TrafficLoc：在3D场景中定位交通监控摄像头
TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes
AI总结：
提出TrafficLoc，一种基于粗到细匹配的图像到点云配准方法，结合几何引导注意力损失和对比学习，在模拟和真实数据集上显著提升交通摄像头定位精度。
摘要：
我们解决了在3D参考地图内定位交通摄像头的问题，并提出了一种新颖的图像到点云配准（I2P）方法TrafficLoc，采用从粗到细的匹配方式。为克服缺乏大规模真实世界交叉路口数据集的难题，我们首先引入了Carla Intersection，这是一个在Carla中构建的包含75个城市和乡村交叉路口的新模拟数据集。我们发现，当前的I2P方法在较大视角差异下进行跨模态匹配时存在困难，尤其是在交通交叉路口。因此，TrafficLoc采用了一种新颖的几何引导注意力损失（GAL），在2D-3D特征融合过程中仅关注不同视角下的对应几何区域。为解决配对图像块-点组中的特征不一致问题，我们进一步提出了模态间-模态内对比学习（ICL），以增强各模态内2D块/3D组特征的区分度，并引入了带有软argmax的密集训练对齐（DTA）以改进位置回归。大量实验表明，我们的TrafficLoc在Carla Intersection上相比最先进的I2P方法性能大幅提升（最高达86%），并能很好地泛化到真实世界数据。TrafficLoc还在KITTI和NuScenes数据集上取得了新的最先进性能，展示了其在车载摄像头和交通摄像头上的优越性。我们的项目页面公开可访问：https://tum-luk.github.io/projects/trafficloc/。
英文摘要：
We tackle the problem of localizing traffic cameras within a 3D reference map and propose a novel image-to-point cloud registration (I2P) method, TrafficLoc, in a coarse-tofine matching fashion. To overcome the lack of large-scale real-world intersection datasets, we first introduce Carla Intersection, a new simulated dataset with 75 urban and rural intersections in Carla. We find that current I2P methods struggle with cross-modal matching under large viewpoint differences, especially at traffic intersections. TrafficLoc thus employs a novel Geometry-guided Attention Loss (GAL) to focus only on the corresponding geometric regions under different viewpoints during 2D-3D feature fusion. To address feature inconsistency in paired image patch-point groups, we further propose Inter-intra Contrastive Learning (ICL) to enhance separating 2D patch/3D group features within each intra-modality and introduce Dense Training Alignment (DTA) with soft-argmax for improving position regression. Extensive experiments show our TrafficLoc greatly improves the performance over the SOTA I2P methods (up to 86%) on Carla Intersection and generalizes well to real-world data. TrafficLoc also achieves new SOTA performance on KITTI and NuScenes datasets, demonstrating the superiority across both in-vehicle and traffic cameras. Our project page is publicly available at https://tum-luk.github.io/projects/trafficloc/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
