融合可见光、热成像与激光雷达，提升林下人体检测精度
Multimodal Object Detection Under Sparse Forest-Canopy Occlusion
- 结合可见-热图像融合与空中光学切片技术增强目标可见性
- 微调YOLOv5在FLIR数据集上达到0.83的平均精度
- 为无人机搜救系统提供林区探测新方案，适合安防与救援领域
由于稀疏、结构化且视角依赖的遮挡，遥感环境下检测林冠下的人员仍具挑战。本文提出一种多模态验证流程：(i) 实验评估激光雷达穿透植被的可行性；(ii) 采用多尺度变换与稀疏表示框架融合可见光-热成像以增强人体显著性；(iii) 利用机载光学切片（AOS）形成合成孔径图像以抑制林冠杂波。在Teledyne FLIR热成像数据集上微调YOLOv5，并在热图与融合图像上评估。结果表明，地面激光雷达配置对物体级检测穿透力有限，而可见-热融合可提升低对比度场景中的目标可见性，AOS则增强合成林地影像中地平面检测效果。微调后的YOLOv5在FLIR前三个类别上达到约0.83的均值平均精度。研究建立了一套适用于无人机部署的搜救与监视系统的初步基准，推动未来专用森林数据集与实时多模态融合的发展。
原文摘要 · Abstract (English)
Reliable detection of humans beneath forest canopy remains a difficult remote-sensing challenge due to sparse, structured, and viewpoint-dependent occlusion. This paper presents a multimodal proof-of-concept pipeline that integrates three complementary approaches: (i) experimental evaluation of LiDAR returns through vegetation to assess the feasibility of active sensing, (ii) visible--thermal image fusion using a multi-scale transform and sparse-representation framework to enhance human saliency, and (iii) synthetic-aperture image formation via Airborne Optical Sectioning (AOS) to suppress canopy clutter. A YOLOv5 detector is fine-tuned on the Teledyne FLIR thermal dataset and evaluated on thermal and fused imagery. Results show that the tested terrestrial LiDAR configuration provides limited penetration for object-level detection, while visible--thermal fusion improves target visibility in low-contrast scenes and AOS enhances ground-plane detection in synthetic forest imagery. The fine-tuned YOLOv5 achieves a mean average precision of $\sim$0.83 on the top three FLIR classes. These findings establish an initial baseline for UAV-deployable search-and-rescue and surveillance systems operating in forested environments, and motivate future work on dedicated forest datasets and real-time multimodal integration.
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。