30 October 2009 Fusion of infrared and visual image sequences based on moving target detection and DT-CWT
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953J (2009) https://doi.org/10.1117/12.833934
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
Combined with moving target detecting theory, a novel algorithm based on dual-tree complex wavelet transform was proposed to fuse infrared and visible image sequences. Firstly, a moving target detecting method was applied to separate moving targets. Then we performed dual-tree complex wavelet transform on each image pair. In order to maximumly retain the target information as well as to achieve high efficiency, different fusion rules were designed for both target and background regions within low and high frequency subbands. Finally, the fusion results were obtained through the inverse dual-tree complex wavelet transform. Experimental results show that the proposed algorithm could effectively integrate important information of target regions from both infrared and visible image sequences. The obtained results are stable and consistent for time, and have better performance than those of traditional wavelet-based fusion algorithm which processes image sequence as independent frames in subjective visual quality and objective evaluation indices.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cheng Zhao, Cheng Zhao, Mengyin Fu, Mengyin Fu, } "Fusion of infrared and visual image sequences based on moving target detection and DT-CWT", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953J (30 October 2009); doi: 10.1117/12.833934; https://doi.org/10.1117/12.833934
PROCEEDINGS
8 PAGES


SHARE
Back to Top