用合成数据训练无人机热成像检测，小量真实数据显著提升效果
Training with synthetic data for drone detection in thermal imagery
- 先用合成场景生成数据预训练，再用少量真实热成像数据微调
- 少量真实数据即可大幅缩小域差距，性能提升远超单纯增大模型规模
- 特征空间语义对齐是预测模型性能最强指标，适合热成像检测初学者参考
中长波红外（MWIR/LWIR）图像中的地面到空中（G2A）无人机检测面临纹理信息少、传感器噪声大、热对比度弱及标注数据稀缺等挑战。本文研究了一种以合成数据为主的训练策略，结合合成场景生成与真实数据微调。结果表明，合成数据能有效建立初始目标表征，而真实域内热成像数据对可靠部署仍至关重要。少量真实红外数据可显著减少域间差异。实验显示，数据集对齐对性能的影响强于模型规模。进一步分析表明，特征空间的语义对齐是模型性能的最佳预测因子，辐射特性如熵和动态范围也影响检测鲁棒性。本工作为融合合成与真实红外数据实现高效G2A无人机检测提供了基础。
原文摘要 · Abstract (English)
Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging due to reduced texture information, sensor noise, weak thermal contrast, and the scarcity of annotated data. This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data. We show that synthetic data provides an effective basis for learning initial object representations, while real in-domain thermal imagery is still essential for reliable deployment. Even small amounts of real IR data substantially reduce domain gaps. Our experiments indicate that dataset alignment has a stronger impact on performance than model scale. Finally, our analysis of the dataset suggests that semantic alignment in feature space is the strongest predictor of model performance, while radiometric properties such as entropy and dynamic range also contribute to detection robustness. This work provides a foundation for combining synthetic and real IR data for effective G2A drone detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。