An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images

Tree species classification is important for the management and sustainable development of forest resources. Traditional object-oriented tree species classification methods, such as support vector machines, require manual feature selection and generally low accuracy, whereas deep learning technology can automatically extract image features to achieve end-to-end classification. Therefore, a tree classification method based on deep learning is proposed in this study. This method combines the semantic segmentation network U-Net and the feature extraction network ResNet into an improved Res-UNet network, where the convolutional layer of the U-Net network is represented by the residual unit of ResNet, and linear interpolation is used instead of deconvolution in each upsampling layer. At the output of the network, conditional random fields are used for post-processing. This network model is used to perform classification experiments on airborne orthophotos of Nanning Gaofeng Forest Farm in Guangxi, China. The results are then compared with those of U-Net and ResNet networks. The proposed method exhibits higher classification accuracy with an overall classification accuracy of 87%. Thus, the proposed model can effectively implement forest tree species classification and provide new opportunities for tree species classification in southern China.