Infrared and Visible Image Fusion Based on NSCT and Deep Learning
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
An image fusion method is proposed on the basis of depth model segmentation to overcome theshortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deepBoltzmann machine is used to perform the priori learning of infrared and visible target and backgroundcontour, and the depth segmentation model of the contour is constructed. The Split Bregman iterativealgorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then,the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and thecorresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results ofMATLAB indicates that the proposed algorithm can obtain the fusion result of both target and backgroundcontours effectively, with a high contrast and noise suppression in subjective evaluation as well as great meritsin objective quantitative indicators.
Abstract
An image fusion method is proposed on the basis of depth model segmentation to overcome theshortcomings of noise interference and artifacts caused by infrared and visible image fusion. Firstly, the deepBoltzmann machine is used to perform the priori learning of infrared and visible target and backgroundcontour, and the depth segmentation model of the contour is constructed. The Split Bregman iterativealgorithm is employed to gain the optimal energy segmentation of infrared and visible image contours. Then,the nonsubsampled contourlet transform (NSCT) transform is taken to decompose the source image, and thecorresponding rules are used to integrate the coefficients in the light of the segmented background contour. Finally, the NSCT inverse transform is used to reconstruct the fused image. The simulation results ofMATLAB indicates that the proposed algorithm can obtain the fusion result of both target and backgroundcontours effectively, with a high contrast and noise suppression in subjective evaluation as well as great meritsin objective quantitative indicators.
참고문헌 (19)
- Z. Wang, "Multi-focus image fusion using PCNN", Pattern Recognition, 43(6), pp.2003~2016 (2010)
- D. P. Bavirisetti, "Fusion of infrared and visible sensor images based on anisotropic diffusion and Karhunen-Loeve transform", IEEE Sensors Journal, 16(1), pp.203~209 (2016)
- V. Bhateja, "Multimodal medical image sensor fusion framework using cascade of wavelet and contourlet transform domains", IEEE Sensors Journal, 15(12), pp.6783~6790 (2015)
- Y. Yang, "Multifocus image fusion based on NSCT and focused area detection", IEEE Sensors Journal, 15(5), pp.2824~2838 (2015)
- H. Zheng, "Visible and infrared image fusion algorithm based on shearlet transform", Chinese Journal of Scientific Instrument, 33(7), pp.1613~1619 (2012)
- J. Wang, "Fusion method for visible and infrared images based on non-subsampled contourlet transform and sparse representation", Acta Armamentarii, 34(7), pp.815~820 (2013)
- T. Gan, "Image fusion algorithm based on block-DCT in wavelet domain", Acta Physica Sinica, 60(11) (2011)
- W. Kong, "Novel fusion method for visible light and infrared images based on NSST–SF–PCNN", Infrared Physics & Technology, 65, pp.103~112 (2014)
- Y. Shen, "Infrared and visible images fusion based on Tetrolet transform", Spectroscopy and Spectral Analysis, 33(6), pp.1506~1511 (2013)
- G. Dahl, "Phone recognition with the mean-covariance restricted Boltzmann machine", Advances in Neural Information Processing Systems, 23, pp.469~477 (2010)
- R. Salakhutdinov, "An efficient learning procedure for deep Boltzmann machines", Neural Computation, 24, pp.1967~2006 (2012)
- S. M. Ali Eslami, "The shape Boltzmann machine: a strong model of object shape", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.406~413 (2012)
- L. J. Latecki, "Shape descriptors for non-rigid shapes with a single closed contour", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.424~429 (2000)
- W. Li, "Total variation blind deconvolution employing split Bregman iteration", Journal of Visual Communication and Image Representation, 23(3), pp.409~417 (2012)
- A. L. Da Cunha, "The nonsubsampled contourlet transform : theory, design, and applications", IEEE Transactions on Image Processing, 15(10), pp.3089~3101 (2006)
- D. Brunet, "On the mathematical properties of the structural similarity index", IEEE Transactions on Image Processing, 21(4), pp.1488~1499 (2012)
- Q. Zhang, "Fusion of infrared and visible light images based on nonsubsampled contourlet transform", Journal of Infrared and Millimeter Waves(Chinese Edition), 26(6), pp.476~480 (2007)
- "TNO UN Camp image"[URL]
- X. Li, "Efficient fusion for infrared and visible images based on compressive sensing principle", IET Image Processing, 5(2), pp.141~147 (2011)