矿区遥感图像去噪方法研究

车守全; 李涛; 包从望; 江伟

doi:10.13272/j.issn.1671-251x.2021090086

矿区遥感图像去噪方法研究

doi: 10.13272/j.issn.1671-251x.2021090086

六盘水师范学院矿业与土木工程学院, 贵州六盘水　553000

基金项目: 贵州省教育厅资助项目(黔教合KY字〔2020〕125)。

详细信息

作者简介:
车守全(1992—)，男，贵州纳雍人，讲师，硕士，研究方向为遥感图像退化复原及超分辨率重建，E-mail: chesq_njtu@163.com

中图分类号: TD67
计量
- 文章访问数: 108
- HTML全文浏览量: 44
- PDF下载量: 17
- 被引次数: 0
出版历程
- 收稿日期: 2021-09-27
- 修回日期: 2022-01-13
- 刊出日期: 2022-01-20

Research on denoising method of remote sensing image in mining area

School of Mines and Civil Engineering, Liupanshui Normal University, Liupanshui 553000, China

摘要

摘要: 去噪是矿区遥感图像得以有效应用的重要预处理步骤。现有的基于统计、基于域变换、基于学习等遥感图像去噪方法普遍存在细节过度平滑、纹理保持不足等问题。基于引导滤波良好的边缘保持特性，提出了迭代引导滤波方法，通过对残差信息进行引导映射，并迭代进行引导滤波及超参数收缩，增强了遥感图像边缘特征提取效果；将迭代引导滤波与传统的小波软阈值、非局部均值(NLM)滤波、三维块匹配 (BM3D)滤波等去噪方法结合，有效提高了传统方法的峰值信噪比，其中NLM滤波、BM3D滤波的去噪性能提升效果最明显；将迭代引导滤波与BM3D滤波融合，通过BM3D滤波初步获取去噪图像，得到残差数据，然后采用迭代引导滤波对残差数据进行处理，在提升图像去噪效果的同时，很好地保持了图像细节特征；将迭代引导滤波与BM3D滤波融合方法用于矿区遥感图像的煤矸石场识别及滑坡区域边缘识别，取得了较好的效果。
- 矿区遥感图像 /
- 图像去噪 /
- 边缘保持 /
- 迭代引导滤波 /
- 三维块匹配 /
- BM3D
Abstract: Denoising is an important preprocessing step for the effective application of remote sensing images in mining area. The existing remote sensing image denoising methods based on statistics, domain transformation and learning generally have the problems of excessive smoothing of details and insufficient texture preservation. Based on the good edge-preserving property of guided filtering, an iterative guided filtering method is proposed. The method enhances the edge characteristics extraction effect of remote sensing images by guided mapping of residual information, and iteratively performing guided filtering and hyper-parameter shrinkage. The iterative guided filtering is combined with traditional wavelet soft threshold, non-local mean (NLM) filtering, block matching 3D(BM3D) filtering and other denoising methods, which improves the peak signal-to-noise ratio of the traditional method effectively. Among them, NLM filtering and BM3D filtering have the most obvious effects on improving the denoising performance. The iterative guided filtering and BM3D filtering are fused, and the denoised images are initially obtained through BM3D filtering to obtain residual data. The iterative guided filtering is used to process the residual data. While improving the image denoising effect, the image detail characteristics are well preserved. The iterative guided filtering and BM3D filtering fusion method are used for coal gangue yard identification and landslide area edge recognition in remote sensing images of mining areas, and good results have been achieved.
- remote sensing image of mining area /
- image denoising /
- edge preserving /
- iterative guided filtering /
- block-matching and 3D /
- BM3D

HTML全文

图 1 迭代引导滤波过程

Figure 1. Iterative guided filtering process

下载: 全尺寸图片幻灯片

图 2 噪声图像迭代引导滤波结果

Figure 2. Iterative guided filtering results of noise image

下载: 全尺寸图片幻灯片

图 3 迭代引导滤波处理后图像PSNR

Figure 3. PSNR of the image processed by iterative guided filtering

下载: 全尺寸图片幻灯片

图 4 遥感图像去噪结果

Figure 4. Denoising results of remote sensing images

下载: 全尺寸图片幻灯片

图 5 煤矸石场识别应用效果

Figure 5. Application effect of coal gangue yard identification

下载: 全尺寸图片幻灯片

图 6 滑坡区域边缘识别应用效果

Figure 6. Application effect of landslide area edge recognition

下载: 全尺寸图片幻灯片

表 1 迭代引导滤波对于典型去噪方法的提升结果

Table 1. Improvement results of iterative guided filtering to typical denosing methods

指标	K−SVD字典学习	小波软阈值	NLM滤波	BM3D滤波
PSNR增大值/dB	0.6	1.9	3.1	3.0
SSIM	0.1	0.2	0.4	0.4
运算时间增加值/s	0.5	0.7	1.0	1.2

下载: 导出CSV

表 2 不同方法的去噪性能对比

Table 2. Comparison of denosing performance of different methods

指标	小波软阈值	K−SVD 字典学习	非局部相似性 K−SVD字典学习	BM3D 滤波	融合方法
PSNR/dB	23.6	25.2	27.3	28.2	30.8
SSIM	0.76	0.72	0.75	0.86	0.92

下载: 导出CSV

参考文献(20)

[1]	王义方, 李新举, 李富强, 等. 基于多时相遥感影像的采煤塌陷区典型扰动轨迹识别−以山东省济宁市典型高潜水位矿区为例[J]. 地质学报,2019,93(增刊1):301-309. WANG Yifang, LI Xinju, LI Fuqiang, et al. Identification of typical disturbance trajectory in coal mining subsidence area based on multi-temporal remote sensing images[J]. Acta Geologica Sinica,2019,93(S1):301-309.
[2]	杨宏业, 赵银娣, 董霁红. 基于纹理转移的露天矿区遥感图像超分辨率重建[J]. 煤炭学报,2019,44(12):3781-3789. YANG Hongye, ZHAO Yindi, DONG Jihong. Remote sensing image super-resolution of open-pit mining area based on texture transfer[J]. Journal of China Coal Society,2019,44(12):3781-3789.
[3]	宋国策, 张志. 内蒙古新巴尔虎右旗多金属矿区扬尘风积物遥感监测方法[J]. 国土资源遥感,2020,32(2):46-53. SONG Guoce, ZHANG Zhi. Remote sensing monitoring method for dust and wind accumulation in multimetal mining area of Xin Barag Right Banner, Inner Mongolia[J]. Remote Sensing for Land & Resources,2020,32(2):46-53.
[4]	周斌, 李雨鸿, 李辑, 等. 岫岩偏岭矿区植被修复生态环境监测评估[J]. 航天返回与遥感,2019,40(3):103-110. doi: 10.3969/j.issn.1009-8518.2019.03.013 ZHOU Bin, LI Yuhong, LI Ji, et al. Monitoring and assessment of vegetation restoration ecology environment in Xiuyan pianling-mining area[J]. Spacecraft Recovery & Remote Sensing,2019,40(3):103-110. doi: 10.3969/j.issn.1009-8518.2019.03.013
[5]	汤伏全, 李林宽, 李小涛, 等. 基于无人机影像的采动地表裂缝特征研究[J]. 煤炭科学技术,2020,48(10):130-136. TANG Fuquan, LI Linkuan, LI Xiaotao, et al. Research on characteristics of mining-induced surface cracks based on UAV images[J]. Coal Science and Technology,2020,48(10):130-136.
[6]	张元军. 基于双边滤波与小波阈值法的矿区遥感图像处理[J]. 金属矿山,2017(9):170-173. doi: 10.3969/j.issn.1001-1250.2017.09.035 ZHANG Yuanjun. Remote sensing image processing method of mining area based on bilateral filtering algorithm and wavelet thresholding method[J]. Metal Mine,2017(9):170-173. doi: 10.3969/j.issn.1001-1250.2017.09.035
[7]	FENG Xubin, ZHANG Wuxia, SU Xiuqin, et al. Optical remote sensing image denoising and super-resolution reconstructing using optimized generative network in wavelet transform domain[J]. Remote Sensing,2021,13(9):1858-1880. doi: 10.3390/rs13091858
[8]	WEN Nu, YANG Shizhi, CUI Shengcheng. High resolution remote sensing image denoising based on curvelet-wavelet transform[J]. Journal of Zhejiang University(Engineering Science),2015,49(1):79-86.
[9]	王跃跃, 陈蓉, 于丽君, 等. 结合二维EMD与自适应高斯滤波的遥感卫星影像去噪[J]. 测绘通报,2019(2):22-27. WANG Yueyue, CHEN Rong, YU Lijun, et al. Denoising from remote sensing satellite image based on two-dimensional EMD and adaptive Gauss filtering[J]. Bulletin of Surveying and Mapping,2019(2):22-27.
[10]	王小兵. 融合提升小波阈值与多方向边缘检测的矿区遥感图像去噪[J]. 国土资源遥感,2020,32(4):46-52. WANG Xiaobing. Denoising algorithm based on the fusion of lifting wavelet thresholding and multidirectional edge detection of remote sensing image of mining area[J]. Remote Sensing for Land & Resources,2020,32(4):46-52.
[11]	HUANG Zhenghua, ZHANG Yaozong, QIAN Li, et al. Unidirectional variation and deep CNN denoiser priors for simultaneously destriping and denoising optical remote sensing images[J]. International Journal of Remote Sensing,2019(15):5737-5748.
[12]	TIAN Chunwei, XU Yong, ZUO Wangmeng. Image denoising using deep CNN with batch renormalization[J]. Neural Networks,2020,121:461-473. doi: 10.1016/j.neunet.2019.08.022
[13]	LIU Jing, XIANG Pengxia, ZHANG Xiaoyan. An improved generative adversarial network for remote sensing image denoising[C]//The 13th International Conference on Digital Image Processing, Singapore, 2021: 11878-11886.
[14]	秦振涛, 杨茹. 基于结构性字典学习的毛儿盖遥感图像去噪研究[J]. 遥感技术与应用,2019,34(4):793-798. QIN Zhentao, YANG Ru. Remote sensing image of Mao'ergai denoising based on structured dictionary learning[J]. Remote Sensing Technology and Application,2019,34(4):793-798.
[15]	马晓乐. 基于稀疏表示的去噪声遥感图像融合算法优化[D]. 北京: 北京交通大学, 2020. MA Xiaole. The algorithm optimization for de-noised remote sensing fusion based on sparse representation[D]. Beijing: Beijing Jiaotong University, 2020.
[16]	陈曦. 基于深度卷积神经网络的图像去噪[D]. 合肥: 合肥工业大学, 2019. CHEN Xi. Image denoising based on deep convolutional neural networks[D]. Hefei: Hefei University of Technology, 2019.
[17]	冯旭斌. 基于深度学习的光学遥感图像去噪与超分辨率重建算法研究[D]. 西安: 中国科学院大学(中国科学院西安光学精密机械研究所), 2020. FENG Xubin. Research on deep-learning based optical remote sensing image denosing and super-resoution reconstructing algorithm[D]. Xi’an: University of Chinese Academy of Science(Xi'an Institute of Optics and Precision Mechanics of Chinese Academy of Sciences), 2020.
[18]	HE Kaiming, SUN Jian, TANG Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.
[19]	DABOV K, FOI A, KATKOVNIK V, et al. Image denoising by sparse 3D transform-domain collaborative filtering[J]. IEEE Transactions on Image Processing,2007:2080-2095.
[20]	刘佳丽. 基于遥感的露天灰岩矿山开采信息提取[D]. 唐山: 华北理工大学, 2018. LIU Jiali. The opencast limestone mine information extraction based on remote sensing[D]. Tangshan: North China University of Science and Technology, 2018.