The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain.

翻译：大规模语言模型（LLMs）的革命性能力为多模态大规模语言模型（MLLMs）铺平了道路，并推动了其在多个专业领域的多样化应用。然而，在遥感（RS）领域，近期MLLM研究未能充分考虑遥感影像中多样化的地理景观与不同地物。为弥补这一不足，我们利用广泛的志愿者地理信息（VGI）与全球可获取的遥感影像，构建了大规模遥感影像-文本数据集LHRS-Align，以及具备遥感领域特色的信息型指令数据集LHRS-Instruct。在此基础上，我们提出LHRS-Bot——一种通过新颖的多层级视觉-语言对齐策略与课程学习方法，专为遥感影像理解设计的MLLM。综合实验表明，LHRS-Bot能深刻理解遥感影像，并在遥感领域展现出执行细腻推理的能力。