发表机构
New South Wales Department of Climate Change, Energy, the Environment and Water; Monash University; University of New England; University of Newcastle（新南威尔士州气候变化、能源、环境与水利部; 莫纳什大学; 新英格兰大学; 纽卡斯尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出带损失缩放系数α的双时相Sentinel-2影像木本植被变化检测模型，经影像增强与生成技术实现零样本迁移，木部分割误差降18.2%，木本植被再生F1达0.845
AI 中文摘要
检测木本植被砍伐对生物多样性管理至关重要。深度学习模型可从双时相遥感影像中检测木本植被变化，但生成的产品可能因损失定义不对齐而不符合最终用户规范。此外，深度学习模型依赖大量数据集，而对于再生检测这类空间上罕见且模糊的事件，难以获取所需数据集。本研究中，我们使用澳大利亚新南威尔士州7年的年度双时相Sentinel-2影像训练木本植被变化检测模型。为使模型目标与最终用户指标对齐，我们引入损失缩放系数α，将目标转换为优化特定Fβ分数。研究发现，引入α可使精度提升1.85倍或召回率提升1.12倍。我们提出输入影像增强与生成技术，使木本植被变化检测模型能零样本迁移至再生与木部分割任务。对于木部分割，采用低α值的激活最大化生成影像以保证稳定性，以及基于手工特征、利用砍伐斑块和人工树镶嵌进行上下文接地的影像生成技术，经测试优于该研究区域此前的木部分割研究，整体误差降低最多18.2%。对于零样本木本植被再生，创建伪后验与先验影像使模型F1分数达到0.845，为未来再生检测工作奠定了基础。
英文摘要
Detecting woody clearing is vital for managing biodiversity. Deep learning models can detect change in woody vegetation from bitemporal remote sensing imagery, however generated products may not meet end-user specifications due to unaligned loss definitions. Further limitations of deep learning models are the reliance on large datasets which can be difficult to attain for spatially rare and ambiguous events such as regrowth detection. In this work we train a model to detect woody change using bitemporal Sentinel-2 imagery consisting of 7 years' worth of annual imagery across the state of New South Wales, Australia. To align the objective of the model with end-user metrics, we introduce the loss scaling coefficient $α$ which transforms the objective to optimize for specific $F_β$ scores. Introducing $α$ was found to increase precision by 1.85x or recall by 1.12x. We propose input imagery augmentation and generation techniques that allow the woody change detection model to zero-shot transfer to regrowth and woody segmentation tasks. For woody segmentation, image generation techniques using activation maximization with low $α$ values for stability and image generation techniques derived from handcrafted features utilizing a mosaic of clearing patches and artificial trees for contextual grounding were found to outperform prior woody segmentation works of the study area, reducing the overall error by up to 18.2%. For zero-shot woody regrowth, creating pseudo-post and prior images resulted in the model achieving an F1 score of 0.845, creating a foundation for future regrowth detection work.
CommentsPublished in IEEE Transactions on Geoscience and Remote Sensing
Journal refIEEE Transactions on Geoscience and Remote Sensing, vol. 64, pp. 1-18, 2026, Art no. 4406318
