Research on semantic segmentation of unmanned aerial vehicle visual image based on deep learning—take the outdoor environment of Anhui University of Finance & Economics as an example

In recent years, with the rapid development of unmanned aerial vehicle (UAV) technology, UAV processing visual information, especially image semantic segmentation technology, has developed rapidly. This paper proposes a semantic segmentation model, which has achieved high accuracy on CityScapes data set, and has been verified on the newly collected data set, and the verification results are in line with the actual situation.