论文标题
P2B：3D对象跟踪的点对点网络在点云中
P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
论文作者
论文摘要
朝向点云中的3D对象跟踪，以端到端的学习方式提出了一个新颖的点对点网络。我们的主要思想是首先将潜在目标中心定位在嵌入目标信息的3D搜索区域中。然后，共同执行以点驱动的3D目标提案和验证。这样，可以避免耗时的3D详尽搜索。具体而言，我们首先从模板和搜索区域中的点云中采样种子。然后，我们执行置换不变的功能增强，以将目标线索从模板嵌入到搜索区域中，并用特定于目标的特征表示它们。因此，增强的搜索区种子通过霍夫投票回归潜在的目标中心。通过种子目标得分进一步加强中心。最后，每个中心都将其邻居聚集起来，以利用联合3D目标提案和验证的整体功率。我们将PointNet ++应用于我们的骨干，并且在Kitti跟踪数据集上进行了实验，证明了P2B的优势（比最新的提高了10％）。请注意，P2B可以在单个NVIDIA 1080TI GPU上使用40fps运行。我们的代码和模型可在https://github.com/haozheqi/p2b上找到。
Towards 3D object tracking in point clouds, a novel point-to-box network termed P2B is proposed in an end-to-end learning manner. Our main idea is to first localize potential target centers in 3D search area embedded with target information. Then point-driven 3D target proposal and verification are executed jointly. In this way, the time-consuming 3D exhaustive search can be avoided. Specifically, we first sample seeds from the point clouds in template and search area respectively. Then, we execute permutation-invariant feature augmentation to embed target clues from template into search area seeds and represent them with target-specific features. Consequently, the augmented search area seeds regress the potential target centers via Hough voting. The centers are further strengthened with seed-wise targetness scores. Finally, each center clusters its neighbors to leverage the ensemble power for joint 3D target proposal and verification. We apply PointNet++ as our backbone and experiments on KITTI tracking dataset demonstrate P2B's superiority (~10%'s improvement over state-of-the-art). Note that P2B can run with 40FPS on a single NVIDIA 1080Ti GPU. Our code and model are available at https://github.com/HaozheQi/P2B.
