{"slug": "impact-of-dataset-composition-on-embedded-real-time-uav-wildfire-detection-using", "title": "Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models", "summary": "A new arXiv study (2608.07554v1) finds that real non-augmented datasets outperform hybrid or augmented sets for embedded real-time UAV wildfire detection using compact YOLO models, achieving the strongest balance between recall and mean average precision. The results indicate that dataset realism and domain alignment are more valuable than synthetic expansion for resource-constrained deployment.", "body_md": "arXiv:2608.07554v1 Announce Type: new\nAbstract: The development of vision-based wildfire detection systems for unmanned aerial vehicles is constrained by the limited availability of diverse real-world training images. This paper investigates the impact of dataset composition on embedded real-time UAV wildfire detection using compact YOLO models as a controlled validation family. Four training configurations were evaluated: real non-augmented, real augmented, hybrid non-augmented, and hybrid augmented, where the hybrid sets combine real wildfire images with AI-generated samples. The objective is to determine whether synthetic data mixing and image augmentation improve practical detection performance under resource-constrained deployment conditions. Experimental results show that the best overall operating point was obtained with the real non-augmented dataset, which achieved the strongest balance between recall and mean average precision for UAV-based wildfire detection. The results also show that neither hybridization with synthetic data nor augmentation produced a better final deployment choice. These findings suggest that, for embedded UAV wildfire detection, dataset realism and domain alignment are more valuable than increasing training set size through synthetic expansion.", "url": "https://wpnews.pro/news/impact-of-dataset-composition-on-embedded-real-time-uav-wildfire-detection-using", "canonical_source": "https://arxiv.org/abs/2608.07554", "published_at": "2026-08-11 04:00:00+00:00", "updated_at": "2026-08-11 04:24:09.136158+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning"], "entities": ["arXiv", "YOLO"], "alternates": {"html": "https://wpnews.pro/news/impact-of-dataset-composition-on-embedded-real-time-uav-wildfire-detection-using", "markdown": "https://wpnews.pro/news/impact-of-dataset-composition-on-embedded-real-time-uav-wildfire-detection-using.md", "text": "https://wpnews.pro/news/impact-of-dataset-composition-on-embedded-real-time-uav-wildfire-detection-using.txt", "jsonld": "https://wpnews.pro/news/impact-of-dataset-composition-on-embedded-real-time-uav-wildfire-detection-using.jsonld"}}