Scene-consistent detection of feature points in video sequences

Ariel Tankus, Yehezkel Yeshurun

Research output: Contribution to journalConference articlepeer-review

Abstract

Detection of feature points in images is an important preprocessing stage for many algorithms in Computer Vision. We address the problem of detection of feature points in video sequences of 3D scenes, which could be mainly used for obtaining scene correspondence. The main feature we use is the zero crossing of the intensity gradient argument. We analytically show that this local feature corresponds to specific constraints on the local 3D geometry of the scene, thus ensuring that the detected poins are based on real 3D features. We present a robust algorithm that tracks the detected points along a video sequence, and suggest some criteria for quantitative evaluation of such algorithms. These criteria serve in a comparison of the suggested operator with two other feature trackers. The suggested criteria are generic and could serve other researchers as well for performance evaluation of stable point detectors.

Original languageEnglish
Pages (from-to)I631-I638
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - 2001
Event2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI, United States
Duration: 8 Dec 200114 Dec 2001

Fingerprint

Dive into the research topics of 'Scene-consistent detection of feature points in video sequences'. Together they form a unique fingerprint.

Cite this