Remote sensing image fusion method based on directionlet domain hidden Markov tree (HMT) model

Abstract

The invention discloses a remote sensing image fusion method based on a directionlet domain hidden Markov tree (HMT) model. The remote sensing image fusion method mainly solves the problems of spectral distortion and lacking of wavelet transform method direction information, wherein the problems exists in an HIS method. The remote sensing image fusion method comprises the following steps: (1) conducting HIS transformation to multispectral images, and obtaining chrominance (H), luminance (I) and saturation (S); (2) enabling full-color images and the component I to conduct directionlet transformation; (3) respectively establishing HMT model for high-frequency coefficients, training to obtain parameter set estimated values, and calculating posterior probability; (4) selecting the optimized high-frequency coefficient according to the posterior probability; (5) fusing low-frequency coefficients by adopting fusion rules of a genetic algorithm; and (6) conducting directionlet inverse transformation to the fused coefficients to obtain a new component I, then conducting HIS inverse transformation by combining components of H and S, and obtaining a final fused image. According to the remote sensing image fusion method based on the directionlet domain HMT model, anisotropic characteristics of source images can be fully abstracted, pertinence in data is fully unearthed, detailed information of the fused image is improved, and meanwhile the spectral characteristics of the multispectral images can be better remained unchanged.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to the fusion technology of multispectral and panchromatic remote sensing images, and can be used in the fields of military affairs, agriculture, geology, ocean, meteorology, environmental protection and the like. Background technique [0002] With the development of remote sensing technology, a large number of military and civilian sensors for various complex applications have emerged. In these multi-sensor systems, the diversity of information representation forms, information capacity, and processing speed requirements all greatly exceed the information synthesis ability of the human brain. Due to the certain redundancy and complementarity between different types of sensor information, how to extract richer, more reliable and more accurate information from the collected data has become a new problem currently facing, so a subject called The technology for information fusion e...

AI Technical Summary

Problems solved by technology

The weighted average image fusion method reduces the contrast of the image; the method based on HIS transformation will distort the spectral characteristics of the fused image, resulting in spectral degradation; the method based on principal component analysis requires a strong relationship between the replaced and replaced data. Usually, this condition does not hold true, so the fusion effect is not ideal; the pyramid-based method takes advantage of its multi-scale and multi-resolution advantages to obtain a better image fusion effect, but due to the pull In the process of Plassian pyramid decomposition, a large amount of redundant information will be generated, which will increase the calculation amount of the fusion process, which is not conducive to real-time processing; in addition, due to the limited direction of image pyramid transformation, it cannot better capture the source The direction information in the image; the fused image obtained based on the wavelet transform method has rich details, clear texture, and better visual effects than other methods, because wavelet transform has excellent characteristics that other methods do not have: wavelet analysis is a new multi- Resolution analysis tool; wavelet is non-redundant, so that the total amount of image data after wavelet decomposition will not increase; because human eyes have different resolutions for high-frequency components in different directions, wavelet decomposition has directionality, which can satisfy human visual requirements of the eye

But the wavelet transform also has its own limitations: the separable wavelet generated by the one-dimensional wavelet has only horizontal, vertical and diagonal basis functions, so it cannot "optimally" represent the singularity of the high-dimensional space; in the standard two-dimensional In the three-dimensional wavelet transform DWT, the one-dimensional filtering and sampling times along the horizontal direction are the same as the vertical direction at the same scale, which is isotropic, but the edge and contour singularity of the image belong to the anisotropic characteristics of the image, which cannot be determined by the standard Two-dimensional wavelet transform effectively captures; Orthogonal wavelet transform does not have translation invariance, which will cause ringing effect in the edge part of the image, that is, false contours appear on the edge of some features, which makes the positioning and expression of image features not robust enough

Images