arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.11275cs.CV
收藏

基于中心的三维目标检测与跟踪

Center-based 3D Object Detection and Tracking

UT Austin(德克萨斯大学奥斯汀分校);cs.utexas.edu(德克萨斯大学奥斯汀分校计算机系)

Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl

摘要:

三维对象通常表示为点云中的3D框。这种表示模仿了基于图像的2D边界框检测,但也带来了额外的挑战。3D世界中的对象不遵循任何特定方向,并且基于框的检测器难以枚举所有方向或将轴对齐的限界框适配到旋转的对象。在本文中,我们建议将3D对象表示,检测和跟踪为点。我们的框架CenterPoint首先使用关键点检测器检测对象的中心,并回归到其他属性,包括3D大小,3D方向和速度。在第二阶段,它使用对象上的附加点特征来细化这些估计。在CenterPoint中,3D对象跟踪简化为贪婪最近点匹配。所得到的检测和跟踪算法是简单,高效,有效的。CenterPoint在nuScenes基准测试中实现了最先进的3D检测和跟踪性能,单个模型的NDS为65.5,AMOTA为63.8。在Waymo Open Dataset上,CenterPoint的表现远远优于之前所有的单一模型方法,在所有仅使用激光雷达的提交中排名第一。代码和预训练模型可在https://github.com/tianweiy/CenterPoint上获得。

英文摘要:

Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world do not follow any particular orientation, and box-based detectors have difficulties enumerating all orientations or fitting an axis-aligned bounding box to rotated objects. In this paper, we instead propose to represent, detect, and track 3D objects as points. Our framework, CenterPoint, first detects centers of objects using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation, and velocity. In a second stage, it refines these estimates using additional point features on the object. In CenterPoint, 3D object tracking simplifies to greedy closest-point matching. The resulting detection and tracking algorithm is simple, efficient, and effective. CenterPoint achieved state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking, with 65.5 NDS and 63.8 AMOTA for a single model. On the Waymo Open Dataset, CenterPoint outperforms all previous single model method by a large margin and ranks first among all Lidar-only submissions. The code and pretrained models are available at https://github.com/tianweiy/CenterPoint.

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。

↑