PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds release_xgp7xy6khrfk5o3fowzacpdca4

by Jiayao Shan, Sifan Zhou, Zheng Fang, Yubo Cui

Released as a article .

2021  

Abstract

3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature embedding, position encoding, and self-attention feature computation. Feature embedding aims to place features closer in the embedding space if they have similar semantic information. Position encoding is used to encode coordinates of point clouds into high dimension distinguishable features. Self-attention generates refined attention features by computing attention weights. Besides, we embed the PTT module into the open-source state-of-the-art method P2B to construct PTT-Net. Experiments on the KITTI dataset reveal that our PTT-Net surpasses the state-of-the-art by a noticeable margin (~10\%). Additionally, PTT-Net could achieve real-time performance (~40FPS) on NVIDIA 1080Ti GPU. Our code is open-sourced for the robotics community at https://github.com/shanjiayao/PTT.
In text/plain format

Archived Files and Locations

application/pdf  4.4 MB
file_4ivyrwlgzneunmdw2lgqyg4gsu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-08-14
Version   v1
Language   en ?
arXiv  2108.06455v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 6923d843-ff3d-4019-ac61-574177e5a748
API URL: JSON