Fusion of hyperspectral and panchromatic images using an average filter and a guided filter☆
Introduction
Image fusion is a process which can synthesize and extract the information of two or more different images to obtain improved information by using a certain algorithm [1]. Remote sensing image fusion is an important part of image fusion. Remote sensing image fusion aims to combine the information of different spectral and spatial resolutions images to achieve more useful information [2]. Low spatial resolution hyperspectral (HS) image and high spatial resolution panchromatic (PAN) image are provided by various sensors. The HS image is a low spatial resolution image but has high spectral resolution. The PAN image is a high spatial resolution image with low spectral resolution. Hence the fusion of hyperspectral and panchromatic images is a meaningful technology because it can produce a fused image with the high spectral resolution of the former and the high spatial resolution of the latter.
A large number of methods have been proposed for the fusion of hyperspectral and panchromatic images [3]. They can be broadly separated into five classes: component substitution (CS) algorithms, multiresolution analysis (MRA) algorithms, matrix factorization algorithms, Bayesian algorithms, and hybrid algorithms [4]. CS algorithms and MRA algorithms are traditional fusion methods. CS approaches convert the HS image into another data space where spectral and spatial information are separated. Then the spatial component is replaced by the PAN image [5]. The CS techniques contain algorithms such as the generalized intensity-hue-saturation (GIHS) [6], the principal component analysis (PCA) [7], [8], the Gram-Schmidt (GS) [9], and the GS Adaptive (GSA) [10] method. Those CS methods have three main advantages: 1. High fidelity of the spatial details [11], 2. Fast and simple implementation [6], and 3. Good robustness [11]. But the CS techniques also have a serious shortcoming. The methods can generate significant spectral distortion [12].
MRA approaches inject the spatial information of the PAN image into the HS image. MRA approaches include algorithms, such as the smoothing filter-based intensity modulation (SFIM) [13], the MTF-Generalized Laplacian Pyramid (MTF-GLP) [14], the MTF-GLP with High Pass Modulation (MTF-GLP-HPM) [15], and the decimated wavelet transform (DWT) [16] method. The advantages of the MRA methods are spectral consistency and temporal coherence [17]. The main shortcoming is the complicated implementation [3].
Matrix factorization approaches, Bayesian approaches, and hybrid approaches are proposed recently. Matrix factorization algorithms and Bayesian algorithms are model based methods. They perform well but are accomplished with high computational cost, e.g., the coupled nonnegative matrix factorization (CNMF) [18], the Bayesian HySure [19], the Bayesian Sparsity promoted Gaussian prior (Bayesian Sparse) [20], [21], and the Bayesian Naive Gaussian prior (Bayesian Naive) [22] method. Hybrid methods use concepts from different methods integrated into one method, such as the guided filter PCA (GFPCA) [23] method. The GFPCA method can preserve the spectral information well. However, the GFPCA method produces lots of blurs because the spatial information is not sufficiently integrated in the fused product.
This paper proposes a novel hyperspectral image fusion method with an average filter and a guided filter (AFGF) to solve the problems mentioned above. Based on the model of component substitution methods, we propose a simple and effective approach to retrieve the spatial information of the HS image by average filtering at first. Then to overcome the serious spectral distortion of component substitution methods, the guided filter is used for extracting more detailed spatial information from the PAN image, which has been sharpened. Finally, the appropriate injection gains matrix is presented to reduce the spectral and spatial distortion. Experimental results illustrate that the method using the enhanced PAN image can achieve better effects. Experimental results also demonstrate that the proposed fusion method performs superior in terms of subjective and objective evaluations.
Section snippets
Component substitution pansharpening methods
Component substitution (CS) is a popular and classical pansharpening method. CS technique projects the HS image into another space to separate spectral and spatial information [12]. Then the transformed spatial information is substituted by the histogram-matched PAN image. Finally, the fused image is obtained by applying the inverse spectral transformation [3]. Many CS pansharpening methods are extended from multispectral images to hyperspectral images.
A general formulation of the CS method is
Proposed method
Fig. 1 shows the main processes of the proposed hyperspectral pansharpening technique with average and guided filters. The proposed approach mainly consists of three steps. First, the spatial information of the HS image is extracted by average filtering. Then, a guided filter is applied to obtain more detailed spatial information from the PAN image which has been sharpened. Finally, the injection gains matrix is generated.
The traditional component substitution methods rely on substituting the
Experimental results and analysis
In this part, the experimental results of the proposed hyperspectral pansharpening technique with an average filter and a guided filter (AFGF) are compared with six state-of-the-art image fusion methods. There are the principal component analysis (PCA) method [7], [8], the Gram-Schmidt adaptive (GSA) method [10], the hybrid method based on a guided filter and PCA (GFPCA) method [23], the coupled nonnegative matrix factorization (CNMF) method [18], the MTF-GLP with High Pass Modulation
Conclusions
The intent of this paper is to introduce a new hyperspectral image fusion method which uses an average filter and a guided filter. This method is based on the component substitution approach. To reduce the amount of calculation, we first propose a simple method that utilizes the average filter to obtain the spatial information of the HS image . Subsequently, the PAN image is sharpened to enhance the spatial detail. In order to avoid the spectral distortion, a guided filter is used in transferring
Acknowledgments
The authors would like to thank the editors, and the anonymous reviewers for their insightful comments and suggestions which have greatly improved this paper. This work was supported by the National Science Foundation of China under Grants 61222101, 61272120, 61301287, 61301291 and 61350110239.
References (31)
- et al.
A new look at IHS-like image fusion methods
Inform. Fusion
(2001) - et al.
Multisensor image fusion in remote sensing: concepts, methods and applications
Int. J. Remote Sens.
(1998) Multi-source remote sensing data fusion: status and trends
Int. J. Image Data Fusion
(2010)- et al.
Hyperspectral pansharpening: a review
IEEE Geosci. Remote Sens. Mag.
(2015) - et al.
Comprehensive review on fusion techniques for spatial information enhancement in hyperspectral imagery
Multidimension. Syst. Signal Process.
(2016) - et al.
Structuring contemporary remote sensing image fusion
Int. J. Image Data Fusion
(2015) - et al.
Extracting spectral contrast in Landsat thematic mapper image data using selective principal component analysis
Photogramm. Eng. Remote Sens.
(1989) - et al.
An efficient pan-sharpening method via combined adaptive PCA approach and contourlets
IEEE Trans. Geosci. Remote Sens.
(2008) - C. Laben, B. Brower, Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening, U.S....
- et al.
Improving component substitution pansharpening through multivariate regression of MS+pan data
IEEE Trans. Geosci. Remote Sens.
(2007)
A theoretical analysis of the effects of aliasing and misregistration on pansharpened imagery
IEEE J. Sel. Top. Signal Process.
Synthesis of multispectral images to high spatial resolution: a critical review of fusion methods based on remote sensing physics
IEEE Trans. Geosci. Remote Sens.
Smoothing filter based intensity modulation: a spectral preserve image fusion technique for improving spatial details
Int. J. Remote Sens.
MTF-tailored multiscale fusion of high-resolution MS and pan imagery
Photogramm. Eng. Remote Sens.
Contrast and error-based fusion schemes for multispectral image pansharpening
IEEE Geosci. Remote Sens. Lett.
Cited by (11)
Spectral Profile Partial Least-Squares (SP-PLS): Local multivariate pansharpening on spectral profiles
2023, ISPRS Open Journal of Photogrammetry and Remote SensingContrast stretching based pansharpening by using weighted differential evolution algorithm
2022, Expert Systems with ApplicationsGuided filter-based multi-focus image fusion through focus region detection
2019, Signal Processing: Image CommunicationCitation Excerpt :Guided filter is also used to multi-scale decomposition in visible and infrared image fusion [30,33,34]. Thirdly, due to preserving local shapes, guided filter is used to detail enhancement in image fusion, such as infrared detail enhancement [35], multi-spectral detail enhancement [36,37]. In addition, Yan et al. [38] employed guided filter to extract salient features in focus region, and obtained initial decision map by using a mixed focus measure, which combines the variance of image intensities and the energy of the image gradient.
Enhanced U-Net-based segmentation and heuristically improved deep neural network for pulmonary emphysema diagnosis
2023, Sadhana - Academy Proceedings in Engineering SciencesBody weight estimation of yak based on cloud edge computing
2021, Eurasip Journal on Wireless Communications and NetworkingHyperspectral imaging for bloodstain identification
2021, Sensors
- ☆
This paper has been recommended for acceptance by Zicheng Liu.