计算机科学 ›› 2021, Vol. 48 ›› Issue (9): 194-199.doi: 10.11896/jsjkx.200800142

• 计算机图形学&多媒体 • 上一篇    下一篇

基于特征优化的SAR图像水华识别方法

毋琳1,2,3, 白澜1,3,4, 孙梦伟1,3,4, 郭拯危1,3,4   

  1. 1 河南大学计算机与信息工程学院 河南 开封475004
    2 河南大学环境与规划学院 河南 开封475004
    3 河南省智能技术与应用工程技术研究中心 河南 开封475004
    4 河南省大数据分析与处理重点实验室 河南 开封475004
  • 收稿日期:2020-08-21 修回日期:2020-10-30 出版日期:2021-09-15 发布日期:2021-09-10
  • 通讯作者: 郭拯危(gzw@henu.edu.cn)
  • 作者简介:henuwl@henu.edu.cn
  • 基金资助:
    国家自然科学基金(61871175);河南省高等学校重点科研项目(19A420005,21A520004);河南省科技攻关计划项目(202102210175,212102210093,212102210101);自然资源部国土卫星遥感应用重点实验室经费资助项目(KLSMNR-202102)

Algal Bloom Discrimination Method Using SAR Image Based on Feature Optimization Algorithm

WU Lin1,2,3, BAI Lan1,3,4, SUN Meng-wei 1,3,4, GOU Zheng-wei1,3,4   

  1. 1 College of Computer and Information Engineering,Henan University,Kaifeng,Henan 475004,China
    2 College of Environment and Planning,Henan University,Kaifeng,Henan 475004,China
    3 Henan Engineering Research Center of Intelligent Technology and Application,Henan University,Kaifeng,Henan 475004,China
    4 Key Laboratory of Analysis and Processing on Big Data of Henan Province,Henan University,Kaifeng,Henan 475004,China
  • Received:2020-08-21 Revised:2020-10-30 Online:2021-09-15 Published:2021-09-10
  • About author:WU Lin,born in 1978,associate professor,master supervisor.Her main research interests include SAR image processing techniques,and SAR image application of water environment.
    GUO Zheng-wei,born in 1963,professor,master supervisor.Her main research interests include SAR image processing techniques,and SAR image application of ecological environment.
  • Supported by:
    National Natural Science Foundation of China(61871175),College Key Research Project of Henan Province(19A420005,21A520004),Plan of Science and Technology of Henan Province(202102210175,212102210093,212102210101) and Key Laboratory of Land Satellite Remote Sensing Application,Ministry of Natural Resources of the People's Republic of China(KLSMNR-202102)

摘要: 内陆湖泊水华现象的频繁爆发,严重影响着地表水环境安全,严重阻碍了我国的生态文明建设。充分发挥合成孔径雷达(Synthetic Aperture Radar,SAR)遥感技术全天时、全天候的优势,可实现大尺度、周期性的水华识别与监测工作,对于地表水生态环境的保护与监管具有重大的现实意义。立足于SAR遥感目标识别技术的研究与应用,文中提出了一种基于特征优化的水华识别方法。该方法基于对水华SAR图像特征的深入分析与提取,应用ReliefF特征优化算法对全部的22个水华特征进行筛选与优化,得到包含10个特征的最优特征子集,并以反向传播(Back Propagation,BP)神经网络为分类识别器完成了多组对比实验,水华识别总体精度最高达81.39%,较优化之前提升了19.38%。实验结果表明,使用最优特征集不仅可以大幅降低算法复杂度,还可以有效地提升水华总体识别精度,具有进一步推广的实用价值。

关键词: ReliefF算法, 合成孔径雷达图像, 水华识别, 水生态, 特征优化

Abstract: The frequent outbreak of algal bloom in inland lakes has seriously affected the safety of surface water environment,and has brought great obstacles to the construction of ecological civilization in China.Taking full advantage of SAR(Synthetic Aperture Radar) remote sensing technologies,large-scale and periodic algal bloom discrimination and monitoring can be realized.It is of great practical significance for the protection and supervision of water environment.Based on the research and application of SAR remote sensing target recognition technology,this paper proposes an algal bloom discrimination method with feature optimization.After the in-depth analysis and extraction of algal bloom image features,the ReliefF algorithm is used to obtain the optimal feature set,which consists of 10 features from all 22 algal bloom features.And then,the BP (Back Propagation) neural network is as the classifier of this discrimination method to carry out a number of comparative experiments.The overall accuracy of the proposed method is 81.39%,which is 19.38% higher than that before optimization.The experimental results show that the optimal feature set can not only greatly reduce the algorithm complexity,but also effectively improve the discrimination accuracy of algal bloom,which has practical value for further promotion.

Key words: Algal bloom discrimination, Feature optimization, ReliefF algorithm, Synthetic aperture radar image, Water ecology

中图分类号: 

  • TP751
[1]TAO F.Air-water CO2 flux in an algae bloom year for Lake Hongfeng,Southwest China:implications for the carbon cycle of global inland waters[J].Acta Geochimica,2017,36(4):658-666.
[2]KATRI R,JOSÉ E C B,MARIA H K V.Identifying Multiple Stressors that Influence Eutrophication in a Finnish Agricultural River[J].Science of the Total Environment,2019,658:1278-1292.
[3]XIE P.Cyanobacteria bloom and its secondary damage[J].Journal of Hydroecology,2015,36(4):1-13.
[4]GUO L E.Doing battle with the green monster of Taihu Lake[J].Science,2007,317(5842):1166.
[5]GUO H D,ZHANG L.60 years of radar remote sensing:Fourstage development.Journal of Remote Sensing[J].Journal of Remote Sensing,2019,23(6):1023-1035.
[6]SUN W W,YANG G,CHEN C,et al.Development status and literature analysis of China's earth observation remote sensing satellites[J].Journal of Remote Sensing,2020,24(5):4-25.
[7]CHEN L F,LIU Y Z,ZHANG P,et al.Road Extraction Algorithm of Multi-feature High-resolution SAR Image Based on Multi-Path RefineNet[J].Computer Science,2020,47(3):156-161.
[8]WANG H,CHEN X,TIAN S Z,et al.SAR Image Recognition Based on Few-shot Learning[J].Computer Science,2020,47(5):124-128.
[9]PENG J X,SU Y Q,XUE X R.SAR Image Feature Retrieval Method Based on Deep Learning and Synchronic Matrix[J].Computer Science,2019,46(6):196-199.
[10]WANG J,WANG S X,YAN F L,et al.Algal bloom range extraction based on ASAR and MODIS images[J].Remote Sen-sing Information,2009,3:54-57.
[11]LIU J,WANG W C.Cyanobacteria bloom extraction based on ASAR and MODIS remote sensing data[J].Journal of Anhui Agricultural Sciences,2013,41(2):889-892.
[12]BRESCIANI M,ADAMO M,DE CAROLIS G,et al.Monitoring blooms and surface accumulation of cyanobacteria in the Curo-nian Lagoon by combining MERIS and ASAR data[J].Remote Sensing of Environment,2014,146:124-135.
[13]WANG G L.Active and passive remote sensing monitoring of cyanobacteria blooms in inland waters[D].Shanghai:East China Normal University,2015.
[14] WU L,WANG L,MIN L,et al.Discrimination of Algal-Bloom Using Spaceborne SAR Observations of Great Lakes in China[J].Remote Sensing,2018,10(5):767.
[15]MERA D,BOLON-CANEDO V,COTOS J M,et al.On the Use of Feature Selection to Improve the Detection of Sea Oil Spills in SAR Images[J].Computers and Geosciences,2017,100:166-178.
[16]RAEISI A,AKBARIZADEH G,MAHMOUDI A.CombinedMethod of an Efficient Cuckoo Search Algorithm and Nonnegative Matrix Factorization of Different Zernike Moment Features for Discrimination between Oil Spills and Lookalikes in SAR Images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(11):4193-4205.
[17]JOHANNESSEN J A,SCHUCHMAN R A,DIGRANCES G,et al.Coastal Ocean Fronts and Eddies Imaged with ERS-1 Synthetic Aperture Radar[J].Journal of Geophysical Research,1996,101:6651-6667.
[18]KONG F X,GAO G.Reflection on the formation mechanism of cyanobacteria bloom in large shallow eutrophication lakes[J].Acta Ecologica Sinica,2005(3):589-595.
[19]KONG F X,MA R H,GAO J F,et al.Theory and Practice of prevention,prediction and early warning of cyanobacteria bloom in Taihu Lake[J].Journal of Lake Sciences,2009(3):10-24.
[20]BAI X H,HU W P,HU Z X,et al.Calculation of wind drift vo-lume of sheet floating algal bloom in Meiliang Bay,Taihu Lake in summer 2004[J].Environmental Science,2005,26(6):57-60.
[21]ZHOU Y Y,CHENG J H,LIU T,et al.Review of Road Extraction for High-resolution SAR Images[J].Computer Science,2020,47(1):124-135.
[22]GUYON I M,GUNN S R,NIKRAVESH M,et al.Feature Extraction:Foundations and Applications[J].Studies in Fuzziness &Soft Computing,2006,205(12):68-84.
[23]KONONENKO I.Estimating attributes:Analysis and exten-sions of RELIEF[C]//European Conference on Machine Lear-ning on Machine Learning. Springer,1994:171-182.
[24]DUAN H,MA R,XU X,et al.Two-Decade Reconstruction of Algal Blooms in China's Lake Taihu[J].Environmental Scien-ce &Technology,2012,43(10):3522-3528.
[25]CHEN Y W,QIN B Q,TEUBNER K,et al.Long-term dyna-mics of phytoplankton assemblages:Microcystis-domination in Lake Taihu,a large shallow lake in China[J].Journal of Plankton Research,2003,25(1):445-453.
[26]YANG L Y,YANG X Y,REN L M,et al.Outbreak mechanism and control measures of cyanobacteria bloom in Taihu Lake[J].Journal of Lake Sciences,2019,31(1):18-27.
[1] 周岳勇,程江华,刘通,王洋,陈明辉.
高分辨率SAR图像道路提取综述
Review of Road Extraction for High-resolution SAR Images
计算机科学, 2020, 47(1): 124-135. https://doi.org/10.11896/jsjkx.190100033
[2] 徐开勇, 肖警续, 郭松, 戴乐育, 段佳良.
基于改进人工蜂群算法的Android恶意应用检测
Android Malicious Application Detection Based on Improved Artificial Bee Colony Algorithms
计算机科学, 2019, 46(11A): 421-427.
[3] 汪磊,曾宪庭,苏金阳.
一种基于多域特征的JPEG图像隐写分析算法
Steganalysis Based on Multi-domain Features for JPEG Images
计算机科学, 2014, 41(6): 94-98. https://doi.org/10.11896/j.issn.1002-137X.2014.06.019
[4] 陈涛,洪增林,邓方安.
基于优化的邻域粗糙集的混合基因选择算法
Hybrid Gene Selection Algorithm Based on Optimized Neighborhood Rough Set
计算机科学, 2014, 41(10): 291-294. https://doi.org/10.11896/j.issn.1002-137X.2014.10.061
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!