Small UAV-based multi-temporal change detection for monitoring cultivated land cover changes in mountainous terrain

ABSTRACT Land degradation, soil erosion and illegal occupation in mountainous terrain of southern China have led to an ever-decreasing stock of cultivated land. Small unmanned aerial vehicles (UAVs) are used to collect images with very fine spatial and temporal resolutions. However, acquired image pairs of the same scene often contain scale changes, noises and rotated changes at different temporal scales. To address these problems, we propose a small UAV-based multi-temporal change detection for cultivated land cover in mountainous terrain which contains the following contributions. First, the multi-scale feature description includes convolutional neural network (CNN)-based feature descriptor (CFD) and neighbouring structure descriptor (NSD), where CFD is generated using layers formed via a pretrained Visual Geometry Group (VGG)-16 architecture. Second, a gradually increasing selection of inliers is defined for improving the robustness of feature point registration. Finally, intuitionistic fuzzy C-Means (IFCM) classifier is adopted to generate a similarity matrix between image pair of geometric correction process. The performance of proposed method is validated on multi-temporal image pairs taken by the small UAV. Experimental results show that the proposed method can detect cultivated land cover change at small size and scattered distribution landscapes, obtain satisfactory change detection results.