Visual Tracking Algorithm Using Pixel-Pair Feature
Authors:
- Kenji NishidaKNKenji Nishida
- Takio KuritaTKTakio Kurita
- Yasuo OgiuchiYOYasuo Ogiuchi
- Masakatsu HigashikuboMHMasakatsu Higashikubo
- 1 August 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10514651,p. 1808-1811
Abstract
A novel visual tracking algorithm is proposed in this paper. The algorithm uses pixel-pair features to discriminate between an image patch with an object in the correct position and image patches with an object in an incorrect position. The pixel-pair feature is considered to be robust for the illumination change, and also is robust for partial occlusion when appropriate features are selected in every video frame. The tracking precision for a deforming object (skier) is examined and also the occlusion detection method is described.Keywords
This publication has 11 references indexed in Scilit:
- Object Tracking by Maximizing Classification Score of Detector Based on Rectangle FeaturesIEICE Transactions on Information and Systems, 2008
- Ensemble TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Tracking Using Online Feature Selection and a Local Generative Model2007
- Real-Time Tracking via On-line Boosting2006
- Online selection of discriminative tracking featuresIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Fast vehicle detection with probabilistic feature grouping and its application to vehicle tracking2003
- A real-time computer vision system for measuring traffic parameters2002
- Robust image registration by increment sign correlationPattern Recognition, 2002
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- A real-time computer vision system for vehicle tracking and traffic surveillanceTransportation Research Part C: Emerging Technologies, 1998