森林工程2025，Vol.41Issue(5)：922-935,14.DOI:10.7525/j.issn.1006-8023.2025.05.006
基于改进YOLOv10和无人机影像的树种识别
Tree Species Identification Based on Improved YOLOv10 and UAV RGB Imagery
摘要
Abstract
Efficient and accurate tree species identification is critical for the realization of smart forestry.Traditional field survey methods are low efficiency and high cost,while machine learning-based tree species identification ap-proaches often rely on extensive feature extraction and prior knowledge.To address these issues,a tree species identifi-cation algorithm based on improved YOLOv10 for UAV imagery is proposed in this paper.The improved architecture in-tegrates lightweight network design and attention mechanisms to enable efficient edge device deployment,providing tech-nical support for digital forest resource management.A UAV imagery dataset was developed for five common tree species(Larix gmelinii,Phellodendron amurense,Juglans mandshurica,Ulmus pumila,and Fraxinus mandshurica)in North-east China.The backbone network was reconstructed using lightweight convolution(Ghost)for computational complexity reduction.The convolutional block attention module(CBAM)was introduced in the fusion layer to strengthen fine-grained feature extraction through channel and spatial dual dimensional feature calibration.Multi-scale feature fusion was optimized through bidirectional cross-scale connections(BiFPN),while bounding box regression efficiency was im-proved using a structured intersection over union(SIoU)loss function.Final deployment validation was conducted on the Jetson Nano embedded platform.The improved YOLOv10 model achieved 91.5％precision and 77.5％mAP@0.5 on the validation set,showing improvements of 4.5％and 3.8％compared to the baseline model,respectively.In practi-cal deployment,the model achieved an inference speed of 43.5 FPS,35.5％faster than the baseline model,with mAP@0.5 of 75.7％.Results showed that,the improved YOLOv10 algorithm successfully balances identification accuracy and real-time performance in complex forest environments through lightweight architecture and multi-scale feature optimiza-tion.The solution demonstrates particular effectiveness in scenarios with dense canopy overlap and variable illumina-tion,offering an embeddable solution for UAV forestry surveys.关键词
树种识别/深度学习/无人机/YOLO/目标检测Key words
Tree species identification/deep learning/UAV/YOLO/object detection分类
农业科技引用本文复制引用
韩誉,刘浩然,林文树..基于改进YOLOv10和无人机影像的树种识别[J].森林工程,2025,41(5):922-935,14.基金项目
黑龙江省自然科学基金联合引导项目(LH2020C049). （LH2020C049）
