Kong Yingying, Zhang Bowen, Yan Biyuan, Liu Yanjuan, Leung Henry, Peng Xiangyang
Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China.
Nanjing Research Institute of Electronics Engineering, Nanjing 210007, China.
Sensors (Basel). 2020 Feb 12;20(4):993. doi: 10.3390/s20040993.
Unmanned aerial vehicles (UAV) have had significant progress in the last decade, which is applied to many relevant fields because of the progress of aerial image processing and the convenience to explore areas that men cannot reach. Still, as the basis of further applications such as object tracking and terrain classification, semantic image segmentation is one of the most difficult challenges in the field of computer vision. In this paper, we propose a method for urban UAV images semantic segmentation, which utilizes the geographical information of the region of interest in the form of a digital surface model (DSM). We introduce an Affiliated Fusion Conditional Random Field (AF-CRF), which combines the information of visual pictures and DSM, and a multi-scale strategy with attention to improve the segmenting results. The experiments show that the proposed structure performs better than state-of-the-art networks in multiple metrics.
