Three-dimensional object detection from light detection and ranging (LiDAR) point clouds has gained great attention in recent years due to its wide applications in smart cities and autonomous driving. Cascade framework shows its advancement in 2-D object detection but is less investigated in 3-D space. Conventional cascade structures use multiple separate subnetworks to sequentially refine region proposals. Such methods, however, have limited ability to measure proposal quality in all the stages, and it is hard to achieve a desirable performance improvement in 3-D space. This article proposes a new cascade framework, termed Cascade Attention (CasA), for 3-D object detection from LiDAR point clouds. CasA consists of a region proposal network (RPN) and a cascade refinement network (CRN). In CRN, we designed a new cascade attention module (CAM) that uses multiple subnetworks and attention modules to aggregate the object features from different stages and progressively refine region proposals. CasA can be integrated into various two-stage 3-D detectors and improve their performance. Extensive experiments on the KITTI and Waymo datasets with various baseline detectors demonstrate the universality and superiority of our CasA. In particular, based on one variant of Voxel-region-based convolutional neural network (RCNN), we achieve the state-of-the-art results on the KITTI dataset. On the KITTI online 3-D object detection leaderboard, we achieve a high detection performance of 83.06%, 47.09%, and 73.47% average precision (AP) in the moderate car, pedestrian, and cyclist classes, respectively. Code is available at https://github.com/hailanyi/CasA

中文翻译：

---

CasA：用于 LiDAR 点云 3D 物体检测的级联注意力网络


近年来，光探测和测距（LiDAR）点云的三维物体检测由于其在智慧城市和自动驾驶中的广泛应用而受到广泛关注。 Cascade 框架显示了其在 2D 对象检测方面的进步，但在 3D 空间中的研究较少。传统的级联结构使用多个单独的子网络来顺序细化区域建议。然而，此类方法在所有阶段测量提案质量的能力有限，并且很难在 3D 空间中实现理想的性能改进。本文提出了一种新的级联框架，称为级联注意力 (CasA)，用于 LiDAR 点云的 3D 对象检测。 CasA由区域提议网络（RPN）和级联细化网络（CRN）组成。在CRN中，我们设计了一个新的级联注意力模块（CAM），它使用多个子网络和注意力模块来聚合不同阶段的对象特征并逐步细化区域建议。 CasA 可以集成到各种两级 3D 探测器中并提高其性能。使用各种基线检测器在 KITTI 和 Waymo 数据集上进行的广泛实验证明了我们的 CasA 的普遍性和优越性。特别是，基于基于体素区域的卷积神经网络（RCNN）的一种变体，我们在 KITTI 数据集上取得了最先进的结果。在 KITTI 在线 3D 目标检测排行榜上，我们在中等汽车、行人和骑自行车者类别中分别实现了 83.06%、47.09% 和 73.47% 平均精度 (AP) 的高检测性能。代码可在 https://github.com/hailanyi/CasA 获取