such as camera phones, visual interpretation methodologies are challenged to provide solutions within the everydays outdoor urban environment. For this purpose, we propose to apply the 'Informative Descriptor Approach' on the SIFT descriptor [4], in order to de ne the informative SIFT (i-SIFT) descriptor. By attentive matching of i-SIFT keypoints, we provide an innovative method on object detection that signifantly improves SIFT based keypoint matching. i-SIFT tackles the SIFT bottlenecks, e.g., extensive nearest neighbor indexing, by (i) signifantly reducing the descriptor dimensionality, (ii) decreasing the size of object representation by one order of magnitude, and (iii) performing matching exclusively on attended descriptors, as required by resource sensitive devices. The key advantages of informative SIFT (i-SIFT) are demonstrated in a typical outdoor mobile vision experiment on the TSG-20 reference database, detecting buildings with high accuracy.
Original languageEnglish
Title of host publicationProceedings of the Joint Hungarian-Austrian Conference on Image Processing and Pattern Recognition (HACIPPR 2005)
EditorsD. Chetverikov, L. Czuni, M. Vincze
PublisherAustrian Computer Society
Pages95-102
Number of pages8
Publication statusPublished - 1 May 2005
Externally publishedYes
EventJoint Hungarian-Austrian Conference on Image Processing and Pattern Recognition, HACIPPR 2005 - Veszprém, Hungary
Duration: 11 May 200513 May 2005
http://vision.vein.hu/HACIPPR/

Conference

ConferenceJoint Hungarian-Austrian Conference on Image Processing and Pattern Recognition, HACIPPR 2005
Abbreviated titleHACIPPR
Country/TerritoryHungary
CityVeszprém
Period11/05/0513/05/05
Internet address

Keywords

  • n/a OA procedure

Fingerprint

Dive into the research topics of 'Learning Informative SIFT Descriptors for Attentive Object Detection'. Together they form a unique fingerprint.

Cite this