3D object tracking in point clouds is still a challenging problem due to the sparsity of LiDAR points in dynamic environments. In this work, we propose a Siamese voxel-to-BEV tracker, which can significantly improve the tracking performance in sparse 3D point clouds. Specifically, it consists of a Siamese shape-aware feature learning network and a voxel-to-BEV target localization network. The Siamese shape-aware feature learning network can capture 3D shape information of the object to learn the discriminative features of the object so that the potential target from the background in sparse point clouds can be identified. To this end, we first perform template feature embedding to embed the template's feature into the potential target and then generate a dense 3D shape to characterize the shape information of the potential target. For localizing the tracked target, the voxel-to-BEV target localization network regresses the target's 2D center and the $z$-axis center from the dense bird's eye view (BEV) feature map in an anchor-free manner. Concretely, we compress the voxelized point cloud along $z$-axis through max pooling to obtain a dense BEV feature map, where the regression of the 2D center and the $z$-axis center can be performed more effectively. Extensive evaluation on the KITTI and nuScenes datasets shows that our method significantly outperforms the current state-of-the-art methods by a large margin.
翻译:点云中的 3D 对象跟踪仍是一个挑战性的问题, 因为在动态环境中, LiDAR 点的偏僻性强。 在此工作中, 我们建议使用 siames voxel 至 BEV 跟踪器, 它可以显著改善 3D 点云中的跟踪性能。 具体地说, 它由 siamese 形状- worce 特征学习网络和 voxel- to- BEV 目标本地化网络组成。 siames 形状学习网络可以捕捉该对象的 3D 形状信息, 以学习该对象在动态环境中的区别性能, 从而可以辨明稀疏云层云层中的潜在目标。 为此, 我们首先使用模板功能将模板的特性嵌入到潜在的3D点, 然后生成一个密度 3D 形状来描述潜在目标的形状信息。 为了定位目标的本地化目标, voxel- to BEVEV 目标定位网络将目标的中心和 $z- 轴中点从密度鸟眼视图( BEVEVEV) 地图中, 定位地图中以免费方式显示 $xxxx 中心 。 我们通过 中 的 的 的 中位值中心, 以 以 AS- borx- cremaxx- creal- sal- creal- cremax- sal- creal- sal- crexxxxxxxxx- sal- sal- sal- sal- sal- sald- crevald- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sald- sal ex ex- sal- sal- sessal- sal- sal- sal- sal- sal- sal- sal- sal- ex ex- s- sal- sal- sal- sal- sal- ex- ex- ex- sal- sal-