Fusion technique for SAR and Gray Visible Image based on Hidden Markov Model in Non-subsample Shearlet Transform Domain

Abstract

To exact the more directional information and important detail information from the images effectively, a novel image fusion algorithm for SAR and gray visible image based on the Hidden Markov Model in the Non-subsample Shearlet Transform (NSST) domain is proposed. In NSST domain, the low frequency coefficients are fused by standard deviation. Meanwhile, the NHMT model is built to train the high frequency coefficients. After that, the energy of gradient is used to select the trained coefficients. Then, the low frequency and high frequency images are fused by inverse transformation of NSST to get the final image. Finally, the simulation proves that compared with other mufti-scale HMT models and traditional NSST fusion strategy, the proposed method in this paper can promote the fusion quality and enhance the information of the images, reducing noise as well.

Research on Target Detection Algorithm of Radar and Visible Image Fusion Based on Wavelet Transform

“…M p T ≥ , the coefficients of the low frequency sub-band are processed by the average fusion strategy, such as Eqs. (8), (9) and (10).…”

“…Aiming at the disadvantages of easy-to-loss target information and low contrast images of the fusion images of SAR and visible images in multi-scale fusion algorithm, a fast fusion algorithm of SAR and optical images based on improved l 1 norm and sparse representation is proposed to retain target information of the source images effectively [9]. Literature [10] proposed a fusion algorithm for SAR and visible images in the nonsubsample wavelet transform domain with Hidden Markov Model. The low frequency factorsare fused by standard deviation.…”