An Online Multiview Learning Algorithm for PolSAR Data Real-Time Classification

Xiangli Nie, Shuguang Ding, Xiayuan Huang, Hong Qiao, Bo Zhang, Zhong-Ping Jiang

Research output: Contribution to journalArticle

Abstract

Polarimetric synthetic aperture radar (PolSAR) data are sequentially acquired and usually large scale. Fast and accurate classification is particularly important for their applications. By introducing online learning, the PolSAR system can learn a classification model incrementally from a stream of instances, which is of high efficiency for newly arrived samples processing, strong adaptability for a dynamically changing environment, and excellent scalability for rapidly increasing data. In this paper, we propose an Online Multi-view Passive-Aggressive learning algorithm, named OMPA, for PolSAR data real-time classification. The polarimetric, color, and texture features are extracted to characterize PolSAR data, and each type of features corresponds to one view. In order to exploit the consistency and complementary property of these views, we give a new optimization model that ensembles the classifiers of multiple distinct views and enforces the agreement between each predictor and the combined predictor. The corresponding algorithms for both binary and multiclass classification tasks are derived, and the update steps have analytical solutions. In addition, we rigorously derive a bound on the number of prediction mistakes of the method. The proposed OMPA algorithm is evaluated on two real PolSAR datasets for built-up areas extraction and land cover classification, respectively. Experimental results demonstrate that OMPA consistently maintains a smaller mistake rate with low time cost and achieves about 1% and 2% accuracy improvements on the datasets, respectively, compared with the best results of the previously known online single-view and multiview learning methods.

Original languageEnglish (US)
Article number8588991
Pages (from-to)302-320
Number of pages19
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume12
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

Synthetic aperture radar
Learning algorithms
synthetic aperture radar
learning
Radar systems
Scalability
land cover
Classifiers
Textures
texture
Color
Processing
prediction
cost
Costs
method

Keywords

  • Multiview learning
  • online classification
  • passive-aggressive (PA) algorithm
  • polarimetric synthetic aperture radar (PolSAR)

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Atmospheric Science

Cite this

An Online Multiview Learning Algorithm for PolSAR Data Real-Time Classification. / Nie, Xiangli; Ding, Shuguang; Huang, Xiayuan; Qiao, Hong; Zhang, Bo; Jiang, Zhong-Ping.

In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 12, No. 1, 8588991, 01.01.2019, p. 302-320.

Research output: Contribution to journalArticle

@article{42fc81cece8648b89118b76b12fe608c,
title = "An Online Multiview Learning Algorithm for PolSAR Data Real-Time Classification",
abstract = "Polarimetric synthetic aperture radar (PolSAR) data are sequentially acquired and usually large scale. Fast and accurate classification is particularly important for their applications. By introducing online learning, the PolSAR system can learn a classification model incrementally from a stream of instances, which is of high efficiency for newly arrived samples processing, strong adaptability for a dynamically changing environment, and excellent scalability for rapidly increasing data. In this paper, we propose an Online Multi-view Passive-Aggressive learning algorithm, named OMPA, for PolSAR data real-time classification. The polarimetric, color, and texture features are extracted to characterize PolSAR data, and each type of features corresponds to one view. In order to exploit the consistency and complementary property of these views, we give a new optimization model that ensembles the classifiers of multiple distinct views and enforces the agreement between each predictor and the combined predictor. The corresponding algorithms for both binary and multiclass classification tasks are derived, and the update steps have analytical solutions. In addition, we rigorously derive a bound on the number of prediction mistakes of the method. The proposed OMPA algorithm is evaluated on two real PolSAR datasets for built-up areas extraction and land cover classification, respectively. Experimental results demonstrate that OMPA consistently maintains a smaller mistake rate with low time cost and achieves about 1{\%} and 2{\%} accuracy improvements on the datasets, respectively, compared with the best results of the previously known online single-view and multiview learning methods.",
keywords = "Multiview learning, online classification, passive-aggressive (PA) algorithm, polarimetric synthetic aperture radar (PolSAR)",
author = "Xiangli Nie and Shuguang Ding and Xiayuan Huang and Hong Qiao and Bo Zhang and Zhong-Ping Jiang",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/JSTARS.2018.2886821",
language = "English (US)",
volume = "12",
pages = "302--320",
journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
issn = "1939-1404",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - An Online Multiview Learning Algorithm for PolSAR Data Real-Time Classification

AU - Nie, Xiangli

AU - Ding, Shuguang

AU - Huang, Xiayuan

AU - Qiao, Hong

AU - Zhang, Bo

AU - Jiang, Zhong-Ping

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Polarimetric synthetic aperture radar (PolSAR) data are sequentially acquired and usually large scale. Fast and accurate classification is particularly important for their applications. By introducing online learning, the PolSAR system can learn a classification model incrementally from a stream of instances, which is of high efficiency for newly arrived samples processing, strong adaptability for a dynamically changing environment, and excellent scalability for rapidly increasing data. In this paper, we propose an Online Multi-view Passive-Aggressive learning algorithm, named OMPA, for PolSAR data real-time classification. The polarimetric, color, and texture features are extracted to characterize PolSAR data, and each type of features corresponds to one view. In order to exploit the consistency and complementary property of these views, we give a new optimization model that ensembles the classifiers of multiple distinct views and enforces the agreement between each predictor and the combined predictor. The corresponding algorithms for both binary and multiclass classification tasks are derived, and the update steps have analytical solutions. In addition, we rigorously derive a bound on the number of prediction mistakes of the method. The proposed OMPA algorithm is evaluated on two real PolSAR datasets for built-up areas extraction and land cover classification, respectively. Experimental results demonstrate that OMPA consistently maintains a smaller mistake rate with low time cost and achieves about 1% and 2% accuracy improvements on the datasets, respectively, compared with the best results of the previously known online single-view and multiview learning methods.

AB - Polarimetric synthetic aperture radar (PolSAR) data are sequentially acquired and usually large scale. Fast and accurate classification is particularly important for their applications. By introducing online learning, the PolSAR system can learn a classification model incrementally from a stream of instances, which is of high efficiency for newly arrived samples processing, strong adaptability for a dynamically changing environment, and excellent scalability for rapidly increasing data. In this paper, we propose an Online Multi-view Passive-Aggressive learning algorithm, named OMPA, for PolSAR data real-time classification. The polarimetric, color, and texture features are extracted to characterize PolSAR data, and each type of features corresponds to one view. In order to exploit the consistency and complementary property of these views, we give a new optimization model that ensembles the classifiers of multiple distinct views and enforces the agreement between each predictor and the combined predictor. The corresponding algorithms for both binary and multiclass classification tasks are derived, and the update steps have analytical solutions. In addition, we rigorously derive a bound on the number of prediction mistakes of the method. The proposed OMPA algorithm is evaluated on two real PolSAR datasets for built-up areas extraction and land cover classification, respectively. Experimental results demonstrate that OMPA consistently maintains a smaller mistake rate with low time cost and achieves about 1% and 2% accuracy improvements on the datasets, respectively, compared with the best results of the previously known online single-view and multiview learning methods.

KW - Multiview learning

KW - online classification

KW - passive-aggressive (PA) algorithm

KW - polarimetric synthetic aperture radar (PolSAR)

UR - http://www.scopus.com/inward/record.url?scp=85059269856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059269856&partnerID=8YFLogxK

U2 - 10.1109/JSTARS.2018.2886821

DO - 10.1109/JSTARS.2018.2886821

M3 - Article

VL - 12

SP - 302

EP - 320

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

IS - 1

M1 - 8588991

ER -