Multi-feature fusion-based recognition and processing of impulse noise in remote sensing images

MA Xiaojian; ZHAO Fashun; LIU Yanbin

doi:10.6046/zrzyyg.2021319

2022 Vol. 34, No. 3

Article Contents

Article navigation > Remote Sensing for Natural Resources > 2022 > 34(3): 17-26

Next Article Previous Article

MA Xiaojian, ZHAO Fashun, LIU Yanbin. 2022. Multi-feature fusion-based recognition and processing of impulse noise in remote sensing images. Remote Sensing for Natural Resources, 34(3): 17-26. doi: 10.6046/zrzyyg.2021319

Citation:

MA Xiaojian, ZHAO Fashun, LIU Yanbin. 2022. Multi-feature fusion-based recognition and processing of impulse noise in remote sensing images. Remote Sensing for Natural Resources, 34(3): 17-26. doi: 10.6046/zrzyyg.2021319

Multi-feature fusion-based recognition and processing of impulse noise in remote sensing images

1. College of Science, Northeast Forestry University, Harbin 150040, China；
2. School of Earth Sciences and Resources, China University of Geosciences(Beijing), Beijing 100083, China

Received Date: 30 September 2021

Revised Date: 15 September 2022

Publish Date: 21 September 2022

Abstract

Abstract

Eliminating impulse noise of high-quality remote sensing images is of great significance for applied research. It has always been a challenge to eliminate high-density impulse noise while remaining detailed information on edges in original remote sensing images. This study concluded that uncertain changes will appear when a remote sensing image is corrupted by impulse noise. Given this, an uncertainty model based on the evidence theory was constructed using multiple features of impulse noise. The BJS divergence and the reliability entropy were fused into the model to obtain new weights and a new probability assignment. Then, the classification between noise and signals was given according to fusion rules and probability transformation, thus effectively reducing the possibility of high-level conflicts. The experimental results show that the classification method proposed in this study is effective even when the noise density is up to over 90% and can well maintain detailed information on different ground objects in the denoised remote sensing images.
- evidence theory /
- uncertainty modeling /
- fusion rules /
- highly conflict /
- remote sensing image

FullText(HTML)

References

[1]	赵洪臣, 周兴华, 彭聪, 等. 一种去除遥感影像混合噪声的集成BM3D方法[J]. 武汉大学学报(信息科学版), 2019, 44(6):925-932. Google Scholar
[2]	Zhao H C, Zhou X H, Peng C et al. An integrated BM3D method for removing mixed noise in remoting sensing image[J]. Geomatics and Information Science of Wuhan University, 2019, 44(6):925-932. Google Scholar
[3]	汪贵平, 杜晶晶, 宋京, 等. 基于梯度倒数的无人机遥感图像融合滤波方法[J]. 科学技术与工程, 2018, 18(31):190-194. Google Scholar
[4]	Wang G P, Du J J, Song J, et al. A fusion filter method for unmanned aerial vehicle remote sensing image based on gradient inverse[J]. Science Technology and Engineering, 2018, 18(31):190-194. Google Scholar
[5]	朱建军, 周靖鸿, 周璀, 等. 一种新的去除遥感影像混合噪声组合滤波方法[J]. 武汉大学学报(信息科学版), 2017, 42(3):348-354. Google Scholar
[6]	Zhu J J, Zhou J H, Zhou C, et al. A new combination filtering method to removing mixed noise of remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2017, 42(3):348-354. Google Scholar
[7]	刘帅. 基于分层稀疏学习和协同表示的高光谱图像去噪和分类[D]. 西安: 西安电子科技大学, 2016. Google Scholar
[8]	Liu S. Hierarchical sparse learning and collaborative representation for hyperspectral imagery restoration and classification[D]. Xi’an: Xidian University, 2016. Google Scholar
[9]	Srinivasan K S, Ebenezer D. A new fast and efficient decision-based algorithm for removal of high-density impulse noises[J]. IEEE Signal Processing Letters, 2007, 14(3):189-192. Google Scholar
[10]	Jayaraj V, Ebenezer D. A new switching-based median filtering scheme and algorithmfor removal of high density salt and pepper noise in images[J]. Journal on Advances in Signal Processing, 2010(1):409-413. Google Scholar
[11]	Dempster A P. Upper and lower probabilities induced by a multivalued mapping[J]. The Annals of Mathematical Statistics, 1967, 38(2):325-339. Google Scholar
[12]	蒋雯. 邓鑫洋. D-S证据理论信息建模与应用[M]. 北京: 科学出版社, 2018. Google Scholar
[13]	Jiang W, Deng X Y. D-S evidence theory information modeling and application[M]. Beijing: Science Press, 2018. Google Scholar
[14]	童涛, 杨桄, 李昕, 等. 基于D-S证据理论的多特征融合SAR图像目标识别方法[J]. 国土资源遥感, 2013, 25(2):37-41.doi: 10.6046/gtzyyg.2013.02.07. Google Scholar
[15]	Tong T, Yang G, Li X, et al. Recognition method of multi-feature fusion based on D-S evidence theory in SAR image[J]. Remote Sensing for Land and Resources, 2013, 25(2):37-41.doi: 10.6046/gtzyyg.2013.02.07. Google Scholar
[16]	李华朋, 张树清, 孙妍. 证据理论结合遥感分类数据能力定量评价研究[J]. 国土资源遥感, 2011, 23(1):26-32.doi: 10.6046/gtzyyg.2011.01.05. Google Scholar
[17]	Li H P, Zhang S Q, Sun Y. The quantitative evaluation of remoting sensing data for supervised evidential classification[J]. Remote sensing for Land and Resources, 2011, 23(1):26-32.doi: 10.6046/gtzyyg.2011.01.05. Google Scholar
[18]	Zhang Z, Han D, Dezert J, et al. A new adaptive switching median filter for impulse noise reduction with predetection based on evidential reasoning[J]. Signal Processing, 2018(147):173-189. Google Scholar
[19]	Ng P E, Ma K. A switching median filter with boundary discriminative noise detection for extremely corrupted images[J]. IEEE Transactions on Image Processing, 2006, 15(6):1506-1516. Google Scholar
[20]	Han D, Dezert J, Duan Z. Evaluation of probability transformations of belief functions fordecision making[J]. IEEE Transactions on Systems,Man,and Cybernetics, 2016, 46(1):93-108. Google Scholar
[21]	Irpino R V. Dynamic clustering of interval data using a wasserstein based distance[J]. Pattern Recognition Letter, 2008, 29(11):1648-1658. Google Scholar
[22]	钱晓亮, 郭雷, 余博. 基于目标尺度的自适应高斯滤波[J]. 计算机工程与应用, 2010, 46(12):14-16. Google Scholar
[23]	Qian X L, Guo L, Yu B. Adaptive Gaussian filter based on object scale[J]. Computer Engineering and Applications, 2010, 46(12):14-16. Google Scholar
[24]	Xiao F. Multi-sensor data fusion based on the belief divergence measure of evidencesand the belief entropy[J]. Information Fusion, 2019,(46):23-32. Google Scholar
[25]	Deng Y. Deng entropy[J]. Chaos,Solitons & Fractals, 2016(91):549-553. Google Scholar
[26]	Jafar I F, AlNa’mneh R A, Darabkh K A. Efficient improvements on the BDND filtering algorithm for the removal of high-density impulse noise[J]. IEEE Transactios on Image Processing, 2013, 22(3):1223-1232. Google Scholar
[27]	Zhao B, Zhong Y, Xia G S, et al. Dirichlet-derived multiple topic scene classification model fusing heterogeneous features for high spatial resolution remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(4):2108-2123. Google Scholar
[28]	Zhao B, Zhong Y, Zhang L, et al. The fisher kernel coding framework for high spatial resolution scene classification[J]. Remote Sensing, 2016, 8(2):157-176. Google Scholar
[29]	Zhu Q, Zhong Y, Zhao B, et al. Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(6):747-751. Google Scholar
[30]	Haidi I, Nicholas S P K, Theam F N. Simple adaptive median filter for the removal of impulse noise from highly corrupted images[J]. IEEE Transactions on Consumer Electronics, 2008, 544(4):1920-1927. Google Scholar