An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification

Xiangli Nie, Yongkang Luo, Hong Qiao, Bo Zhang, Zhong-Ping Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The fast and accurate classification of polarimetric synthetic aperture radar (PolSAR) data in dynamically changing environments is an important and challenging task. In this paper, we propose an Incremental Multi-view Passive-Aggressive Active learning algorithm, named IMPAA, for PolSAR data classification. This algorithm can deal with online two-view multi-class categorization problem by exploiting the relationship between the polarimetric-color and texture feature sets of PolSAR data. In addition, the IMPAA algorithm can handle the dynamic large-scale datasets where not only the amount of data but also the number of classes gradually increases. Moreover, this algorithm only queries the class labels of some informative incoming samples to update the classifier based on the disagreement of different views' predictors and a randomized rule. Experiments on real PolSAR data demonstrate that the proposed method can use a smaller fraction of queried labels to achieve low online classification errors compared with previously known methods.

Original languageEnglish (US)
Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2251-2255
Number of pages5
ISBN (Electronic)9781538637883
DOIs
StatePublished - Nov 26 2018
Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
Duration: Aug 20 2018Aug 24 2018

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2018-August
ISSN (Print)1051-4651

Other

Other24th International Conference on Pattern Recognition, ICPR 2018
CountryChina
CityBeijing
Period8/20/188/24/18

Fingerprint

Synthetic aperture radar
Learning algorithms
Labels
Classifiers
Textures
Color
Problem-Based Learning
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Nie, X., Luo, Y., Qiao, H., Zhang, B., & Jiang, Z-P. (2018). An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification. In 2018 24th International Conference on Pattern Recognition, ICPR 2018 (pp. 2251-2255). [8545325] (Proceedings - International Conference on Pattern Recognition; Vol. 2018-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8545325

An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification. / Nie, Xiangli; Luo, Yongkang; Qiao, Hong; Zhang, Bo; Jiang, Zhong-Ping.

2018 24th International Conference on Pattern Recognition, ICPR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 2251-2255 8545325 (Proceedings - International Conference on Pattern Recognition; Vol. 2018-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nie, X, Luo, Y, Qiao, H, Zhang, B & Jiang, Z-P 2018, An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification. in 2018 24th International Conference on Pattern Recognition, ICPR 2018., 8545325, Proceedings - International Conference on Pattern Recognition, vol. 2018-August, Institute of Electrical and Electronics Engineers Inc., pp. 2251-2255, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 8/20/18. https://doi.org/10.1109/ICPR.2018.8545325
Nie X, Luo Y, Qiao H, Zhang B, Jiang Z-P. An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification. In 2018 24th International Conference on Pattern Recognition, ICPR 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 2251-2255. 8545325. (Proceedings - International Conference on Pattern Recognition). https://doi.org/10.1109/ICPR.2018.8545325
Nie, Xiangli ; Luo, Yongkang ; Qiao, Hong ; Zhang, Bo ; Jiang, Zhong-Ping. / An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification. 2018 24th International Conference on Pattern Recognition, ICPR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 2251-2255 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{23d16df4dfd6476e9ae66f8b413f4421,
title = "An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification",
abstract = "The fast and accurate classification of polarimetric synthetic aperture radar (PolSAR) data in dynamically changing environments is an important and challenging task. In this paper, we propose an Incremental Multi-view Passive-Aggressive Active learning algorithm, named IMPAA, for PolSAR data classification. This algorithm can deal with online two-view multi-class categorization problem by exploiting the relationship between the polarimetric-color and texture feature sets of PolSAR data. In addition, the IMPAA algorithm can handle the dynamic large-scale datasets where not only the amount of data but also the number of classes gradually increases. Moreover, this algorithm only queries the class labels of some informative incoming samples to update the classifier based on the disagreement of different views' predictors and a randomized rule. Experiments on real PolSAR data demonstrate that the proposed method can use a smaller fraction of queried labels to achieve low online classification errors compared with previously known methods.",
author = "Xiangli Nie and Yongkang Luo and Hong Qiao and Bo Zhang and Zhong-Ping Jiang",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICPR.2018.8545325",
language = "English (US)",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2251--2255",
booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",

}

TY - GEN

T1 - An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification

AU - Nie, Xiangli

AU - Luo, Yongkang

AU - Qiao, Hong

AU - Zhang, Bo

AU - Jiang, Zhong-Ping

PY - 2018/11/26

Y1 - 2018/11/26

N2 - The fast and accurate classification of polarimetric synthetic aperture radar (PolSAR) data in dynamically changing environments is an important and challenging task. In this paper, we propose an Incremental Multi-view Passive-Aggressive Active learning algorithm, named IMPAA, for PolSAR data classification. This algorithm can deal with online two-view multi-class categorization problem by exploiting the relationship between the polarimetric-color and texture feature sets of PolSAR data. In addition, the IMPAA algorithm can handle the dynamic large-scale datasets where not only the amount of data but also the number of classes gradually increases. Moreover, this algorithm only queries the class labels of some informative incoming samples to update the classifier based on the disagreement of different views' predictors and a randomized rule. Experiments on real PolSAR data demonstrate that the proposed method can use a smaller fraction of queried labels to achieve low online classification errors compared with previously known methods.

AB - The fast and accurate classification of polarimetric synthetic aperture radar (PolSAR) data in dynamically changing environments is an important and challenging task. In this paper, we propose an Incremental Multi-view Passive-Aggressive Active learning algorithm, named IMPAA, for PolSAR data classification. This algorithm can deal with online two-view multi-class categorization problem by exploiting the relationship between the polarimetric-color and texture feature sets of PolSAR data. In addition, the IMPAA algorithm can handle the dynamic large-scale datasets where not only the amount of data but also the number of classes gradually increases. Moreover, this algorithm only queries the class labels of some informative incoming samples to update the classifier based on the disagreement of different views' predictors and a randomized rule. Experiments on real PolSAR data demonstrate that the proposed method can use a smaller fraction of queried labels to achieve low online classification errors compared with previously known methods.

UR - http://www.scopus.com/inward/record.url?scp=85059776399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059776399&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2018.8545325

DO - 10.1109/ICPR.2018.8545325

M3 - Conference contribution

T3 - Proceedings - International Conference on Pattern Recognition

SP - 2251

EP - 2255

BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -