用SAM模型实现遥感图像无监督变化检测，精准捕捉地物分裂合并等复杂变化。
MergeSAM: Unsupervised change detection of remote sensing images based on the Segment Anything Model
- 基于SAM构建多时相掩码，利用其分割能力捕捉复杂变化
- 提出MaskMatching与MaskSplitting策略应对真实场景中的地物分裂与合并
- 无需标注数据，适合大规模遥感影像变化监测
近期在海量数据上训练的大规模基础模型展现出卓越的特征提取与通用表征能力。深度学习驱动的大模型进展为加速无监督变化检测方法提供了巨大潜力，从而提升变化检测技术的实际应用价值。基于此，本文提出MergeSAM，一种基于Segment Anything Model（SAM）的高分辨率遥感影像无监督变化检测新方法。针对真实场景中物体分裂、合并及其他复杂变化问题，设计了两种新颖策略：MaskMatching与MaskSplitting。该方法充分利用SAM的物体分割能力，构建多时相掩码以捕捉复杂变化，并将地表覆盖的空间结构嵌入变化检测过程，显著提升检测精度。
原文摘要 · Abstract (English)
Recently, large foundation models trained on vast datasets have demonstrated exceptional capabilities in feature extraction and general feature representation. The ongoing advancements in deep learning-driven large models have shown great promise in accelerating unsupervised change detection methods, thereby enhancing the practical applicability of change detection technologies. Building on this progress, this paper introduces MergeSAM, an innovative unsupervised change detection method for high-resolution remote sensing imagery, based on the Segment Anything Model (SAM). Two novel strategies, MaskMatching and MaskSplitting, are designed to address real-world complexities such as object splitting, merging, and other intricate changes. The proposed method fully leverages SAM's object segmentation capabilities to construct multitemporal masks that capture complex changes, embedding the spatial structure of land cover into the change detection process.
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。