发表机构
University of Naples Parthenope; University of Sannio; CNRS; INRIA（那不勒斯 Parthenope 大学; 萨尼奥大学; 法国国家科学研究中心; 法国国家信息与自动化研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对圣诞树种植园检测难题，将其视为稀有目标语义分割问题，引入难负样本挖掘策略，基于DeepLabV3模型在法国莫尔旺地区航空影像上实现高精度检测，且具备良好时间迁移性。
AI 中文摘要
圣诞树种植园具有重要经济价值，但在遥感（RS）领域仍是一个尚未充分探索的应用方向。对其进行轮廓描绘颇具挑战性，原因包括种植密度高、轮伐周期短、与周边植被视觉混淆、仅某一参考年份有密集标注，以及景观尺度上存在严重的类别不平衡问题。尽管深度学习（DL）方法在植被制图中展现出强大潜力，但现有方法通常针对森林、通用种植系统或果园设计，未明确解决圣诞树种植园特有的结构特性及与难区分负样本的混淆问题。针对这些挑战，本研究有三项主要贡献：（i）将圣诞树种植园制图定义为一个独特的稀有目标语义分割问题；（ii）引入难负样本挖掘（Hard Negative Mining, HNM）策略，以提升对易混淆背景模式的区分能力；（iii）在多个互补层面评估所提框架，包括监督测试、时间迁移及大规模验证。在留出的2020年测试集上，表现最佳的模型为带ResNet-34编码器的DeepLabV3，其交并比（IoU）达0.733，F1分数为0.846。HNM显著改善了精确率-召回率表现，使精确率-召回率曲线下面积从0.204提升至0.913。时间推断进一步显示出可观的迁移能力，在2017/2018数据集上IoU/F1值达0.751/0.858，2023年则达0.691/0.817。大规模验证还凸显了该任务的固有难度：在总面积87,309.4公顷的通用评估范围内，圣诞树种植园仅占极小比例，2017/2018年对应1,498.4公顷（1.72%），2023年对应1,782.2公顷（2.04%）。
英文摘要
Christmas tree plantations are economically relevant, yet a largely unexplored application domain in Remote Sensing (RS). Their delineation is challenging because of high planting density, short rotation cycles, visual confusion with surrounding vegetation, the availability of dense labels for one reference year only, and severe class imbalance at the landscape scale. Although Deep Learning (DL) methods have shown strong potential for vegetation mapping, existing approaches are typically designed for forests, generic plantation systems, or orchards, and do not explicitly address the structural specificity and hard-negative confusion that characterize Christmas tree plantations. In response to these challenges, this work makes three main contributions: (i) it frames Christmas tree plantation mapping as a distinct rare-target semantic segmentation problem; (ii) it introduces a Hard Negative Mining (HNM) strategy to improve discrimination against confusing background patterns; and (iii) it evaluates the proposed framework across complementary levels, including supervised testing, temporal transfer, and large-scale validation. On the 2020 test set held out, the best model, DeepLabV3 with a ResNet-34 encoder, achieves an IoU of 0.733 and an F1-score of 0.846. HNM substantially improves precision-recall behavior, increasing the area under the precision-recall curve from 0.204 to 0.913. Temporal inference further shows meaningful transferability, reaching IoU/F1 values of 0.751/0.858 on 2017/2018 and 0.691/0.817 on 2023. Large-scale validation further highlights the intrinsic difficulty of the task, as Christmas tree plantations occupied only a very small fraction of the extent of the common evaluation, corresponding to 1,498.4 ha (1.72\%) in 2017/2018 and 1,782.2 ha (2.04\%) in 2023 out of 87,309.4 ha in total.
Comments18 pages, 9 figures. Submitted to IEEE JSTARS; currently under revision
