文献类型：期刊文献

英文题名：Data Augmentation in Prototypical Networks for Forest Tree Species Classification Using Airborne Hyperspectral Images

作者：Chen, Long[1,2] Wei, Yuxin[1,2] Yao, Zongqi[1,2] Chen, Erxue[3] Zhang, Xiaoli[1,2]

第一作者：Chen, Long

通信作者：Zhang, XL[1];Zhang, XL[2]

机构：[1]Beijing Forestry Univ, Precis Forestry Key Lab Beijing, Beijing 100083, Peoples R China;[2]Beijing Forestry Univ, Lab Silviculture & Conservat, Minist Educ, Beijing 100083, Peoples R China;[3]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China

年份：2022

卷号：60

外文期刊名：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

收录：;EI(收录号：20221712037994);Scopus(收录号：2-s2.0-85128596773);WOS:【SCI-EXPANDED(收录号:WOS:000788976800010)】；

基金：This work was supported in part by the National Key Research and Development Program of China, Ministry of Science and Technology, under Grant 2017YFD0600900; and in part by the Dragon 5 Cooperation under Grant 59257. (Corresponding author: Xiaoli Zhang.)

语种：英文

外文关键词：Vegetation; Hyperspectral imaging; Forestry; Training; Testing; Task analysis; Feature extraction; Airborne hyperspectral images; data augmentation; MaxUp; prototypical networks (P-Nets); tree species classification

摘要：Accurate and fine multiple tree species supervised classification based on few-shot learning has attracted close attention from researchers, because the sample collection is often hindered in forests. Prototypical networks (P-Nets), as a simple but efficient few-shot learning method, have 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 (PM) 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 (GFF) in Nanning City, Guangxi Province, as the study area, nine 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 PM to obtain the best classification performance. To verify the robustness and validity of the proposed strategy, we applied PM 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 (overall accuracy (OA) and Kappa, are 98.08% and 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 PM data augmentation strategy and backbone proposed in this article.