Intelligence Based Automatic Detection and Classification of Ground Collapses Using Object-Based Image Analysis Method: A Case Study in Paitan of Pearl River delta

摘要

In this paper, a new method is proposed by applying case-based reasoning technique for detecting the ground collapses. The study demonstrates that the high resolution remote sensing images are suitable for monitoring the ground collapses in the study area with karst relief. With the help of object-based image analysis method, the generic algorithm (GA) for optimizing the spatial, shape, spectral, hierarchy and textural features was used in the multi-scale image segmentation with the good fitness value, and then the case library was built for detecting the collapse. The case library is reusable for place-independent detection. The proposed method has been tested in the Pearl River Delta in south China. The result of ground-collapse detection is well.