多极化星载SAR森林覆盖变化检测方法

详细信息    查看全文 | 推荐本文 |

英文篇名：Forest Cover Change Detection Method Using Multi-Polarization Space-Borne SAR 作者：谷鑫志 ; 陈尔学 ; 李增元 ; 赵磊 ; 范亚雄 ; 王雅慧 英文作者：Gu Xinzhi;Chen Erxue;Li Zengyuan;Zhao Lei;Fan Yaxiong;Wang Yahui;Key Lab.of Remote Sensing and Information Technology, National Forestry and Grassland Administration Research Institute of Forest Resource Information Techniques,CAF; 关键词：ALOS ; PALSAR ; 双极化 ; 森林覆盖 ; 变化检测 ; 马尔科夫随机场 ; 贝叶斯准则 英文关键词：ALOS PALSAR;;dual-polarization;;forest cover;;change detection;;Markov random field;;Bayes' rule 中文刊名：LYKE 英文刊名：Scientia Silvae Sinicae 机构：中国林业科学研究院资源信息研究所国家林业和草原局遥感与信息技术重点开放性实验室; 出版日期：2019-05-15 出版单位：林业科学 年：2019 期：v.55 基金：国家重大科技专项课题“高分森林资源调查应用示范子系统(一期)”(21-Y30B05-9001-13-15-1) 语种：中文; 页：LYKE201905007 页数：11 CN：05 ISSN：11-1908/S 分类号：77-87

摘要

【目的】利用多极化星载SAR数据,分析后向散射强度比值影像的概率密度分布特征,融合后向散射强度信息和影像空间上下文信息,提出一种具有较高检测正确率及较低虚警率和漏警率的森林覆盖变化检测方法,为多极化SAR卫星数据的业务化应用提供技术支撑。【方法】将"2期分别分类森林覆盖变化检测法"(CBFC)与"贝叶斯最大期望-马尔科夫随机场(EM-MRF)变化检测法"相结合,首先采用阈值分割法分别对2期多极化SAR影像进行森林-非森林分类得到初始森林覆盖变化图,然后以初始森林覆盖变化图作为训练数据对多极化比值影像进行Fisher特征变换和EM-MRF分类处理,2个时相的HH、HV极化比值影像经Fisher特征变换转化为一个综合差异影像,输入EM-MRF进行迭代分类得到森林覆盖变化检测结果。以黑龙江省逊克县为试验区,以2期ALOS PALSAR双极化数据为SAR遥感数据,以对2期Landsat-5影像、高空间分辨率遥感影像进行目视解译得到的森林覆盖变化图为参考,对本研究提出方法的有效性与CBFC方法及直接用CBFC提取的森林覆盖变化检测图掩膜EM-MRF地表覆盖变化检测图方法(CBFC-EM-MRF)进行比较评价。【结果】通过Fisher特征变换得到的差异影像可有效增强森林覆盖变化、未变化类别的对比度; CBFC通过阈值分割法进行森林-非森林分类,提取的森林覆盖变化图中出现很多面积很小的虚警检测,漏警率也很高,而本研究提出方法通过MRF加入影像空间上下文信息,提高了检测结果的空间连贯性,森林覆盖变化检测虚警率为1.58%,漏警率为11.87%,正确率为98.36%,检测效果和精度明显优于CBFC和CBFC-EM-MRF。【结论】多极化星载SAR森林覆盖变化检测方法具有收敛性好、检测结果可信度高、需要用户交互较少等特点,对我国高分三号及未来其他多极化SAR卫星的森林资源监测业务应用具有重要参考价值。
        【Objective】 Using multipolar spaceborne SAR data, the probability density distribution characteristics of backscatter intensity ratio images were analyzed, the backscatter intensity information and image spatial context information was fused to develop a forest cover change detection method with high detection accuracy, low false alarm rate and low missing alarm rate, in order to provide technical support for the operational application of multi-polarization SAR satellite data.【Method】 This study developed a forest cover change detection method that combines the "change detection method based on bi-temporal forest cover classification"(CBFC) and the "Bayesian maximum expected-Markov random field(EM-MRF) change detection method ". Firstly, based on the threshold segmentation method, the initial forest cover change map was obtained through forest/non-forest classification of bi-temporal multi-polarization SAR images. Then, Fisher feature transformation and EM-MRF classification were performed on the multi-polarization ratio image with the initial forest cover change map as training data. The results of forest cover change detection were obtained by EM-MRF iteration classification of the composite difference image converted from bi-temporal polarization(HH,HV) ratio image with Fisher feature transformation. In Xunke County, Heilongjiang Province, the effectiveness of the proposed method was evaluated based on bi-temporal ALOS PALSAR dual-polarization SAR data and the reference forest cover change map, which was obtained by visually interpretation of bi-temporal Landsat-5 images and high spatial resolution remote sensing images. And the comparative analysis was conducted between the proposed method, CBFC method and the method of combining the CBFC with EM-MRF by direct masking(CBFC-EM-MRF).【Result】 The difference image obtained by Fisher feature transformation can effectively increase the contrast of the changed/non-changed category of forest cover. There are many wrongly detected small changed areas in the results of CBFC, and the false alarm rate and missed alarm rate of which are also very high. In contrast, the proposed method can improve the spatial coherence of the detection results by considering the context information of the difference image through MRF, and the false alarm rate, missed alarm rate and the accuracy were 1.58%, 11.87% and 98.36% respectively, so both the performance and the accuracy of the proposed method are better than that of CBFC and CBFC-EM-MRF.【Conclusion】 The forest cover change detection method proposed in this paper has the advantages of good convergence, high reliability and demanding less user interaction, so it is of valuable reference value for the operational application of forest resource monitoring using GF-3 and the other multi-polarization SAR satellites to be launched in the future.

引文

董锡超.2014.面向热带雨林的多维度SAR毁林检测技术研究.北京:北京理工大学博士学位论文.(Dong X C.2014.Study on tropical deforestation detection using multi-dimensional SAR.Beijing:PhD thesis of Beijing Institute of Technology.[in Chinese])
    高丛珊,张红,王超,等.2010.广义Gamma模型及自适应KI阈值分割的SAR图像变化检测.遥感学报,14(4):710-724.(Gao C S,Zhang H,Wang C,et al.2010.SAR change detection based on generalized Gamma distribution divergence and auto-threshold segmentation.Journal of Remote Sensing,14(4):710-724.[in Chinese])
    刘萌.2013.极化SAR图像变化检测技术研究.北京:中国科学院大学博士学位论文.(Liu M.2013.Research on change detection of PolSAR images.Beijing:PhD thesis of University of Chinese Academy of Sciencess.[in Chinese])
    沈蕾.2010.基于广义Gamma分布的SAR图像变化检测.成都:西南交通大学硕士学位论文.(Shen L.2010.SAR image change detection based on generalized Gamma distribution.Chengdou:MS thesis of Southwest Jiaotong University.[in Chinese])
    孙晓霞.2011.基于多极化SAR影像的土地利用/土地覆盖变化检测方法研究.徐州:中国矿业大学博士学位论文.(Sun X X.2011.Land use and land cover change detection by multi-polarimetric SAR images.Xuzhou:PhD thesis of China University of Mining & Technology.[in Chinese])
    王虎清.2009.基于广义Gamma混合模型的遥感图像变化检测研究.成都:西南交通大学硕士学位论文.(Wang H Q.2009.The research of change detection in remote sensing images based on generalized Gamma mixture model.Chengdu:MS thesis of Southwest Jiaotong University.[in Chinese])
    王纬华,江涛,张永红,等.2016.基于高分SAR影像的城市用地变化检测.测绘与空间地理信息,37(7):141-147.(Wang W H,Jiang T,Zhang Y H,et al.2016.Detection of urban land use change based on high resolution SAR images.Geomatics & Spatial Information Technology,37(7):141-147.[in Chinese])
    张斌.2013.基于MRF的SAR图像分类与变化检测应用研究.武汉:武汉大学博士学位论文.(Zhang B.2013.Research on the SAR image classification and change detection based on the Markov random field.Wuhan:PhD thesis of Wuhan University.[in Chinese])
    Mermoz S,Le Toan T.2016.Forest disturbances and regrowth assessment using ALOS PALSAR data from 2007 to 2010 in Vietnam,Cambodia and Lao PDR.Remote Sensing,8(3):217.
    Moser G,Serpico S B.2006.Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery.IEEE Transactions on Geoscience and Remote Sensing,44(10):2972-2982.
    Moser G,Serpico S,Vernazza G.2007.Unsupervised change detection from multichannel SAR images.IEEE Geoscience and Remote Sensing Letters,4(2):278-282.
    Moser G,Serpico S B.2009.Unsupervised change detection from multichannel SAR data by Markovian data fusion.IEEE Transactions on Geoscience and Remote Sensing,47(7):2114-2128.
    Pantze A,Santoro M,Fransson J E S.2014.Change detection of boreal forest using bi-temporal ALOS PALSAR backscatter data.Remote Sensing of Environment,155:120-128.
    Santoro M,Pantze A,Fransson J E S,et al.2012.Nation-wide clear-cut mapping in Sweden using ALOS PALSAR strip images.Remote Sensing,4(6):1693-1715.
    Shimada M,Itoh T,Motooka T,et al.2014.New global forest/non-forest maps from ALOS PALSAR data (2007-2010).Remote Sensing of Environment,155:13-31.
    Xiong B,Chen J M,Kuang G.2012.A change detection measure based on a likelihood ratio and statistical properties of SAR intensity images.Remote Sensing Letters,3(3):267-275.