P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Haozhe Qi, Chen Feng, Zhiguo Cao, Feng Zhao, Yang Xiao; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 6329-6338

Abstract


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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Qi_2020_CVPR,
author = {Qi, Haozhe and Feng, Chen and Cao, Zhiguo and Zhao, Feng and Xiao, Yang},
title = {P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}