arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09548cs.CVcs.AI
收藏

面向双时相卫星影像的时序变化解释研究

Towards Temporal Change Explanations from Bi-Temporal Satellite Images

Nara Institute of Science and Technology(奈良科学技术大学)

Ryo Tsujimoto, Hiroki Ouchi, Hidetaka Kamigaito, Taro Watanabe

AI总结:

针对双时相卫星影像时序变化解释任务人工构建数据集成本高的问题,研究LVLMs的相关能力,提出三种适配双影像输入的提示方法,经人工评估验证逐步推理提示法有效,为人机协作开展该任务提供支撑。

摘要:

解释不同时间拍摄的卫星影像之间的时序变化对城市规划和环境监测具有重要意义。然而,为该任务手动构建数据集成本高昂,因此人机协作是颇具前景的方向。围绕这一方向,本文研究了大规模视觉语言模型(LVLMs)解释卫星影像间时序变化的能力。尽管已知LVLMs可生成优质图像描述,但它们仅以单张图像作为输入。为处理以一对卫星影像作为输入的场景,我们提出了三种提示方法。通过人工评估,我们发现基于逐步推理的提示方法具备有效性。

英文摘要:

Explaining temporal changes between satellite images taken at different times is important for urban planning and environmental monitoring. However, manual dataset construction for the task is costly, so human-AI collaboration is promissing. Toward the direction, in this paper, we investigate the ability of Large-scale Vision-Language Models (LVLMs) to explain temporal changes between satellite images. While LVLMs are known to generate good image captions, they receive only a single image as input. To deal with a par of satellite images as input, we propose three prompting methods. Through human evaluation, we found the effectiveness of our step-by-step reasoning based prompting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑