对比22种模型在三分辨率下分割树枝，为林业自动化提供性能基准。
Performance Evaluation of Deep Learning for Tree Branch Segmentation in Autonomous Forestry Systems
- 用不同深度模型在三种图像分辨率下测试树枝分割效果。
- 512x512分辨率下，MiT-B4+U-Net在各项指标中领先。
- 首次引入细结构与连通性指标，适合嵌入式林业系统选型。
基于无人机的自主林业作业需在不同像素分辨率和运行条件下快速精准分割树枝，以保障导航安全与自动修剪。本文在三个分辨率（256x256、512x512、1024x1024）下评估22种深度学习配置，使用标准指标（IoU、Dice）及专用指标（薄结构IoU TS-IoU、连通性保持率 CPR）。结果显示：在256x256下，带MiT-B4主干的U-Net表现优异；512x512下，MiT-B4在IoU、Dice、TS-IoU与边界F1上均领先；1024x1024下，U-Net+MiT-B3在IoU/Dice与精度上最佳，而U-Net++在边界质量上最优。PSPNet效率最高（2.36/9.43/37.74 GFLOPs），但对应分辨率下IoU下降25.7/19.6/11.8个百分点。研究建立了多分辨率下的精度-效率权衡基准，代码已开源。
原文摘要 · Abstract (English)
UAV-based autonomous forestry operations require rapid and precise tree branch segmentation for safe navigation and automated pruning across varying pixel resolutions and operational conditions. We evaluate different deep learning methods at three resolutions (256x256, 512x512, 1024x1024) using the Urban Street Tree Dataset, employing standard metrics (IoU, Dice) and specialized measures including Thin Structure IoU (TS-IoU) and Connectivity Preservation Rate (CPR). Among 22 configurations tested, U-Net with MiT-B4 backbone achieves strong performance at 256x256. At 512x512, MiT-B4 leads in IoU, Dice, TS-IoU, and Boundary-F1. At 1024x1024, U-Net+MiT-B3 shows the best validation performance for IoU/Dice and precision, while U-Net++ excels in boundary quality. PSPNet provides the most efficient option (2.36/9.43/37.74 GFLOPs) with 25.7/19.6/11.8 percentage point IoU reductions compared to top performers at respective resolutions. These results establish multi-resolution benchmarks for accuracy-efficiency trade-offs in embedded forestry systems. Implementation is available at https://github.com/BennyLinntu/PerformanceTreeBranchSegmentation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。