データセット構成が組み込みリアルタイムUAV山火事検出に与える影響：コンパクトYOLOモデルを用いた検証
Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models
UAVによる山火事検出において、実画像とAI生成画像の混合やデータ拡張が性能に与える影響を、コンパクトなYOLOモデルで評価した。実データのみの非拡張データセットが最良の性能を示し、合成データや拡張の効果は限定的だった。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Eduardo de los Santos, Andre S. Kelbouscas, Ricardo B. Grando, Bruna V. Guterres
分類: cs.CV, cs.RO
原文アブストラクト
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.
