论文部分内容阅读
Detecting land use/cover (LULC) changes in the rural-urban fringe areas (RUFAs) timely and accurately with satellite image is essential for land use planning and management in China.Though traditional spectral-based change vector analysis (CVA) proved to be an effective and potential method in LULC change detection,it encounters reasonable difficulty in RUFAs because of the deficiency of spectral information in the satellite image.In order to detect LULC changes in RUFAs effectively,this paper proposed an extended CVA approach by combing the textural change information into the traditional spectral-based CVA.The performance of the extended CVA in Haidian district,Beijing,China showed its improvement compared with the traditional spectral-based CVA.The overall accuracy increased from 90.67% to 95.33% and the Kappa coefficient increased from 0.81 to 0.91.The advantage of the extended CVA lies in its integration of spectral change information and textural information to detect LULC changes effectively,especially in discriminating some LULC changes that are spectrally similar but texturally different in RUFAs.The extended CVA has great potential to be widely used to detect LULC changes in the RUFAs which are often heterogeneous and fragmental in nature with rich textural information.