Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction

In order to address the problems of in-plane rotation and fast motion during near-infrared (NIR) video target tracking, this study explores the application of capsule networks in NIR video and proposes a capsule network method based on background information and spectral position prediction. First,...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Wu, Mengyuan Wang, Weixiang Zhong, Kunpeng Huang, Wenhao Jiang, Jia Li, Dong Zhao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4275
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712359654817792
author Li Wu
Mengyuan Wang
Weixiang Zhong
Kunpeng Huang
Wenhao Jiang
Jia Li
Dong Zhao
author_facet Li Wu
Mengyuan Wang
Weixiang Zhong
Kunpeng Huang
Wenhao Jiang
Jia Li
Dong Zhao
author_sort Li Wu
collection DOAJ
description In order to address the problems of in-plane rotation and fast motion during near-infrared (NIR) video target tracking, this study explores the application of capsule networks in NIR video and proposes a capsule network method based on background information and spectral position prediction. First, the history frame background information extraction module is proposed. This module performs spectral matching on the history frame images through the average spectral curve of the groundtruth value of the target and makes a rough distinction between the target and the background. On this basis, the background information of history frames is stored as a background pool for subsequent operations. The proposed background target routing module combines the traditional capsule network algorithm with spectral information. Specifically, the similarity between the target capsule and the background capsule in the spectral feature space is calculated, and the capsule weight allocation mechanism is dynamically adjusted. Thus, the discriminative ability of the target and background is strengthened. Finally, the spectral information position prediction module locates the center of the search region in the next frame by fusing the position information and spectral features of adjacent frames with the current frame. This module effectively reduces the computational complexity of feature extraction by capsule networks and improves tracking stability. Experimental evaluations demonstrate that the novel framework achieves superior performance compared to current methods, attaining a 70.3% success rate and 88.4% accuracy on near-infrared (NIR) data. Meanwhile, for visible spectrum (VIS) data analysis, the architecture maintains competitive effectiveness with a 59.6% success rate and 78.8% precision.
format Article
id doaj-art-e19d0447551147d6a40ddd1603ea60a3
institution DOAJ
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e19d0447551147d6a40ddd1603ea60a32025-08-20T03:14:17ZengMDPI AGApplied Sciences2076-34172025-04-01158427510.3390/app15084275Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position PredictionLi Wu0Mengyuan Wang1Weixiang Zhong2Kunpeng Huang3Wenhao Jiang4Jia Li5Dong Zhao6Jiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaJiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaJiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaJiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaJiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaFundamentals Department, Air Force Engineering University, Xi’an 710051, ChinaJiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaIn order to address the problems of in-plane rotation and fast motion during near-infrared (NIR) video target tracking, this study explores the application of capsule networks in NIR video and proposes a capsule network method based on background information and spectral position prediction. First, the history frame background information extraction module is proposed. This module performs spectral matching on the history frame images through the average spectral curve of the groundtruth value of the target and makes a rough distinction between the target and the background. On this basis, the background information of history frames is stored as a background pool for subsequent operations. The proposed background target routing module combines the traditional capsule network algorithm with spectral information. Specifically, the similarity between the target capsule and the background capsule in the spectral feature space is calculated, and the capsule weight allocation mechanism is dynamically adjusted. Thus, the discriminative ability of the target and background is strengthened. Finally, the spectral information position prediction module locates the center of the search region in the next frame by fusing the position information and spectral features of adjacent frames with the current frame. This module effectively reduces the computational complexity of feature extraction by capsule networks and improves tracking stability. Experimental evaluations demonstrate that the novel framework achieves superior performance compared to current methods, attaining a 70.3% success rate and 88.4% accuracy on near-infrared (NIR) data. Meanwhile, for visible spectrum (VIS) data analysis, the architecture maintains competitive effectiveness with a 59.6% success rate and 78.8% precision.https://www.mdpi.com/2076-3417/15/8/4275near-infrared hyperspectralvideo trackercapsule networkspectral informationbackground information
spellingShingle Li Wu
Mengyuan Wang
Weixiang Zhong
Kunpeng Huang
Wenhao Jiang
Jia Li
Dong Zhao
Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction
Applied Sciences
near-infrared hyperspectral
video tracker
capsule network
spectral information
background information
title Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction
title_full Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction
title_fullStr Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction
title_full_unstemmed Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction
title_short Near-Infrared Hyperspectral Target Tracking Based on Background Information and Spectral Position Prediction
title_sort near infrared hyperspectral target tracking based on background information and spectral position prediction
topic near-infrared hyperspectral
video tracker
capsule network
spectral information
background information
url https://www.mdpi.com/2076-3417/15/8/4275
work_keys_str_mv AT liwu nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction
AT mengyuanwang nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction
AT weixiangzhong nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction
AT kunpenghuang nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction
AT wenhaojiang nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction
AT jiali nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction
AT dongzhao nearinfraredhyperspectraltargettrackingbasedonbackgroundinformationandspectralpositionprediction