RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911020212027392 |
|---|---|
| author | Zhang, Bowen Boulerice, Jesse T. Kuniyil, Nikhil Mendiratta, Charvi Kumar, Satish Shamon, Hila Manjunath, B. S. |
| author_facet | Zhang, Bowen Boulerice, Jesse T. Kuniyil, Nikhil Mendiratta, Charvi Kumar, Satish Shamon, Hila Manjunath, B. S. |
| contents | Automated detection of small and rare wildlife in aerial imagery is crucial for effective conservation, yet remains a significant technical challenge. Prairie dogs exemplify this issue: their ecological importance as keystone species contrasts sharply with their elusive presence--marked by small size, sparse distribution, and subtle visual features--which undermines existing detection approaches. To address these challenges, we propose RareSpot, a robust detection framework integrating multi-scale consistency learning and context-aware augmentation. Our multi-scale consistency approach leverages structured alignment across feature pyramids, enhancing fine-grained object representation and mitigating scale-related feature loss. Complementarily, context-aware augmentation strategically synthesizes challenging training instances by embedding difficult-to-detect samples into realistic environmental contexts, significantly boosting model precision and recall. Evaluated on an expert-annotated prairie dog drone imagery benchmark, our method achieves state-of-the-art performance, improving detection accuracy by over 35% compared to baseline methods. Importantly, it generalizes effectively across additional wildlife datasets, demonstrating broad applicability. The RareSpot benchmark and approach not only support critical ecological monitoring but also establish a new foundation for detecting small, rare species in complex aerial scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19087 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation Zhang, Bowen Boulerice, Jesse T. Kuniyil, Nikhil Mendiratta, Charvi Kumar, Satish Shamon, Hila Manjunath, B. S. Computer Vision and Pattern Recognition Artificial Intelligence Automated detection of small and rare wildlife in aerial imagery is crucial for effective conservation, yet remains a significant technical challenge. Prairie dogs exemplify this issue: their ecological importance as keystone species contrasts sharply with their elusive presence--marked by small size, sparse distribution, and subtle visual features--which undermines existing detection approaches. To address these challenges, we propose RareSpot, a robust detection framework integrating multi-scale consistency learning and context-aware augmentation. Our multi-scale consistency approach leverages structured alignment across feature pyramids, enhancing fine-grained object representation and mitigating scale-related feature loss. Complementarily, context-aware augmentation strategically synthesizes challenging training instances by embedding difficult-to-detect samples into realistic environmental contexts, significantly boosting model precision and recall. Evaluated on an expert-annotated prairie dog drone imagery benchmark, our method achieves state-of-the-art performance, improving detection accuracy by over 35% compared to baseline methods. Importantly, it generalizes effectively across additional wildlife datasets, demonstrating broad applicability. The RareSpot benchmark and approach not only support critical ecological monitoring but also establish a new foundation for detecting small, rare species in complex aerial scenes. |
| title | RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.19087 |