TriSAR-3D 三模态数据集与 PaintFusion 搜救 3D 人员检测方法
原标题：TriSAR-3D and PaintFusion: A Novel Trimodal LiDAR-RGB-Thermal Dataset and Method for 3D Person Detection in Search and Rescue
AI 摘要
该论文提出 TriSAR-3D，一个用 128 线 LiDAR、RGB 相机和热成像相机采集的多模态人员检测数据集，覆盖室内外、昼夜及站立、行走、坐、躺等多种姿态，面向搜救机器人场景。作者同时提出三模态 3D 检测方法 PaintFusion，基于 PointPainting 融合并用简单 MLP 实现，在该数据集上达到 65.4 AP@50，优于仅 LiDAR 的 CenterPoint（53.4）、RGB+LiDAR 的 BEVFusion（60.5）和改造后的 Tri-BEVFusion（60.7），且延迟约为其他融合方法的一半。研究还发现，若训练集中移除躺姿样本，所有检测器对躺姿的 AP@50 都降至接近零，说明数据多样性对 3D 检测性能影响很大。
正文节选
TriSAR-3D and PaintFusion: A Novel Trimodal LiDAR–RGB–Thermal Dataset and Method for 3D Person Detection in Search and Rescue Abstract Reliable 3D person detection is important for rescue robotics to give first responders situational awareness. Yet most multimodal 3D detection research targets automotive scenarios in which pedestrians mostly appear in a narrow range of upright, near-road poses. It is therefore unclear how much of the reported performance transfers to rescue settings, as a pers