Multispectral Images and Panchromatic Remote Sensing Images Fusion Algorithm Based on Wavelet Transform

DOI: https://doi.org/10.62517/jike.202404112

Author(s)

Xingyue Zhang1,*, Mingju Chen1,2

Affiliation(s)

1School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan, China 2Artificial Intelligence Key Laboratory of Sichuan Province, Sichuan University of Science & Engineering, Yibin, Sichuan, China *Corresponding Author.

Abstract

Multispectral images and panchromatic remote sensing images carry incomplete spectral information, which reduces the application value of spectral images. The fusion of these two types of images can increase the amount of spectral information, highlight the features, and to a certain extent, make up for the shortcomings of the two when they exist separately. However, the existing fusion algorithms cannot solve the problem of spectral distortion well, so this paper proposes a fusion algorithm of multispectral images and panchromatic remote sensing images, through the low-frequency component of multispectral images and the low-frequency component of panchromatic remote sensing images to get the new low-frequency component by the weighted average operation, the high-frequency component of multispectral images and panchromatic remote sensing images high-frequency component to get the new high-frequency component by adopting the rule of great value fusion. The new low-frequency and high-frequency components are finally inverted by wavelet to get the final fused images. Experiments show that the fusion effect of this algorithm is better than other algorithms; especially it can make up for the defects such as spectral distortion or image chunking that exist in some fusion algorithms. Moreover, when the number of wavelet decomposition layers is 2, the fusion images obtained by this algorithm is of better quality.

Keywords

Image Fusion; Wavelet Transform; Multispectral Images; Panchromatic Remote; Sensing Images

References

[1] Gemine V. Multispectral and hyperspectral image fusion in remote sensing: A survey. Information Fusion, 2023, 89405-417. [2] Chen M, Yi S, Lan Z, et al. An Efficient Image Deblurring Network with a Hybrid Architecture. Sensors, 2023, 23 (16). [3] Mingju C, Sihang Y, Mei Y, et al. UNet segmentation network of COVID-19 CT images with multi-scale attention. Mathematical biosciences and engineering: MBE, 2023, 20 (9): 16762-16785. [4] Yingqing H, Zhan Y, Xiaoyu J, et al. Performance Enhanced Elemental Array Generation for Integral Image Display Using Pixel Fusion.Frontiers in Physics, 2021, 9. [5] Ruizhe W, Wang X. Adaptive Enhancement Algorithm of High-Resolution Satellite Image Based on Feature Fusion. Journal of Mathematics, 2022. [6] Palubinskas. Model-based view at multi-resolution image fusion methods and quality assessment measures. International Journal of Image and Data Fusion, 2016, 7 (3): 203-218. [7] Yufei W, Chengchao Q, Qinglei D. Target recognition of heterogeneous fusion images based on improved YOLO model deep learning algorithm. Journal of Physics: Conference Series, 2022, 2170 (1). [8] Remote Sensing; Findings from Chongqing University of Posts and Telecommunications Broaden Understanding of Remote Sensing (Model-based Variational Pansharpening Method with Fast Generalized Intensity-hue-saturation). Journal of Technology, 2019. [9] Gunnam S, Bellamkonda S, Hari R M P, et al. Fusion of hyperspectral and multispectral images based on principal component analysis and guided bilateral filtering. International Journal of System Assurance Engineering and Management, 2022, 15 (1): 439-448. [10] Wavelet Research; Findings in Wavelet Research Reported from Sri Ramakrishna Institute of Technology (Hyperspectral image compression using hybrid transform with different wavelet-based transform coding). Journal of Technology, 2020. [11] Dahui L, Qi F, Jianzhao C, et al. Research on Target Detection Algorithm of Radar and Visible Image Fusion Based on Wavelet Transform. Tehnički vjesnik, 2020, 27 (5): 1563-1570. [12] Harmeet K, Satish K, Kuljinder B, et al. Multi-modality medical image fusion using cross-bilateral filter and neuro-fuzzy approach. Journal of Medical Physics, 2021, 46 (4): 263-277. [13] Chen M, Duan Z, Li L, et al. A Two-Stage Image Inpainting Technique for Old Photographs Based on Transfer Learning. Electronics, 2023, 12 (15). [14] Xianghai W, Xinying W, Ruoxi S, et al. MCT-Net: Multi-hierarchical cross transformer for hyperspectral and multispectral image fusion. Knowledge-Based Systems, 2023, 264 [15] Ahmed J B, Lianfang T, Qiliang D, et al. An Improved Infrared and Visible Image Fusion Using an Adaptive Contrast Enhancement Method and Deep Learning Network with Transfer Learning. Remote Sensing, 2022, 14 (4): 939-939. [16] Zhibo W, Youqiang D, Zengchen Y, et al. Semi-Supervised Support Vector Machine for Digital Twins Based Brain Image Fusion13; Frontiers in Neuroscience,2021,15705323-705323. [17] I S I, A M M, S G E. Multimodal medical image fusion algorithm based on pulse coupled neural networks and nonsubsampled contourlet transform. Medical biological engineering computing, 2022, 61 (1).