Deep Learning Based Unmanned Aerial Vehicle Landcover Image Segmentation Method

Abstract:

Compilation of landcover maps needs high qualified landcover data with precise classification. Traditional techniques to obtain these have the problem of high cost, heavy workload and unsatisfied results. To this end, a semantic segmentation method was proposed for unmanned aerial vehicle (UAV) images, which was used to segment and classify different types of land areas to obtain landcover data. Firstly, the UAV images were annotated which contained various land use types at pixel level according to the latest national standards, and the highresolution complex landcover image data set of UAV was established. Then, several significant improvements based on original design of semantic segmentation model DeepLabV3+ were made, including replacing the original backbone network Xception+ with the deep residual network ResNet+; adding joint upsampling unit after backbone network to enhance the encoder’s capability of information transfer and conduct preliminary upsampling; adjusting dilated rates of atrous spatial pyramid pooling (ASPP) unit to smaller ones and removing global pooling connection of the module; and improving the decoder by fusing more lowlevel features. Finally, the models were trained and tested on the UAV highresolution landcover dataset. The presented model achieved good experimental results with pixel accuracy of 95.06% and mean intersectionoverunion of 81.22% on the test set, which was 14.55 percentage points and 25.49 percentage points higher than that of the original DeepLabV3+ model respectively. The proposed method was also superior to the commonly used semantic segmentation methods FCN-8S (pixel accuracy was 32.39%, mean intersectionoverunion was 8.39%) and PSPNet (pixel accuracy was 87.50%, mean intersectionoverunion was 50.75%). The results showed that the proposed method can obtain more accurate landcover data and meet the needs of compiling fine landcover maps. 