3D Object Tracking with Transformer

Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including target object information. However, most existing LiDAR-based app...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Cui, Yubo, Zheng, Fang, Jiayao Shan, Gu, Zuoxu, Zhou, Sifan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 28.10.2021
Subjects
Cloud computing
Coders
Feature extraction
Microprocessors
Similarity
Three dimensional models
Tracking
Online AccessGet full text

Cover

More Information
Summary:Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including target object information. However, most existing LiDAR-based approaches directly use the extracted point cloud feature to compute similarity while ignoring the attention changes of object regions during tracking. In this paper, we propose a feature fusion network based on transformer architecture. Benefiting from the self-attention mechanism, the transformer encoder captures the inter- and intra- relations among different regions of the point cloud. By using cross-attention, the transformer decoder fuses features and includes more target cues into the current point cloud feature to compute the region attentions, which makes the similarity computing more efficient. Based on this feature fusion network, we propose an end-to-end point cloud object tracking framework, a simple yet effective method for 3D object tracking using point clouds. Comprehensive experimental results on the KITTI dataset show that our method achieves new state-of-the-art performance. Code is available at: https://github.com/3bobo/lttr.
ISSN:2331-8422