Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ishaq, Ayesha, Boudjoghra, Mohamed El Amine, Lahoud, Jean, Khan, Fahad Shahbaz, Khan, Salman, Cholakkal, Hisham, Anwer, Rao Muhammad
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909513447112704
author Ishaq, Ayesha
Boudjoghra, Mohamed El Amine
Lahoud, Jean
Khan, Fahad Shahbaz
Khan, Salman
Cholakkal, Hisham
Anwer, Rao Muhammad
author_facet Ishaq, Ayesha
Boudjoghra, Mohamed El Amine
Lahoud, Jean
Khan, Fahad Shahbaz
Khan, Salman
Cholakkal, Hisham
Anwer, Rao Muhammad
contents 3D multi-object tracking plays a critical role in autonomous driving by enabling the real-time monitoring and prediction of multiple objects' movements. Traditional 3D tracking systems are typically constrained by predefined object categories, limiting their adaptability to novel, unseen objects in dynamic environments. To address this limitation, we introduce open-vocabulary 3D tracking, which extends the scope of 3D tracking to include objects beyond predefined categories. We formulate the problem of open-vocabulary 3D tracking and introduce dataset splits designed to represent various open-vocabulary scenarios. We propose a novel approach that integrates open-vocabulary capabilities into a 3D tracking framework, allowing for generalization to unseen object classes. Our method effectively reduces the performance gap between tracking known and novel objects through strategic adaptation. Experimental results demonstrate the robustness and adaptability of our method in diverse outdoor driving scenarios. To the best of our knowledge, this work is the first to address open-vocabulary 3D tracking, presenting a significant advancement for autonomous systems in real-world settings. Code, trained models, and dataset splits are available publicly.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01678
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking
Ishaq, Ayesha
Boudjoghra, Mohamed El Amine
Lahoud, Jean
Khan, Fahad Shahbaz
Khan, Salman
Cholakkal, Hisham
Anwer, Rao Muhammad
Computer Vision and Pattern Recognition
Robotics
3D multi-object tracking plays a critical role in autonomous driving by enabling the real-time monitoring and prediction of multiple objects' movements. Traditional 3D tracking systems are typically constrained by predefined object categories, limiting their adaptability to novel, unseen objects in dynamic environments. To address this limitation, we introduce open-vocabulary 3D tracking, which extends the scope of 3D tracking to include objects beyond predefined categories. We formulate the problem of open-vocabulary 3D tracking and introduce dataset splits designed to represent various open-vocabulary scenarios. We propose a novel approach that integrates open-vocabulary capabilities into a 3D tracking framework, allowing for generalization to unseen object classes. Our method effectively reduces the performance gap between tracking known and novel objects through strategic adaptation. Experimental results demonstrate the robustness and adaptability of our method in diverse outdoor driving scenarios. To the best of our knowledge, this work is the first to address open-vocabulary 3D tracking, presenting a significant advancement for autonomous systems in real-world settings. Code, trained models, and dataset splits are available publicly.
title Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2410.01678