A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data
Unsupervised change detection approaches, which are relatively straightforward and easy to implement and interpret, and which require no human intervention, are widely used in change detection. Polarimetric synthetic aperture radar (PolSAR), which has an all-weather response capability with increase...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/5/1508 |
id |
doaj-ff17fb46422e49308cc0a453533be980 |
---|---|
record_format |
Article |
spelling |
doaj-ff17fb46422e49308cc0a453533be9802020-11-25T03:00:20ZengMDPI AGSensors1424-82202020-03-01205150810.3390/s20051508s20051508A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR DataJinqi Zhao0Yonglei Chang1Jie Yang2Yufen Niu3Zhong Lu4Pingxiang Li5State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaFaculty of Geomatics, East China University of Technology, Nanchang 330013, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaCollege of Geology Engineering and Geomatics, Chang’an University, Xian 710054, ChinaHuffington Department of Earth Sciences, Southern Methodist University, Dallas, TX 75275, USAState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaUnsupervised change detection approaches, which are relatively straightforward and easy to implement and interpret, and which require no human intervention, are widely used in change detection. Polarimetric synthetic aperture radar (PolSAR), which has an all-weather response capability with increased polarimetric information, is a key tool for change detection. However, for PolSAR data, inadequate evaluation of the difference image (DI) map makes the threshold-based algorithms incompatible with the true distribution model, which causes the change detection results to be ineffective and inaccurate. In this paper, to solve these problems, we focus on the generation of the DI map and the selection of the optimal threshold. An omnibus test statistic is used to generate the DI map from multi-temporal PolSAR images, and an improved Kittler and Illingworth algorithm based on either Weibull or gamma distribution is used to obtain the optimal threshold for generating the change detection map. Multi-temporal PolSAR data obtained by the Radarsat-2 sensor over Wuhan in China are used to verify the efficiency of the proposed method. The experimental results using our approach obtained the best performance in East Lake and Yanxi Lake regions with false alarm rates of 1.59% and 1.80%, total errors of 2.73% and 4.33%, overall accuracy of 97.27% and 95.67%, and Kappa coefficients of 0.6486 and 0.6275, respectively. Our results demonstrated that the proposed method is more suitable than the other compared methods for multi-temporal PolSAR data, and it can obtain both effective and accurate results.https://www.mdpi.com/1424-8220/20/5/1508change detectionomnibus test statistickittler and illingworth (k&i)weibull distributiongamma distributionpolsar |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jinqi Zhao Yonglei Chang Jie Yang Yufen Niu Zhong Lu Pingxiang Li |
spellingShingle |
Jinqi Zhao Yonglei Chang Jie Yang Yufen Niu Zhong Lu Pingxiang Li A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data Sensors change detection omnibus test statistic kittler and illingworth (k& i) weibull distribution gamma distribution polsar |
author_facet |
Jinqi Zhao Yonglei Chang Jie Yang Yufen Niu Zhong Lu Pingxiang Li |
author_sort |
Jinqi Zhao |
title |
A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data |
title_short |
A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data |
title_full |
A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data |
title_fullStr |
A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data |
title_full_unstemmed |
A Novel Change Detection Method Based on Statistical Distribution Characteristics Using Multi-Temporal PolSAR Data |
title_sort |
novel change detection method based on statistical distribution characteristics using multi-temporal polsar data |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-03-01 |
description |
Unsupervised change detection approaches, which are relatively straightforward and easy to implement and interpret, and which require no human intervention, are widely used in change detection. Polarimetric synthetic aperture radar (PolSAR), which has an all-weather response capability with increased polarimetric information, is a key tool for change detection. However, for PolSAR data, inadequate evaluation of the difference image (DI) map makes the threshold-based algorithms incompatible with the true distribution model, which causes the change detection results to be ineffective and inaccurate. In this paper, to solve these problems, we focus on the generation of the DI map and the selection of the optimal threshold. An omnibus test statistic is used to generate the DI map from multi-temporal PolSAR images, and an improved Kittler and Illingworth algorithm based on either Weibull or gamma distribution is used to obtain the optimal threshold for generating the change detection map. Multi-temporal PolSAR data obtained by the Radarsat-2 sensor over Wuhan in China are used to verify the efficiency of the proposed method. The experimental results using our approach obtained the best performance in East Lake and Yanxi Lake regions with false alarm rates of 1.59% and 1.80%, total errors of 2.73% and 4.33%, overall accuracy of 97.27% and 95.67%, and Kappa coefficients of 0.6486 and 0.6275, respectively. Our results demonstrated that the proposed method is more suitable than the other compared methods for multi-temporal PolSAR data, and it can obtain both effective and accurate results. |
topic |
change detection omnibus test statistic kittler and illingworth (k& i) weibull distribution gamma distribution polsar |
url |
https://www.mdpi.com/1424-8220/20/5/1508 |
work_keys_str_mv |
AT jinqizhao anovelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT yongleichang anovelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT jieyang anovelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT yufenniu anovelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT zhonglu anovelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT pingxiangli anovelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT jinqizhao novelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT yongleichang novelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT jieyang novelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT yufenniu novelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT zhonglu novelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata AT pingxiangli novelchangedetectionmethodbasedonstatisticaldistributioncharacteristicsusingmultitemporalpolsardata |
_version_ |
1724698687737692160 |