Research Area 5: Video Data Mining and Target Tracking: A Model Adaptation and Feedback Control Approach
Abstract
This project involves detecting objects from various video samples by searching for local features to describe each part of the image, and feeding these detections to a grid-based Bayesian algorithm. A constrained shape manifold method for shape based recognition and retrieval has been developed through building a novel quantitative shape description scheme that constructs constrained shape spaces with the aid of physically meaningful transformations of the underlying structural invariant. The grid-based algorithm has been developed for tracking that drastically outperforms the existing algorithms in terms of computational efficiency, accuracy and robustness. Furthermore, by judiciously incorporating feature representation, sample generation and sample weighting, the grid-based approach accommodates contrast change, jitter, target deformation and occlusion. Tracking performance of the proposed grid-based algorithm is compared with two recent algorithms, the gradient vector flow snake tracker and the Monte Carlo tracker, in the context of leukocyte tracking and UAV-based tracking. This comparison indicates that the proposed tracking algorithm is approximately 100 times faster, and at the same time, is significantly more accurate and more robust, thus enabling real-time robust tracking.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 06, 2014
- Accession Number
- ADA605921
Entities
People
- Scott T. Acton
- Zongli Lin
Organizations
- University of Virginia