ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918502009405440 |
|---|---|
| author | Cui, Kangning Bohara, Surendra Prasai, Suraj Shao, Zishan Tang, Wei Pillaca, Martin Flores, Edwin Yang, Zhen Larsen, Gregory Dethier, Evan Lutz, David Morel, Jean-Michel Silman, Miles Pauca, Victor Yang, Fan |
| author_facet | Cui, Kangning Bohara, Surendra Prasai, Suraj Shao, Zishan Tang, Wei Pillaca, Martin Flores, Edwin Yang, Zhen Larsen, Gregory Dethier, Evan Lutz, David Morel, Jean-Michel Silman, Miles Pauca, Victor Yang, Fan |
| contents | Illegal gold mining in the Amazon rainforest causes deforestation, water contamination, and long-term ecosystem disruption, yet remains difficult to monitor at fine spatial scales. Satellite imagery supports large-scale observation, but often misses small mining-related structures and subtle land-cover transitions, especially under frequent cloud cover. We introduce ELDOR, a large-scale UAV benchmark for monitoring environmental and landscape disturbance from illegal gold mining in the rainforest. ELDOR contains manually annotated orthomosaic imagery covering over 2,500 hectares, with pixel-level semantic labels for both mining-related activities and surrounding ecological structures. With this unified annotation source, we establish four benchmark tasks: semantic segmentation, segmentation-derived recognition, direct multi-label classification, and class-presence recognition with vision-language models. Across these tasks, we compare generic and remote-sensing-specific segmentation models, vision foundation model-related segmentation methods, direct multi-label classification methods, and vision-language models under a controlled closed-set protocol. Results show that current methods still struggle with rare small-scale mining structures and fine-grained recovery classes, suggesting the need for context-aware and multimodal modeling. To support domain analysis and practical use, we further build an interactive explorer for domain experts that provides a unified interface for data exploration and model inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15397 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest Cui, Kangning Bohara, Surendra Prasai, Suraj Shao, Zishan Tang, Wei Pillaca, Martin Flores, Edwin Yang, Zhen Larsen, Gregory Dethier, Evan Lutz, David Morel, Jean-Michel Silman, Miles Pauca, Victor Yang, Fan Computer Vision and Pattern Recognition Illegal gold mining in the Amazon rainforest causes deforestation, water contamination, and long-term ecosystem disruption, yet remains difficult to monitor at fine spatial scales. Satellite imagery supports large-scale observation, but often misses small mining-related structures and subtle land-cover transitions, especially under frequent cloud cover. We introduce ELDOR, a large-scale UAV benchmark for monitoring environmental and landscape disturbance from illegal gold mining in the rainforest. ELDOR contains manually annotated orthomosaic imagery covering over 2,500 hectares, with pixel-level semantic labels for both mining-related activities and surrounding ecological structures. With this unified annotation source, we establish four benchmark tasks: semantic segmentation, segmentation-derived recognition, direct multi-label classification, and class-presence recognition with vision-language models. Across these tasks, we compare generic and remote-sensing-specific segmentation models, vision foundation model-related segmentation methods, direct multi-label classification methods, and vision-language models under a controlled closed-set protocol. Results show that current methods still struggle with rare small-scale mining structures and fine-grained recovery classes, suggesting the need for context-aware and multimodal modeling. To support domain analysis and practical use, we further build an interactive explorer for domain experts that provides a unified interface for data exploration and model inference. |
| title | ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.15397 |