Fusing Infrared and Visible Imageries for Improved Tracking of Moving Targets
Abstract
Video surveillance is an important tool for force protection and law enforcement, and visible and infrared video cameras are the most common imaging sensors used for this purpose. In this report, we present a feasibility study on fusing concurrent visible and infrared imageries to improve the tracking performance of an existing video surveillance system. Image fusion was performed using 13 pixel-based image fusion algorithms, including four simple-combination methods and nine pyramid-based methods. The effects of all 13 algorithms on the detection and tracking performance of a given target tracker were examined. Five of the pyramid-based methods were shown to provide superior performance enhancements, three of which also managed to achieve it with relatively low computational costs.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2011
- Accession Number
- ADA549133
Entities
People
- Alex L. Chan
- Stephen R. Schnelle
Organizations
- United States Army Research Laboratory