As one of the most important methods for limiting urban sprawl, the accurate delineation of the urban–rural boundary not only promotes the intensive use of urban resources, but also helps to alleviate the urban issues caused by urban sprawl, realizing the intensive and healthy development of urban cities. Previous studies on delineating urban–rural boundaries were only based on the level of urban and rural development reflected by night-time light (NTL) data, ignoring the differences in the spatial development between urban and rural areas; so, the comprehensive consideration of NTL and point of interest (POI) data can help improve the accuracy of urban–rural boundary delineation. In this study, the NTL and POI data were fused using wavelet transform, and then the urban–rural boundary before and after data fusion was delineated by multiresolution segmentation. Finally, the delineation results were verified. The verification result shows that the accuracy of delineating the urban–rural boundary using only NTL data is 84.20%, and the Kappa value is 0.6549; the accuracy using the fusion of NTL and POI data on the basis of wavelet transform is 93.2%, and the Kappa value is 0.8132. Therefore, we concluded that the proposed method of using wavelet transform to fuse NTL and POI data considers the differences between urban and rural development, which significantly improves the accuracy of the delineation of urban–rural boundaries. Accurate delineation of urban–rural boundaries is helpful for optimizing internal spatial structure in both urban and rural areas, alleviating environmental problems resulting from urban development, assisting the formulation of development policies for urban and rural fringes, and promoting the intensive and healthy development of urban areas.
Efficient data fusion using wavelet transform: the case of SPOT satellite images