LAUSR

Accurate and fine multiple tree species supervised classification based on few-shot learning has attracted close attention from researchers since the sample collection is often hindered in forests. Prototypical networks (P-Net), as a simple but efficient few-shot learning method, has significant advantages in forest tree species classification. Nevertheless, the overfitting phenomenon caused by the lack of training samples is still prevalent in few-shot classifiers, which brings challenges to training accurate classification models. In this study, we proposed a novel Proto-MaxUp framework to minimize the issue of overfitting from the perspective of data augmentation and a feature extraction backbone for tree species classification. Taking Gaofeng Forest Farm in Nanning City, Guangxi Province as the study area, 9 tree species, cutting-site and road were classified. First, by analyzing the effects of a series of popular data augmentation methods and their combinations in different parts of the P-Net, several effective data augmentation pools were established. Then, the pools aforementioned were combined with Proto-MaxUp to obtain the best classification performance. In order to verify the robustness and validity of the proposed strategy, we applied Proto-MaxUp to the other four popular public hyperspectral datasets, and achieved excellent results. Finally, this efficient data augmentation method was used in different feature extraction backbones. The results show that the classification accuracy was greatly improved with the optimal backbone (OA and Kappa are 98.08%, 0.9789, respectively), and the difference between training accuracy and test accuracy is less than 2%. It is concluded that the accurate and fine classification for multiple tree species can be realized by the Proto-MaxUp data augmentation strategy and backbone proposed in this paper.