Using Projection Pursuit Learning Network Architecture to Detect Land Use Changes

摘要：

A robust method to conduct land use change detection between multi-temporal images using projection pursuit learning network architecture (PPLNA) is proposed.The method uses a parallel approach that includes three different PPLNs:two of them are used to generate the change map using the multi-spectral information,while the third produces a change mask exploiting multi-temporality.The distinctive feature and major merit of PPLNA from traditional neural network for land use change detection are the proposed method simultaneously exploits both the post classification of multi-spectral and multi-temporal information that is associated with the changes values of the pixel spectral reflectance,and hence improve the change detection accuracies.To validate the performance of the proposed method,the experiments using the ETM+ images for the area of Calgary have been carried out.The accuracies of the final classification and change detection maps have been evaluated with ground truth comparisons.The experimental result demonstrates that the proposed method achieves better accuracies.

关键词： projection pursuit learning network change detection ETM image land use

作者: Bo WU Bo HUANG Yong YAN

作者单位: Key lab of spatial data mining and information sharing of ministry of education,Fuzhou university,Fu Department of geography and resource management,The Chinese university of HongKong,Shatin,N.T.,Hong Department of Urban and Environment,University of Science and Technology of Suzhou,Suzhou,China

会议类型: 国际会议

会议名称: 第16届国际地理信息科学与技术大会(16th International Conference on GeoInformatics and the Joint Conference)

会议地点: 广州

会议语种:英文

在线出版日期: 2008-06-28（万方平台首次上网日期，不代表论文的发表时间）