变更检测
计算机科学
分割
钥匙(锁)
人工智能
土地覆盖
过程(计算)
遥感
模式识别(心理学)
计算机视觉
数据挖掘
土地利用
地理
操作系统
工程类
土木工程
计算机安全
作者
Hongruixuan Chen,Jian Song,Naoto Yokoya
出处
期刊:Cornell University - arXiv
日期:2024-01-01
标识
DOI:10.48550/arxiv.2401.09019
摘要
Unsupervised multimodal change detection is pivotal for time-sensitive tasks and comprehensive multi-temporal Earth monitoring. In this study, we explore unsupervised multimodal change detection between two key remote sensing data sources: optical high-resolution imagery and OpenStreetMap (OSM) data. Specifically, we propose to utilize the vision foundation model Segmentation Anything Model (SAM), for addressing our task. Leveraging SAM's exceptional zero-shot transfer capability, high-quality segmentation maps of optical images can be obtained. Thus, we can directly compare these two heterogeneous data forms in the so-called segmentation domain. We then introduce two strategies for guiding SAM's segmentation process: the 'no-prompt' and 'box/mask prompt' methods. The two strategies are designed to detect land-cover changes in general scenarios and to identify new land-cover objects within existing backgrounds, respectively. Experimental results on three datasets indicate that the proposed approach can achieve more competitive results compared to representative unsupervised multimodal change detection methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI