Integrating UAV-Based RGB Imagery with Semi-Supervised Learning for Tree Species Identification in Heterogeneous Forests

文献类型： 外文期刊

第一作者： Hou, Bingru

作者： Hou, Bingru;Chen, Mengyuan;Gouda, Mostafa M.;Liu, Fei;Feng, Xuping;Lin, Chenfeng;Zhao, Yunpeng;Gouda, Mostafa M.;Chen, Yuefeng

作者机构：

关键词： UAV-based RGB imagery; tree species identification; semi-supervised learning; heterogeneous forests; phenology

期刊名称：REMOTE SENSING （ 影响因子：4.1； 五年影响因子：4.8 ）

ISSN：

年卷期： 2025 年 17 卷 15 期

页码：

收录情况： SCI

摘要： The integration of unmanned aerial vehicle (UAV) remote sensing and deep learning has emerged as a highly effective strategy for inventorying forest resources. However, the spatiotemporal variability of forest environments and the scarcity of annotated data hinder the performance of conventional supervised deep-learning models. To overcome these challenges, this study has developed efficient tree (ET), a semi-supervised tree detector designed for forest scenes. ET employed an enhanced YOLO model (YOLO-Tree) as a base detector and incorporated a teacher-student semi-supervised learning (SSL) framework based on pseudo-labeling, effectively leveraging abundant unlabeled data to bolster model robustness. The results revealed that SSL significantly improved outcomes in scenarios with sparse labeled data, specifically when the annotation proportion was below 50%. Additionally, employing overlapping cropping as a data augmentation strategy mitigated instability during semi-supervised training under conditions of limited sample size. Notably, introducing unlabeled data from external sites enhances the accuracy and cross-site generalization of models trained on diverse datasets, achieving impressive results with F1, mAP50, and mAP50-95 scores of 0.979, 0.992, and 0.871, respectively. In conclusion, this study highlights the potential of combining UAV-based RGB imagery with SSL to advance tree species identification in heterogeneous forests.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序