The Quantitative Evaluation of Remote Sensing Data for Supervised Evidential Classification
LI Hua-peng 1,2， ZHANG Shu-qing 1， SUN Yan 1，2
（1.Northeast Institute of Geography and Agricultural Ecology， CAS， Changchun 130012， China； 2.Graduate University of Chinese Academy of Sciences， Beijing 100049， China）
摘要DS（Dempster-Shafer）证据理论具有结合多源数据的能力，在遥感分类中应用越来越广泛。然而，并不是所有数据源利用证据理论结合后都能提高目标类别的基本概率分配（Basic Probability Assignment，BPA），从而提高遥感分类效果。如何对证据结合的效果进行评价已成为应用证据理论的一个关键问题。本文提出了评价证据结合效果的证据结合指数（evidence combine index，eci），选择TM影像的第5、7波段作为验证eci的多源数据，应用eci评价证据结合效果，利用证据理论遥感分类Kappa系数的变化对证据结合指数进行了验证。结果表明，该指数能够反映证据理论结合效果，为定量评价证据理论结合多源数据效果奠定了基础。
Abstract： DS (Dempster-Shafer) evidence theory has the capability of combining multisource data，and has been used more and more widely in the remote sensing classification field. However，it is not true that all the data sources can improve target category’s Basic Probability Assignment (BPA) so as to improve the remote sensing classification accuracy. The evaluation of the effect of combined evidence is therefore a key point in the application of DS evidence theory. This paper proposed the evidence combine index (eci) for evaluating the combined evidence. The authors chose band 5 and band 7 of TM image as verification data，applied the eci index to evaluate the combining effect，and used the variation of kappa coefficient before and after evidence combination classification to validate the eci. The results show that the eci index can reflect the effect of evidence combination and thus lay the foundation for evaluating supervised evidential classification quantitatively.
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.
LI Hua-Peng, ZHANG Shu-Qing, SUN Yan. The Quantitative Evaluation of Remote Sensing Data for Supervised Evidential Classification. REMOTE SENSING FOR LAND & RESOURCES, 2011, 23(1): 26-32.
［1］Carrere V.Development of Multiple Source Data-processing for Structural-analysis at a Regional Scale ［J］.Photogrammetric Engineering and Remote Sensing，1990，56(5)：587-595.［2］Peddle D R，Ferguson D T.Optimisation of Multisource Data Analysis：an Example Using Evidential Reasoning for GIS Data Classification ［J］.Computers & Geosciences，2002，28(1)：45-52.［3］Peddle D R.Knowledge Formulation for Supervised Evidential Classification ［J］.Photogrammetric Engineering and Remote Sensing，1995，61(4)：409-417.［4］Franklin S E，Peddle D R，Dechka J A，et al.Evidential Reasoning with Landsat TM,DEM and GIS Data for Landcover Classification in Support of Grizzly Bear Habitat Mapping ［J］.International Journal of Remote Sensing，2002，23(21)：4633-4652.［5］Kartikeyan B，Majumder K L，Dasgupta A R.An Expert-system for Land-cover Classification ［J］.IEEE Transactions of Geoscience and Remote Sensing，1995，33(1)：58-66.［6］Cohen Y，Shoshany M.Analysis of Convergent Evidence in an Evidential Reasoning Knowledge-based Classification ［J］.Remote Sensing of Environment，2005，96(3-4)：518-528.［7］Hajj E M，Begue A，Guillaume S，et al.Integrating SPOT-5 Time Series，Crop Growth Modeling and Expert Knowledge for Monitoring Agricultural Practices——The Case of Sugarcane Harvest on Reunion Island ［J］.Remote Sensing of Environment，2009，113(10)：2052-2061.［8］Momani A B，McClean S，Morrow.Using Dempster-Shafer to Incorporate Knowledge into Satellite Iimage Classification ［J］.Artificial Intelligence Review，2006，25(1-2)：161-178.［9］LeHegaratMascle S，Bloch I，VidalMadjar D.Application of Dempster-Shafer Evidence Theory to Unsupervised Classification in Multisource Remote Sensing ［J］.IEEE Transactions on Geoscience and Remote Sensing，1997，35(4)：1018-1031.［10］Diaconis P.Mathematical-theory of Evidence-Shafer ［J］.Journal of the American Statistical Association，1978，73(363)：677-678.［11］Gordon J，Shortliffe E H.A Method for Managing Evidential Reasoning in a Hierarchical Hypothesis Space ［J］.Artificial Intelligence，1985，26(3)：323-357.［12］Lein J K.Applying Evidential Reasoning Methods to Agricultural Land Cover Classification ［J］.International Journal of Remote Sensing，2003，24(21)：4161-4180.
2011, Vol. 23 
