Deep semantic segmentation of unmanned aerial vehicle remote sensing images based on fully convolutional neural network

Abstract

In the era of artificial intelligence and big data, semantic segmentation of images plays a vital role in various fields, such as people’s livelihoods and the military. The accuracy of semantic segmentation results directly affects the subsequent data analysis and intelligent applications. Presently, semantic segmentation of unmanned aerial vehicle (UAV) remote-sensing images is a research hotspot. Compared with manual segmentation and object-based segmentation methods, semantic segmentation methods based on deep learning are efficient and highly accurate segmentation methods. The author has seriously studied the implementation principle and process of the classical deep semantic segmentation model—the fully convolutional neural network (FCN), including convolution and pooling in the encoding stage, deconvolution and upsampling, etc., in the decoding stage. The author has applied the three structures (i.e., FCN-32s, FCN-16s, and FCN-8s) to the UAV remote sensing image dataset AeroScapes. And the results show that the accuracy of vegetation recognition is stable at about 94%. The accuracy of road recognition can reach up to more than 88%. The mean pixel accuracy rate of the whole test dataset is above 91%. Applying full convolution neural network to semantic segmentation of UAV remote sensing images can improve the efficiency and accuracy of semantic segmentation significantly.

Sea and Land Segmentation of Optical Remote Sensing Images Based on U-Net Optimization

“…Zhang Gang of the Chinese Academy of Sciences proposed an optimization algorithm for neural networks [14], that is, before and after matching it with the current superpixel segmentation that performs better. Peng Hu of Harbin Institute of Technology proposed an improved method of deep feature extraction for DeepLab v3+ deep and shallow layer fusion [15], which added a batch normalization layer to optimize the performance of DeepLab v3+ and reduce the training difficulty of the model. Wang Lanyu of Harbin Institute of Technology proposed to use Xception_71 as a feature extraction network to optimize DeepLab v3+ [16].…”