论文标题
基于中心的3D对象检测和跟踪
Center-based 3D Object Detection and Tracking
论文作者
论文摘要
三维对象通常表示为点云中的3D框。该表示形式模仿了良好的基于图像的2D边界框检测，但还带来了其他挑战。 3D世界中的对象不遵循任何特定的方向，基于框的探测器在所有方向上都有困难，或者将轴对齐的边界框安装到旋转的对象上。在本文中，我们建议表示，检测和跟踪3D对象作为点。我们的框架，中心点首先使用键盘检测器检测对象中心，并回归到其他属性，包括3D大小，3D方向和速度。在第二阶段，它使用对象上的其他点功能来完善这些估计。在Centerpoint中，3D对象跟踪简化为贪婪的最接近点匹配。所得的检测和跟踪算法是简单，高效且有效的。 Centerpoint在Nuscenes基准测试中实现了3D检测和跟踪的最佳性能，单个模型的65.5 NDS和63.8 AMOTA。在Waymo打开数据集中，CenterPoint的表现要优于所有先前的单个模型方法，并在所有千圈提交中排名第一。代码和预估计的模型可在https://github.com/tianweiy/centerpoint上找到。
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.
