Change Detection Between Optical Remote Sensing Imagery and Map Data via Segment Anything Model (SAM)
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913198777565184 |
|---|---|
| author | Chen, Hongruixuan Song, Jian Yokoya, Naoto |
| author_facet | Chen, Hongruixuan Song, Jian Yokoya, Naoto |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09019 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Change Detection Between Optical Remote Sensing Imagery and Map Data via Segment Anything Model (SAM) Chen, Hongruixuan Song, Jian Yokoya, Naoto Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Multimedia 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. |
| title | Change Detection Between Optical Remote Sensing Imagery and Map Data via Segment Anything Model (SAM) |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2401.09019 |