MITracker: Multi-View Integration for Visual Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Mengjie, Zhu, Yitao, Jiang, Haotian, Li, Jiaming, Shen, Zhenrong, Wang, Sheng, Huang, Haolin, Wang, Xinyu, Yang, Qing, Zhang, Han, Wang, Qian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916633583288320
author Xu, Mengjie
Zhu, Yitao
Jiang, Haotian
Li, Jiaming
Shen, Zhenrong
Wang, Sheng
Huang, Haolin
Wang, Xinyu
Yang, Qing
Zhang, Han
Wang, Qian
author_facet Xu, Mengjie
Zhu, Yitao
Jiang, Haotian
Li, Jiaming
Shen, Zhenrong
Wang, Sheng
Huang, Haolin
Wang, Xinyu
Yang, Qing
Zhang, Han
Wang, Qian
contents Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking. However, progress has been limited by the lack of comprehensive multi-view datasets and effective cross-view integration methods. To overcome these limitations, we compiled a Multi-View object Tracking (MVTrack) dataset of 234K high-quality annotated frames featuring 27 distinct objects across various scenes. In conjunction with this dataset, we introduce a novel MVOT method, Multi-View Integration Tracker (MITracker), to efficiently integrate multi-view object features and provide stable tracking outcomes. MITracker can track any object in video frames of arbitrary length from arbitrary viewpoints. The key advancements of our method over traditional single-view approaches come from two aspects: (1) MITracker transforms 2D image features into a 3D feature volume and compresses it into a bird's eye view (BEV) plane, facilitating inter-view information fusion; (2) we propose an attention mechanism that leverages geometric information from fused 3D feature volume to refine the tracking results at each view. MITracker outperforms existing methods on the MVTrack and GMTD datasets, achieving state-of-the-art performance. The code and the new dataset will be available at https://mii-laboratory.github.io/MITracker/.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20111
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MITracker: Multi-View Integration for Visual Object Tracking
Xu, Mengjie
Zhu, Yitao
Jiang, Haotian
Li, Jiaming
Shen, Zhenrong
Wang, Sheng
Huang, Haolin
Wang, Xinyu
Yang, Qing
Zhang, Han
Wang, Qian
Computer Vision and Pattern Recognition
Artificial Intelligence
Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking. However, progress has been limited by the lack of comprehensive multi-view datasets and effective cross-view integration methods. To overcome these limitations, we compiled a Multi-View object Tracking (MVTrack) dataset of 234K high-quality annotated frames featuring 27 distinct objects across various scenes. In conjunction with this dataset, we introduce a novel MVOT method, Multi-View Integration Tracker (MITracker), to efficiently integrate multi-view object features and provide stable tracking outcomes. MITracker can track any object in video frames of arbitrary length from arbitrary viewpoints. The key advancements of our method over traditional single-view approaches come from two aspects: (1) MITracker transforms 2D image features into a 3D feature volume and compresses it into a bird's eye view (BEV) plane, facilitating inter-view information fusion; (2) we propose an attention mechanism that leverages geometric information from fused 3D feature volume to refine the tracking results at each view. MITracker outperforms existing methods on the MVTrack and GMTD datasets, achieving state-of-the-art performance. The code and the new dataset will be available at https://mii-laboratory.github.io/MITracker/.
title MITracker: Multi-View Integration for Visual Object Tracking
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2502.20111