Small object detection for 3D point cloud is a challenging problem because of two limitations: (1) Perceiving small objects is much more diffcult than normal objects due to the lack of valid points. (2) Small objects are easily blocked which breaks the shape of their meshes in 3D point cloud. In this paper, we propose a pillar set abstraction (PSA) and foreground point compensation (FPC) and design a point-based detection network, PSA-Det3D, to improve the detection performance for small object. The PSA embeds a pillar query operation on the basis of set abstraction (SA) to expand its receptive field of the network, which can aggregate point-wise features effectively. To locate more occluded objects, we persent a proposal generation layer consisting of a foreground point segmentation and a FPC module. Both the foreground points and the estimated centers are finally fused together to generate the detection result. The experiments on the KITTI 3D detection benchmark show that our proposed PSA-Det3D outperforms other algorithms with high accuracy for small object detection.

翻译：3D点云的小天体探测是一个具有挑战性的问题,因为有两个限制:(1) 由于缺乏有效点,感知小天体比正常天体要困难得多。(2) 小型天体很容易被阻塞,以3D点云打破其间歇形状。在本文中,我们提议设置一个立柱式抽象(PSA)和前景点补偿(FPC),并设计一个基于点的探测网络(PSA-Det3D),以改进小天体的探测性能。PSA在设定的抽象(SA)的基础上嵌入了一个界碑查询操作,以扩展其网络的可接受场,从而有效地综合点向特征。要找到更多隐蔽的天体,我们收到一个建议生成层,由地表点分割和一个FPC模块组成。前角点和估计的中心最终结合在一起,以产生探测结果。KITTI 3D检测基准的实验显示,我们提议的PSA-DD将其他算出精准小天体探测的算法。