LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble

Change detection (CD) in synthetic aperture radar (SAR) images faces two challenging problems limiting the detection performance: inherent speckle noise in SAR data causes the overlapping nature of changed and unchanged classes and, thus, affects the image understanding for inferring category of eac...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jian Wang, Yinghua Wang, Bo Chen, Hongwei Liu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Change detection (CD) deep neural network (DNN) label-consistent self-ensemble semisupervised learning (SSL) spatially enhanced (SE) difference image (DI) synthetic aperture radar (SAR) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/2fa5a4f1708f43a4a1ddec9e489c119e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2fa5a4f1708f43a4a1ddec9e489c119e
record_format	dspace
spelling	oai:doaj.org-article:2fa5a4f1708f43a4a1ddec9e489c119e2021-12-04T00:00:11ZLCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble2151-153510.1109/JSTARS.2021.3122461https://doaj.org/article/2fa5a4f1708f43a4a1ddec9e489c119e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9585635/https://doaj.org/toc/2151-1535Change detection (CD) in synthetic aperture radar (SAR) images faces two challenging problems limiting the detection performance: inherent speckle noise in SAR data causes the overlapping nature of changed and unchanged classes and, thus, affects the image understanding for inferring category of each image pixel; and adequate labeled samples are quite laborious and time-consuming to collect, which is the major limitation for supervised methods. In this article, we develop a novel deep learning-based semisupervised method to address these challenges. The method first incorporates a pixel-wise log-ratio difference image (DI) and its saliency map to produce a spatially enhanced (SE) DI using a reweighting scheme based on the fact that changed pixels exhibit higher saliency than unchanged pixels. As a result, prominent changed regions are highlighted, and the class separability is significantly increased. We construct pixel-wise and context-wise features based on the log-ratio DI and SE DI, which respectively provide image detail cue and spatial context cue, as dual input features to jointly characterize the change information at each pixel position. Second, we propose a label-consistent self-ensemble network (LCS-EnsemNet), which can take advantage of the unlabeled samples to learn discriminative high-level features for the precise identification of changed pixels. By enforcing a label consistency between dual features and a label consistency across multiple classifiers, the label-consistent self-ensemble strategy enables the proposed network to selectively transform unlabeled samples into pseudo-labeled samples in an unsupervised manner and ensures that the selected pseudo-labels are reliably and stably predicted. Finally, the cross-entropy loss is calculated with the limited labeled data and selected pseudo-labeled samples to optimize the LCS-EnsemNet in a supervised way. The proposed method is evaluated on three low/medium-resolution SAR datasets and one high-resolution SAR dataset, and experimental results have demonstrated its efficiency and effectiveness.Jian WangYinghua WangBo ChenHongwei LiuIEEEarticleChange detection (CD)deep neural network (DNN)label-consistent self-ensemblesemisupervised learning (SSL)spatially enhanced (SE) difference image (DI)synthetic aperture radar (SAR)Ocean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11903-11925 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Change detection (CD) deep neural network (DNN) label-consistent self-ensemble semisupervised learning (SSL) spatially enhanced (SE) difference image (DI) synthetic aperture radar (SAR) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Change detection (CD) deep neural network (DNN) label-consistent self-ensemble semisupervised learning (SSL) spatially enhanced (SE) difference image (DI) synthetic aperture radar (SAR) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Jian Wang Yinghua Wang Bo Chen Hongwei Liu LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble
description	Change detection (CD) in synthetic aperture radar (SAR) images faces two challenging problems limiting the detection performance: inherent speckle noise in SAR data causes the overlapping nature of changed and unchanged classes and, thus, affects the image understanding for inferring category of each image pixel; and adequate labeled samples are quite laborious and time-consuming to collect, which is the major limitation for supervised methods. In this article, we develop a novel deep learning-based semisupervised method to address these challenges. The method first incorporates a pixel-wise log-ratio difference image (DI) and its saliency map to produce a spatially enhanced (SE) DI using a reweighting scheme based on the fact that changed pixels exhibit higher saliency than unchanged pixels. As a result, prominent changed regions are highlighted, and the class separability is significantly increased. We construct pixel-wise and context-wise features based on the log-ratio DI and SE DI, which respectively provide image detail cue and spatial context cue, as dual input features to jointly characterize the change information at each pixel position. Second, we propose a label-consistent self-ensemble network (LCS-EnsemNet), which can take advantage of the unlabeled samples to learn discriminative high-level features for the precise identification of changed pixels. By enforcing a label consistency between dual features and a label consistency across multiple classifiers, the label-consistent self-ensemble strategy enables the proposed network to selectively transform unlabeled samples into pseudo-labeled samples in an unsupervised manner and ensures that the selected pseudo-labels are reliably and stably predicted. Finally, the cross-entropy loss is calculated with the limited labeled data and selected pseudo-labeled samples to optimize the LCS-EnsemNet in a supervised way. The proposed method is evaluated on three low/medium-resolution SAR datasets and one high-resolution SAR dataset, and experimental results have demonstrated its efficiency and effectiveness.
format	article
author	Jian Wang Yinghua Wang Bo Chen Hongwei Liu
author_facet	Jian Wang Yinghua Wang Bo Chen Hongwei Liu
author_sort	Jian Wang
title	LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble
title_short	LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble
title_full	LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble
title_fullStr	LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble
title_full_unstemmed	LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble
title_sort	lcs-ensemnet: a semisupervised deep neural network for sar image change detection with dual feature extraction and label-consistent self-ensemble
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/2fa5a4f1708f43a4a1ddec9e489c119e
work_keys_str_mv	AT jianwang lcsensemnetasemisuperviseddeepneuralnetworkforsarimagechangedetectionwithdualfeatureextractionandlabelconsistentselfensemble AT yinghuawang lcsensemnetasemisuperviseddeepneuralnetworkforsarimagechangedetectionwithdualfeatureextractionandlabelconsistentselfensemble AT bochen lcsensemnetasemisuperviseddeepneuralnetworkforsarimagechangedetectionwithdualfeatureextractionandlabelconsistentselfensemble AT hongweiliu lcsensemnetasemisuperviseddeepneuralnetworkforsarimagechangedetectionwithdualfeatureextractionandlabelconsistentselfensemble
_version_	1718373022212030464

LCS-EnsemNet: A Semisupervised Deep Neural Network for SAR Image Change Detection With Dual Feature Extraction and Label-Consistent Self-Ensemble

Ejemplares similares