Please wait a minute...
浙江大学学报(工学版)
Journal of ZheJiang University (Engineering Science)  2022, Vol. 56 Issue (4): 764-774    DOI: 10.3785/j.issn.1008-973X.2022.04.016
    
Water extraction from unmanned aerial vehicle remote sensing images
Yan BIAN(),Yu-sheng GONG*(),Guo-peng MA,Chang WANG
School of Civil Engineering, University of Science and Technology Liaoning, Anshan 114051, China
Download: HTML     PDF(1839KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A new method named automatic segmentation (AUCSN), which combines edge detection algorithm with the object-oriented method, was proposed in order to solve the problems such as noise interference, spectral confusion, segmentation scale error, and water index unavailable which happen in water extraction from unmanned aerial vehicle (UAV) images. An anisotropic diffusion filtering algorithm was used to denoise the image. The Canny edge detection operator was used to extract the edge of the denoised image, and the extraction results were reconstructed with the denoised image. Then an improved absolute mean difference variance ratio method was used to select the optimal segmentation scale for the reconstructed image to conduct multi-scale segmentation. A model combined with the spectral, morphological, and texture feature of the water object was established in order to coarsely extract water objects from the segmented image. The morphological closed operation was used to fill the holes of the coarse extraction results, realizing water extraction. Results show that the AUCSN method can improve the extraction efficiency and the extraction accuracy can reach 96%.

Key words： unmanned aerial vehicle image      denoising      Canny      multi-scale segmentation      feature extraction      morphology     
Received: 09 May 2021      Published: 24 April 2022
CLC:  TP 75  
Fund:  国家自然科学基金青年科学基金资助项目(41801294)；武汉大学测绘遥感信息工程国家重点实验室珞珈一号特别开放研究基金资助项目(18T07)
Corresponding Authors: Yu-sheng GONG     E-mail: 997166041@qq.com;38642709@qq.com
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Yan BIAN
Yu-sheng GONG
Guo-peng MA
Chang WANG
Cite this article:

Yan BIAN,Yu-sheng GONG,Guo-peng MA,Chang WANG. Water extraction from unmanned aerial vehicle remote sensing images. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 764-774.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2022.04.016     OR     https://www.zjujournals.com/eng/Y2022/V56/I4/764


基于无人机遥感影像的水体提取方法

针对无人机（UAV）影像水体提取出现的噪声干扰、光谱混淆、分割尺度难把握、无法使用水体指数等问题，提出边缘检测算法结合面向对象方法的新水体提取方法（AUCSN）. 采用各向扩散滤波算法对影像去噪；采用Canny边缘检测算子对去噪后影像进行边缘提取，提取结果与去噪后影像进行波段重组，利用改进的邻域绝对均值差分方差比法对重组影像选取最优分割尺度，开展多尺度分割. 结合水体对象的光谱、形态、纹理特征建立模型，对分割后影像实现水体粗提取. 将粗提取结果利用形态学闭运算填充孔洞，实现水体提取. 实验结果表明，采用AUCSN方法进行水体提取，不仅提高了提取效率，而且提取精度能够达到96%.


关键词： 无人机影像,  去噪,  Canny,  多尺度分割,  特征提取,  形态学 
Fig.1 Experimental data of UAV remote sensing images
Fig.2 Reference images of water vector information in study area
Fig.3 Flow chart of AUCSN water extraction method
Fig.4 Flow chart of M-SS multi-scale segmentation method
Fig.5 Partially magnified images of denoising effect of experimental data
去噪方法 SSIM
人工湖 万水河 南沙河
中值滤波 0.863 0.795 0.758
均值滤波 0.754 0.731 0.715
P-M滤波 0.976 0.953 0.981
Tab.1 SSIM before and after PSNR of images before and after denoising by three denoising methods
去噪方法 PSNR/dB
人工湖 万水河 南沙河
中值滤波 36.258 35.976 35.683
均值滤波 33.684 35.976 35.541
P-M滤波 38.419 39.186 39.232
Tab.2 PSNR of images before and after denoising by three denoising methods
Fig.6 Edge detection results are superimposed with hand-drawn boundary vectors and their locally magnified images
Fig.7 Segmentation renderings with or without Canny
Fig.8 Segmentation renderings with different weights of Canny layer
方法 t/s
人工湖 万水河 南沙河
有Canny参与 54.28 9.73 16.76
无Canny参与 95.36 16.06 27.17
Tab.3 Time consumption with or without Canny involved in multi-scale segmentation
实验区域 M n r μ
人工湖 ≤930 ≥580 ≥2 ≤50
万水河 ≤840 ≥760 ≥15 ≤45
南沙河 ≤820 ≥660 ≥9 ≤41
Tab.4 Threshold setting for AUCSN method
Fig.9 Results of crude extraction of water in study area
Fig.10 Results of closed operation processing in research area
Fig.11 Results of water extraction by different methods
实验区域 实验方法 P/% Q/% R/% t/s
人工湖 AUCSN方法 96.34 3.66 2.31 87.32
人工湖 无Canny-AUCSN方法 90.46 9.54 11.98 120.67
人工湖 K-Mean方法 85.46 14.54 18.32 53.13
人工湖 文献[12]方法 90.12 9.88 6.43 150.76
万水河 AUCSN方法 97.62 2.38 1.02 39.43
万水河 无Canny-AUCSN方法 89.03 10.97 9.65 59.31
万水河 K-Mean方法 86.62 13.38 26.85 30.11
万水河 文献[12]方法 88.86 11.14 7.85 80.19
南沙河 AUCSN方法 97.47 2.53 1.84 49.65
南沙河 无Canny-AUCSN方法 86.91 4.87 5.89 68.83
南沙河 K-Mean方法 85.73 14.27 9.01 38.74
南沙河 文献[12]方法 87.66 12.34 8.98 95.66
Tab.5 Statistical table of water extraction accuracy and operating efficiency
[1]   JIA K, JIANG W, LI J Spectral matching based on discrete particle swarm optimization: a new method for terrestrial water body extraction using multi-temporal Landsat 8 images[J]. Remote Sensing of Environment, 2018, 209: 1- 18
doi: 10.1016/j.rse.2018.02.012
[2]   STABLER L B Management regimes affect woody plant productivity and water use efficiency in an urban desert ecosystem[J]. Urban Ecosystems, 2008, 11 (2): 197- 211
doi: 10.1007/s11252-008-0050-2
[3]   YANG F, GUO J H, TAN H Automated extraction of urban water bodies from ZY-3 multi-spectral imagery[J]. Water, 2017, 9 (2): 144
doi: 10.3390/w9020144
[4]   徐涵秋 利用改进的归一化差异水体指数( MNDWI) 提取水体信息的研究[J]. 遥感学报, 2005, 9 (5): 589- 595
XU Han-qiu By using the improved normalized difference water index (MNDWI) to extract water body information research[J]. Remote Sensing, 2005, 9 (5): 589- 595
[5]   LIRA J. Segmentation and morphology of open water bodies from multispectral images [J]. International Journal of Remote Sensing. 2006, 27(18): 4015-4038.
[6]   GAUTAM V K, GAURAV P K, MURUGAN P, et al Assessment of surface water dynamics in Bangalore using WRI, NDWI, MNDWI, supervised classification and K-T transformation[J]. Aquatic Procedia, 2015, 4: 739- 746
doi: 10.1016/j.aqpro.2015.02.095
[7]   BRYANT R G, RAINEY M P. Investigation of flood inundation on playas within the zone of Chotts, using a time-series of AVHRR [J]. Remote Sensing of Environment. 2002, 82(2/3): 360–375.
[8]   范亚洲, 张珂, 刘林鑫, 等 水库水体的最大类间方差迭代遥感提取方法[J]. 水资源保护, 2021, 37 (3): 50- 55
FAN Ya-zhou, ZHANG Ke, LIU Lin-xin, et al Maximum inter-class variance iterative remote sensing extraction method for reservoir water bodies[J]. Water Resources Protection, 2021, 37 (3): 50- 55
[9]   孙芳 遥感图像水体识别方法的比较与改进[J]. 遥感技术, 2012, 33: 6854- 6875
SUN Fang Comparison and improvement of water body recognition methods in remote sensing images[J]. Remote Sensing Technology, 2012, 33: 6854- 6875
[10]   CHEN Y, FAN R, YANG X, et al Extraction of urban water bodies from high-resolution remote-sensing imagery using deep learning[J]. Water, 2018, 10 (5): 585
doi: 10.3390/w10050585
[11]   何红术, 黄晓霞, 李红旮 基于改进U-Net网络的高分遥感影像水体提取[J]. 地球信息科学学报, 2020, 22 (10): 2010- 2022
HE Hong-shu, HUANG Xiao-xia, LI Hong-ga High resolution remote sensing image water extraction based on improved U-Net network[J]. Journal of Geo-information Science, 2020, 22 (10): 2010- 2022
[12]   秦慧杰, 高磊, 梁文广, 等 面向对象的无人机影像水体变化监测方法[J]. 水土保持通报, 2018, 36 (4): 67- 71
QIN Hui-jie, GAO Lei, LIANG Wen-guang, et al Object-oriented method for monitoring water body change in UAV image[J]. Bulletin of Soil and Water Conservation, 2018, 36 (4): 67- 71
[13]   周晓明 基于特征于规则的河流水系信息提取研究[J]. 长江科学院院报, 2018, 35 (8): 128- 131
ZHOU Xiao-ming Research on river system information extraction based on feature rules[J]. Journal of Changjiang River Scientific Research Institute, 2018, 35 (8): 128- 131
doi: 10.11988/ckyyb.20180441
[14]   PERONA P, MALIK J Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12 (7): 629- 639
[15]   李艳华. 基于国产高分一号影像的新疆山区河流及桥梁信息提取技术研究 [D]. 乌鲁木齐: 新疆大学, 2015.
LI Yan-hua. Research on information extraction technology of rivers and bridges in xinjiang mountainous area based on GF-1 image [D]. Urumqi: Xinjiang University, 2015.
[16]   STEELE M K, HEFFERNAN J B Morphological characteristics of urban water bodies: mechanisms of change and implications for ecosystem function[J]. Ecological Applications, 2014, 24 (5): 1070- 1084
[17]   杨博雄, 陈颖, 于杰. 卫星遥感影像分水岭分割与边缘检测的海岸线提取 [J]. 电子技术与软件工程, 2020(11): 170-171.
YANG Bo-xiong, CHEN Ying, YU Jie. Coastline extraction based on watershed segmentation and edge detection of satellite remote sensing images [J], Electronics and Software Engineering, 2020(11): 170-171.
[18]   丁月平, 史玉峰 高空间分辨率遥感影像分类最优分割尺度[J]. 辽宁工程技术大学学报:自然科学版, 2014, 33 (1): 56- 61
DING Yue-ping, SHI Yu-feng Optimal segmentation scale for high spatial resolution remote sensing image classification[J]. Journal of Liaoning Technical University: Natural Science, 2014, 33 (1): 56- 61
[19]   谭衢霖, 刘正军, 沈伟 一种面向对象的遥感影像多尺度分割方法[J]. 北京交通大学学报, 2007, (4): 111- 114
TAN Qu-lin, LIU Zheng-jun, SHEN Wei An object-oriented multi-scale segmentation method for remote sensing image[J]. Journal of Beijing Jiaotong University, 2007, (4): 111- 114
[20]   王昶, 张永生, 韩世静. 基于频域显著性方法和ELM的遥感影像变化检测 [J]. 华中科技大学学报: 自然科学版, 2020, 48(5): 19-24.
WANG Chang, ZHANG Yong-sheng, HAN Shi-jing. Remote sensing image change detection based on frequency domain saliency method and ELM [J]. Journal of Huazhong University of Science and Technology: Natural Science Edition, 2020, 48(5): 19-24.
[21]   林荣清, 王延正, 刘晓恒. 基于 eCognition 的水体提取研究 [J]. 科技与创新, 2020(19): 17-20.
LIN Rong-qing, WANG Yan-zheng, LIU Xiao-heng. Research on water extraction based on eCognition [J]. Technology and Innovation, 2020(19): 17-20.
[22]   詹福雷. 基于面向对象的高分辨率遥感影像信息提取[D]. 长春: 吉林大学, 2014.
ZHAN Fu-lei. High resolution remote sensing image information extraction based on object-oriented [D]. Changchun: Jilin University, 2014.
[23]   邹橙. 基于GF-2遥感影像的水体信息提取方法研究 [D]. 合肥: 合肥工业大学, 2019.
ZOU Cheng. Research on water body information extraction method based on GF-2 remote sensing image [D]. Hefei: Hefei University of Technology, 2019.
[24]   WANG Z, BOVIK A C, SHEIKH H R Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13 (4): 600- 612
doi: 10.1109/TIP.2003.819861
[1] Xun CHENG,Jian-bo YU. Monitoring method for machining tool wear based on machine vision[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(5): 896-904.
[2] Zhe-he YAO,Cao-qi ZHANG,Qi-wei SONG,Xi-jiang LU,Jian-qiang KONG,Jian-hua YAO. Ultrasonic assisted laser repair of V-grooves in nickel-based superalloy[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(5): 887-895.
[3] Fang LIU,Zhen WANG,Rui-di LIU,Kai WANG. Short-term forecasting method of wind power generation based on BP neural network with combined loss function[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(3): 594-600.
[4] Jing-xin CHANG,Xian-jun GAO,Yuan-wei YANG,Shao-hua LI,Ping WANG. Building boundary optimization method based on object-oriented contour constraint GGVF Snake model[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(10): 1847-1855.
[5] Zhen JIA,Wen-de DONG,Gui-li XU,Shi-peng ZHU. Image Poisson denoising algorithm based on Markov fields of experts[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(6): 1164-1169.
[6] Yi-xiong FENG,Kang-jie LI,Yi-cong GAO,Hao ZHEN,Jian-rong TAN. Shaft surface defect detection method based on feature and morphology reconstruction[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(3): 427-434.
[7] Mei-ying QIAO,Xia-xia TANG,Shu-hao YAN,Jian-ke SHI. Bearing fault diagnosis based on improved sparse filter and deep network fusion[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(12): 2301-2309.
[8] Xiao-hu ZHAO,Liang-fei YIN,Cheng-long ZHAO. Image captioning based on global-local feature and adaptive-attention[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(1): 126-134.
[9] Wan-liang WANG,Xiao-han YANG,Yan-wei ZHAO,Nan GAO,Chuang LV,Zhao-juan ZHANG. Image enhancement algorithm with convolutional auto-encoder network[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(9): 1728-1740.
[10] Gui-ran HE,Qi LI,Hua-jun FENG,Zhi-hai XU,Yue-ting CHEN. Dual-focal camera continuous digital zoom based onCNN and feature extraction[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(6): 1182-1189.
[11] Yue DONG,Hua-jun FENG,Zhi-hai XU,Yue-ting CHEN,Qi LI. Attention Res-Unet: an efficient shadow detection algorithm[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(2): 373-381.
[12] Xiang-long ZHAO,Jie CHEN,Rong-jing HONG,Hua WANG,Yuan-yuan LI. Adaptive feature extraction method for slewing bearing based on Wavelet leader and optimized isometric mapping method[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(11): 2092-2101.
[13] TONG Shui-guang, ZHANG Yi-dong, XU Jian, CONG Fei-yun. Spectral band refined composite multiscale fuzzy entropy and its application in fault diagnosis of rolling bearings[J]. Journal of ZheJiang University (Engineering Science), 2018, 52(8): 1509-1516.
[14] YU Yong, ZHOU Yang, CAO Peng, ZHAO Gang. In-process model construction method based on model-based definition model[J]. Journal of ZheJiang University (Engineering Science), 2018, 52(6): 1025-1034.
[15] GE Dan dong, TONG Lei, WU Ning, HUA Chen, DU Jia. Parametric analysis and reconstruction method of village’s road morphology[J]. Journal of ZheJiang University (Engineering Science), 2017, 51(2): 279-286.