Scale Saliency: Applications in Visual Matching, Tracking and View-Based Object Recognition

Hare, Jonathon S. and Lewis, Paul H. (2003) Scale Saliency: Applications in Visual Matching, Tracking and View-Based Object Recognition. Distributed Multimedia Systems 2003 / Visual Information Systems 2003, Florida International University, Miami, Florida, United States. 24 - 26 Sep 2003. pp. 436-440 .

Record type: Conference or Workshop Item (Paper)

Abstract

In this paper, we introduce a novel technique for image matching and feature-based tracking. The technique is based on the idea of using the Scale-Saliency algorithm to pick a sparse number of ‘interesting’ or ‘salient’ features. Feature vectors for each of the salient regions are generated and used in the matching process. Due to the nature of the sparse representation of feature vectors generated by the technique, sub-image matching is also accomplished. We demonstrate the techniques robustness to geometric transformations in the query image and suggest that the technique would be suitable for view-based object recognition. We also apply the matching technique to the problem of feature tracking across multiple video frames by matching salient regions across frame pairs. We show that our tracking algorithm is able to explicitly extract the 3D motion vector of each salient region during the tracking process, using a single uncalibrated camera. We illustrate the functionality of our tracking algorithm by showing results from tracking a single salient region in near real-time with a live camera input.

Text

vis03-hare.pdf - Other

Download (3MB)

More information

Published date: 2003

Additional Information: Event Dates: 24-26/09/2003

Venue - Dates: Distributed Multimedia Systems 2003 / Visual Information Systems 2003, Florida International University, Miami, Florida, United States, 2003-09-24 - 2003-09-26

Keywords: Saliency, Object Recognition, Scale, Tracking, Matching

Organisations: Web & Internet Science