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; Conservation Science Research Group（新南威尔士州气候变化、能源、环境和水利部; 莫纳什大学; 新英格兰大学; 纽卡斯尔大学; 保护科学研究组）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出含影像合成、预测融合、标签迁移的框架，对澳新南威尔士州木本植被制图，多源学习使误差降28.1%-76.2%，单方法降38.2%、53.6%，标准差降13倍。
AI 中文摘要
树覆盖图是基础的遥感产品，用于获取景观的生态信息，对变化检测、植被制图和火灾监测项目至关重要。然而，全面的树覆盖制图需要可靠且高质量的影像，且无云或天气缺陷，以确保模型输出准确。深度学习方法可在最少人工干预下生成高质量地图，但要成功需大量人工标注数据。本研究提出一个框架，旨在通过数据融合技术提升深度学习模型的数据效率与鲁棒性，用于对澳大利亚新南威尔士州境内高度超过2米的木本植被进行分割。为提升模型对不同影像质量的鲁棒性，本研究提出一种影像合成方法，可对影像进行归一化处理并去除缺陷，同时提出一种预测融合方法，以最小化对单张影像质量的依赖。这两种方法与单源影像相比，分别使误差降低了38.2%和53.6%。为解决深度学习方法需大量数据的局限性，本研究将标签迁移应用于多源影像，作为数据增强的一种形式以提升数据效率。从多源影像中学习被证明是性能提升的最大来源，在不同验证实验中，该方法使误差降低了28.1%至76.2%，同时将不同影像日期下的性能标准差降低了13倍。
英文摘要
Tree cover maps are a fundamental remote sensing product, used to derive ecological insights about the landscape and are essential to change detection, vegetation mapping and fire monitoring programs. However, comprehensive tree cover mapping requires reliable and high-quality imagery, free of cloud and weather defects to ensure accurate model outputs. Deep learning approaches can generate high quality maps with minimal human intervention but require large amounts of human annotated data to be successful. In this work we propose a framework consisting of methods that aim to improve the data efficiency and robustness of deep learning models using data fusion techniques to segment woody vegetation defined as vegetation over the height of 2m across the state of New South Wales, Australia. To improve robustness against varying image quality, we propose an image composition method that normalizes the imagery and removes defects, whilst also minimizing the reliance on individual image quality by proposing a prediction fusion method. The two methods resulted in an error reduction of 38.2% and 53.6% respectively compared to single-source imagery. To address deep learning approaches' limitation of requiring large amounts of data, we apply label transfer to multiple sources of imagery as a form of data augmentation to improve data efficiency. Learning from multiple image sources was shown to be the biggest improvement in performance, resulting in an error reduction between 28.1% to 76.2% across the different validation experiments, whilst reducing the standard deviation of performance across image dates by a factor of 13.
CommentsPublished in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Journal refIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 19, pp. 9856-9867, 2026,
DOI：10.1109/JSTARS.2026.3672149
