Part-Based Background-Aware Tracking for UAV With Convolutional Features
In recent years, visual tracking is a challenging task in UAV applications. The standard correlation filter (CF) has been extensively applied for UAV object tracking. However, the CF-based tracker severely suffers from boundary effects and cannot effectively cope with object occlusion, which results...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8736485/ |
id |
doaj-3b588e7831d847a1aabff1b3c144728d |
---|---|
record_format |
Article |
spelling |
doaj-3b588e7831d847a1aabff1b3c144728d2021-03-30T00:09:59ZengIEEEIEEE Access2169-35362019-01-017799978001010.1109/ACCESS.2019.29227038736485Part-Based Background-Aware Tracking for UAV With Convolutional FeaturesChanghong Fu0https://orcid.org/0000-0002-9897-6022Yinqiang Zhang1Ziyuan Huang2Ran Duan3Zongwu Xie4School of Mechanical Engineering, Tongji University, Shanghai, ChinaDepartment of Mechanical Engineering, Technical University of Munich, Munich, GermanySchool of Automotive Studies, Tongji University, Shanghai, ChinaAdaptive Robotic Controls Lab, Hong Kong Polytechnic University, Hong KongState Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, ChinaIn recent years, visual tracking is a challenging task in UAV applications. The standard correlation filter (CF) has been extensively applied for UAV object tracking. However, the CF-based tracker severely suffers from boundary effects and cannot effectively cope with object occlusion, which results in suboptimal performance. Besides, it is still a tough task to obtain an appearance model precisely with hand-crafted features. In this paper, a novel part-based tracker is proposed for the UAV. With successive cropping operations, the tracking object is separated into several parts. More specially, the background-aware correlation filters with different cropping matrices are applied. To estimate the translation and scale variation of the tracking object, a structured comparison, and a Bayesian inference approach are proposed, which jointly achieve a coarse-to-fine strategy. Moreover, an adaptive mechanism is used to update the local appearance model of each part with a Gaussian process regression method. To construct a better appearance model, features extracted from the convolutional neural network are utilized instead of hand-crafted features. Through extensive experiments, the proposed tracker reaches competitive performance on 123 challenging UAV image sequences and outperforms other 20 popular state-of-the-art visual trackers in terms of overall performance and different challenging attributes.https://ieeexplore.ieee.org/document/8736485/Visual object trackingunmanned aerial vehicle (UAV)convolutional neural networkbackground-aware correlation filterpart-based strategyGaussian process regression |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Changhong Fu Yinqiang Zhang Ziyuan Huang Ran Duan Zongwu Xie |
spellingShingle |
Changhong Fu Yinqiang Zhang Ziyuan Huang Ran Duan Zongwu Xie Part-Based Background-Aware Tracking for UAV With Convolutional Features IEEE Access Visual object tracking unmanned aerial vehicle (UAV) convolutional neural network background-aware correlation filter part-based strategy Gaussian process regression |
author_facet |
Changhong Fu Yinqiang Zhang Ziyuan Huang Ran Duan Zongwu Xie |
author_sort |
Changhong Fu |
title |
Part-Based Background-Aware Tracking for UAV With Convolutional Features |
title_short |
Part-Based Background-Aware Tracking for UAV With Convolutional Features |
title_full |
Part-Based Background-Aware Tracking for UAV With Convolutional Features |
title_fullStr |
Part-Based Background-Aware Tracking for UAV With Convolutional Features |
title_full_unstemmed |
Part-Based Background-Aware Tracking for UAV With Convolutional Features |
title_sort |
part-based background-aware tracking for uav with convolutional features |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
In recent years, visual tracking is a challenging task in UAV applications. The standard correlation filter (CF) has been extensively applied for UAV object tracking. However, the CF-based tracker severely suffers from boundary effects and cannot effectively cope with object occlusion, which results in suboptimal performance. Besides, it is still a tough task to obtain an appearance model precisely with hand-crafted features. In this paper, a novel part-based tracker is proposed for the UAV. With successive cropping operations, the tracking object is separated into several parts. More specially, the background-aware correlation filters with different cropping matrices are applied. To estimate the translation and scale variation of the tracking object, a structured comparison, and a Bayesian inference approach are proposed, which jointly achieve a coarse-to-fine strategy. Moreover, an adaptive mechanism is used to update the local appearance model of each part with a Gaussian process regression method. To construct a better appearance model, features extracted from the convolutional neural network are utilized instead of hand-crafted features. Through extensive experiments, the proposed tracker reaches competitive performance on 123 challenging UAV image sequences and outperforms other 20 popular state-of-the-art visual trackers in terms of overall performance and different challenging attributes. |
topic |
Visual object tracking unmanned aerial vehicle (UAV) convolutional neural network background-aware correlation filter part-based strategy Gaussian process regression |
url |
https://ieeexplore.ieee.org/document/8736485/ |
work_keys_str_mv |
AT changhongfu partbasedbackgroundawaretrackingforuavwithconvolutionalfeatures AT yinqiangzhang partbasedbackgroundawaretrackingforuavwithconvolutionalfeatures AT ziyuanhuang partbasedbackgroundawaretrackingforuavwithconvolutionalfeatures AT randuan partbasedbackgroundawaretrackingforuavwithconvolutionalfeatures AT zongwuxie partbasedbackgroundawaretrackingforuavwithconvolutionalfeatures |
_version_ |
1724188534668001280 |