Depth Attention for Robust RGB Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yu, Mahmood, Arif, Khan, Muhammad Haris
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914992884809728
author Liu, Yu
Mahmood, Arif
Khan, Muhammad Haris
author_facet Liu, Yu
Mahmood, Arif
Khan, Muhammad Haris
contents RGB video object tracking is a fundamental task in computer vision. Its effectiveness can be improved using depth information, particularly for handling motion-blurred target. However, depth information is often missing in commonly used tracking benchmarks. In this work, we propose a new framework that leverages monocular depth estimation to counter the challenges of tracking targets that are out of view or affected by motion blur in RGB video sequences. Specifically, our work introduces following contributions. To the best of our knowledge, we are the first to propose a depth attention mechanism and to formulate a simple framework that allows seamlessly integration of depth information with state of the art tracking algorithms, without RGB-D cameras, elevating accuracy and robustness. We provide extensive experiments on six challenging tracking benchmarks. Our results demonstrate that our approach provides consistent gains over several strong baselines and achieves new SOTA performance. We believe that our method will open up new possibilities for more sophisticated VOT solutions in real-world scenarios. Our code and models are publicly released: https://github.com/LiuYuML/Depth-Attention.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20395
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Depth Attention for Robust RGB Tracking
Liu, Yu
Mahmood, Arif
Khan, Muhammad Haris
Computer Vision and Pattern Recognition
Image and Video Processing
RGB video object tracking is a fundamental task in computer vision. Its effectiveness can be improved using depth information, particularly for handling motion-blurred target. However, depth information is often missing in commonly used tracking benchmarks. In this work, we propose a new framework that leverages monocular depth estimation to counter the challenges of tracking targets that are out of view or affected by motion blur in RGB video sequences. Specifically, our work introduces following contributions. To the best of our knowledge, we are the first to propose a depth attention mechanism and to formulate a simple framework that allows seamlessly integration of depth information with state of the art tracking algorithms, without RGB-D cameras, elevating accuracy and robustness. We provide extensive experiments on six challenging tracking benchmarks. Our results demonstrate that our approach provides consistent gains over several strong baselines and achieves new SOTA performance. We believe that our method will open up new possibilities for more sophisticated VOT solutions in real-world scenarios. Our code and models are publicly released: https://github.com/LiuYuML/Depth-Attention.
title Depth Attention for Robust RGB Tracking
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2410.20395