Paper
8 September 2011 The effect of infrared and visible image fusion on object tracking using correlation matching
Songfeng Yin, Liangcai Cao, Guofan Jin
Author Affiliations +
Abstract
This paper studies on how the performance of object tracking using correlation matching can be affected by the pixel-level infrared and visible image fusion approaches, as compared to tracking using single modality source images. Several classic grayscale and color image fusion approaches have been investigated, with the former including traditional DWT method and our proposed adaptive weighted average method based on fuzzy logic and the latter including both linear and nonlinear color transfer methods. Object tracking in various conditions has been tested on a representative set of both simulated and real captured image sequences. Experimental results suggest that the location precision and robustness of object tracking can be improved effectively using fused images. Among the various tested fusion approaches, the techniques of fuzzy logic based grayscale image fusion and nonlinear color transfer consistently offer the best tracking performance.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Songfeng Yin, Liangcai Cao, and Guofan Jin "The effect of infrared and visible image fusion on object tracking using correlation matching", Proc. SPIE 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, 81933P (8 September 2011); https://doi.org/10.1117/12.900833
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image fusion

Infrared imaging

Visible radiation

Discrete wavelet transforms

Infrared radiation

Fuzzy logic

Image processing

Back to Top