Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination

Spatial infrared spot target (SIST) discrimination based on infrared radiation sequences (IRSs) can be considered a univariate trending time series classification task. However, due to the complexity of actual scenarios and the limited opportunities for acquiring IRSs, resulting in noise interferenc...

Full description

Saved in:
Bibliographic Details
Main Authors: Huiying Liu, Jiarong Wang, Weijun Zhong, Haitao Nie, Xiaotong Deng, Jiaqi Sun, Ming Zhu, Ming Wei
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/24/4624
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102917760679936
author Huiying Liu
Jiarong Wang
Weijun Zhong
Haitao Nie
Xiaotong Deng
Jiaqi Sun
Ming Zhu
Ming Wei
author_facet Huiying Liu
Jiarong Wang
Weijun Zhong
Haitao Nie
Xiaotong Deng
Jiaqi Sun
Ming Zhu
Ming Wei
author_sort Huiying Liu
collection DOAJ
description Spatial infrared spot target (SIST) discrimination based on infrared radiation sequences (IRSs) can be considered a univariate trending time series classification task. However, due to the complexity of actual scenarios and the limited opportunities for acquiring IRSs, resulting in noise interference, extremely small-scale datasets with imbalanced distribution of classes and widely varying sequence lengths range from a few hundred to several thousand time steps. Current research is primarily based on idealized simulation datasets, resulting in a performance gap when applied to actual applications. To address these issues, firstly, we construct a simulation dataset tailored to the challenges of actual scenarios. Secondly, we design a practical data preprocessing method to achieve uniform sequence length, coarse alignment of shapelets and filtering while preserving key points. Thirdly, we propose a residual network Res-LK-SLR for IRS classification based on large kernels (LKs, providing long-term dependence) and shapelet-level representations (SLRs, where the hidden layer features are aligned with the learned high-level representations to obtain the optimal segmentation and generate shapelet-level representations). Additionally, we conduct extensive evaluations and validations on both the simulation dataset and 18 UCR time series classification datasets. The results demonstrate the effectiveness and generalization ability of our proposed Res-LK-SLR.
format Article
id doaj-art-3f68463c47d24ae98b1242d61a748a19
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-3f68463c47d24ae98b1242d61a748a192024-12-27T14:50:43ZengMDPI AGRemote Sensing2072-42922024-12-011624462410.3390/rs16244624Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target DiscriminationHuiying Liu0Jiarong Wang1Weijun Zhong2Haitao Nie3Xiaotong Deng4Jiaqi Sun5Ming Zhu6Ming Wei7University of Chinese Academy of Sciences, Beijing 100049, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaSatellite Information Intelligent Processing and Application Research Laboratory, Beijing 100192, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaSatellite Information Intelligent Processing and Application Research Laboratory, Beijing 100192, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaUniversity of Chinese Academy of Sciences, Beijing 100049, ChinaSpatial infrared spot target (SIST) discrimination based on infrared radiation sequences (IRSs) can be considered a univariate trending time series classification task. However, due to the complexity of actual scenarios and the limited opportunities for acquiring IRSs, resulting in noise interference, extremely small-scale datasets with imbalanced distribution of classes and widely varying sequence lengths range from a few hundred to several thousand time steps. Current research is primarily based on idealized simulation datasets, resulting in a performance gap when applied to actual applications. To address these issues, firstly, we construct a simulation dataset tailored to the challenges of actual scenarios. Secondly, we design a practical data preprocessing method to achieve uniform sequence length, coarse alignment of shapelets and filtering while preserving key points. Thirdly, we propose a residual network Res-LK-SLR for IRS classification based on large kernels (LKs, providing long-term dependence) and shapelet-level representations (SLRs, where the hidden layer features are aligned with the learned high-level representations to obtain the optimal segmentation and generate shapelet-level representations). Additionally, we conduct extensive evaluations and validations on both the simulation dataset and 18 UCR time series classification datasets. The results demonstrate the effectiveness and generalization ability of our proposed Res-LK-SLR.https://www.mdpi.com/2072-4292/16/24/4624spatial infrared spot target (SIST) discriminationlarge kernels (LKs)shapelet-level representations (SLRs)oriented toward the real scenario
spellingShingle Huiying Liu
Jiarong Wang
Weijun Zhong
Haitao Nie
Xiaotong Deng
Jiaqi Sun
Ming Zhu
Ming Wei
Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination
Remote Sensing
spatial infrared spot target (SIST) discrimination
large kernels (LKs)
shapelet-level representations (SLRs)
oriented toward the real scenario
title Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination
title_full Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination
title_fullStr Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination
title_full_unstemmed Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination
title_short Res-LK-SLR: A Residual Network Based on Large Kernels and Shapelet-Level Representations for Spatial Infrared Spot Target Discrimination
title_sort res lk slr a residual network based on large kernels and shapelet level representations for spatial infrared spot target discrimination
topic spatial infrared spot target (SIST) discrimination
large kernels (LKs)
shapelet-level representations (SLRs)
oriented toward the real scenario
url https://www.mdpi.com/2072-4292/16/24/4624
work_keys_str_mv AT huiyingliu reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT jiarongwang reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT weijunzhong reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT haitaonie reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT xiaotongdeng reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT jiaqisun reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT mingzhu reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination
AT mingwei reslkslraresidualnetworkbasedonlargekernelsandshapeletlevelrepresentationsforspatialinfraredspottargetdiscrimination