论文标题
PSA-DET3D：3D对象检测的支柱集抽象
PSA-Det3D: Pillar Set Abstraction for 3D object Detection
论文作者
论文摘要
3D点云的小物体检测是一个具有挑战性的问题，因为有两个局限性：（1）由于缺乏有效的点，感知小对象比普通对象更为困难。 （2）很容易阻止小物体，从而在3D点云中打破其网格的形状。在本文中，我们提出了一个支柱集抽象（PSA）和前景补偿（FPC），并设计基于点的检测网络PSA-DET3D，以改善小物体的检测性能。 PSA根据设定抽象（SA）嵌入了支柱查询操作，以扩展其网络的接受场，该网络可以有效地汇总点的特征。为了找到更多遮挡的对象，我们将提案生成层组成，该层由前景分段和FPC模块组成。前景点和估计的中心最终都融合在一起以产生检测结果。 KITTI 3D检测基准上的实验表明，我们提出的PSA-DET3D优于其他算法，以高度准确地进行小物体检测。
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.
