A new approach for crop identification with wavelet variance and JM distance

Bingwen Qiu, Zhanling Fan, Ming Zhong, Zhenghong Tang, Chongcheng Chen

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This paper develops a new crop mapping method through combined utilization of both time and frequency information based on wavelet variance and Jeffries–Matusita (JM) distance (CIWJ for short). A two-dimensional wavelet spectrum was obtained from datasets of daily continuous vegetation indices through a continuous wavelet transform using the Mexican hat and the Morlet mother wavelets. The time-average wavelet variance (TAWV) and the scale-average wavelet variance (SAWV) were then calculated based on the wavelet spectrum of the Mexican hat and the Morlet wavelet, respectively. The class separability based on the JM distance was evaluated to discriminate the proper period or scale range applied. Finally, a procedure for criteria quantification was developed using the TAWV and SAWV as the major metrics, and the similarity between unclassified pixels and established land use/cover types was calculated. The proposed CIWJ method was applied to the middle Hexi Corridor in northwest China using 250-m 8-day composite moderate-resolution imaging spectroradiometer (MODIS) enhanced vegetation index (EVI) time series datasets in 2012. The CIWJ method was shown to be efficient in crop field mapping, with an overall accuracy of 83.6 % and kappa coefficient of 0.7009, assessed with 30 m Chinese Environmental Disaster Reduction Satellite (HJ-1)-derived data. Compared with methods utilizing information on either frequency or time, the CIWJ method demonstrates tremendous potential for efficient crop mapping and for further applications. This method could be applied to either coarse or high spatial resolution images for agricultural crop identification, as well as other more general or specific land use classifications.

Original languageEnglish (US)
Pages (from-to)7929-7940
Number of pages12
JournalEnvironmental Monitoring and Assessment
Volume186
Issue number11
DOIs
StatePublished - Oct 3 2014

Fingerprint

wavelet
Crops
crop
Land use
Image resolution
Disasters
Wavelet transforms
Satellite Imagery
Time series
Agricultural Crops
vegetation index
Pixels
Wavelet Analysis
Satellites
Imaging techniques
Composite materials
mapping method
China
MODIS
disaster

Keywords

  • Continuous wavelet transform
  • Crop mapping
  • JM distance
  • SAWV
  • TAWV

ASJC Scopus subject areas

  • Environmental Science(all)
  • Pollution
  • Management, Monitoring, Policy and Law

Cite this

A new approach for crop identification with wavelet variance and JM distance. / Qiu, Bingwen; Fan, Zhanling; Zhong, Ming; Tang, Zhenghong; Chen, Chongcheng.

In: Environmental Monitoring and Assessment, Vol. 186, No. 11, 03.10.2014, p. 7929-7940.

Research output: Contribution to journalArticle

Qiu, Bingwen ; Fan, Zhanling ; Zhong, Ming ; Tang, Zhenghong ; Chen, Chongcheng. / A new approach for crop identification with wavelet variance and JM distance. In: Environmental Monitoring and Assessment. 2014 ; Vol. 186, No. 11. pp. 7929-7940.
@article{dde79a3b9a114b3ab67046c9b271300c,
title = "A new approach for crop identification with wavelet variance and JM distance",
abstract = "This paper develops a new crop mapping method through combined utilization of both time and frequency information based on wavelet variance and Jeffries–Matusita (JM) distance (CIWJ for short). A two-dimensional wavelet spectrum was obtained from datasets of daily continuous vegetation indices through a continuous wavelet transform using the Mexican hat and the Morlet mother wavelets. The time-average wavelet variance (TAWV) and the scale-average wavelet variance (SAWV) were then calculated based on the wavelet spectrum of the Mexican hat and the Morlet wavelet, respectively. The class separability based on the JM distance was evaluated to discriminate the proper period or scale range applied. Finally, a procedure for criteria quantification was developed using the TAWV and SAWV as the major metrics, and the similarity between unclassified pixels and established land use/cover types was calculated. The proposed CIWJ method was applied to the middle Hexi Corridor in northwest China using 250-m 8-day composite moderate-resolution imaging spectroradiometer (MODIS) enhanced vegetation index (EVI) time series datasets in 2012. The CIWJ method was shown to be efficient in crop field mapping, with an overall accuracy of 83.6 {\%} and kappa coefficient of 0.7009, assessed with 30 m Chinese Environmental Disaster Reduction Satellite (HJ-1)-derived data. Compared with methods utilizing information on either frequency or time, the CIWJ method demonstrates tremendous potential for efficient crop mapping and for further applications. This method could be applied to either coarse or high spatial resolution images for agricultural crop identification, as well as other more general or specific land use classifications.",
keywords = "Continuous wavelet transform, Crop mapping, JM distance, SAWV, TAWV",
author = "Bingwen Qiu and Zhanling Fan and Ming Zhong and Zhenghong Tang and Chongcheng Chen",
year = "2014",
month = "10",
day = "3",
doi = "10.1007/s10661-014-3977-1",
language = "English (US)",
volume = "186",
pages = "7929--7940",
journal = "Environmental Monitoring and Assessment",
issn = "0167-6369",
publisher = "Springer Netherlands",
number = "11",

}

TY - JOUR

T1 - A new approach for crop identification with wavelet variance and JM distance

AU - Qiu, Bingwen

AU - Fan, Zhanling

AU - Zhong, Ming

AU - Tang, Zhenghong

AU - Chen, Chongcheng

PY - 2014/10/3

Y1 - 2014/10/3

N2 - This paper develops a new crop mapping method through combined utilization of both time and frequency information based on wavelet variance and Jeffries–Matusita (JM) distance (CIWJ for short). A two-dimensional wavelet spectrum was obtained from datasets of daily continuous vegetation indices through a continuous wavelet transform using the Mexican hat and the Morlet mother wavelets. The time-average wavelet variance (TAWV) and the scale-average wavelet variance (SAWV) were then calculated based on the wavelet spectrum of the Mexican hat and the Morlet wavelet, respectively. The class separability based on the JM distance was evaluated to discriminate the proper period or scale range applied. Finally, a procedure for criteria quantification was developed using the TAWV and SAWV as the major metrics, and the similarity between unclassified pixels and established land use/cover types was calculated. The proposed CIWJ method was applied to the middle Hexi Corridor in northwest China using 250-m 8-day composite moderate-resolution imaging spectroradiometer (MODIS) enhanced vegetation index (EVI) time series datasets in 2012. The CIWJ method was shown to be efficient in crop field mapping, with an overall accuracy of 83.6 % and kappa coefficient of 0.7009, assessed with 30 m Chinese Environmental Disaster Reduction Satellite (HJ-1)-derived data. Compared with methods utilizing information on either frequency or time, the CIWJ method demonstrates tremendous potential for efficient crop mapping and for further applications. This method could be applied to either coarse or high spatial resolution images for agricultural crop identification, as well as other more general or specific land use classifications.

AB - This paper develops a new crop mapping method through combined utilization of both time and frequency information based on wavelet variance and Jeffries–Matusita (JM) distance (CIWJ for short). A two-dimensional wavelet spectrum was obtained from datasets of daily continuous vegetation indices through a continuous wavelet transform using the Mexican hat and the Morlet mother wavelets. The time-average wavelet variance (TAWV) and the scale-average wavelet variance (SAWV) were then calculated based on the wavelet spectrum of the Mexican hat and the Morlet wavelet, respectively. The class separability based on the JM distance was evaluated to discriminate the proper period or scale range applied. Finally, a procedure for criteria quantification was developed using the TAWV and SAWV as the major metrics, and the similarity between unclassified pixels and established land use/cover types was calculated. The proposed CIWJ method was applied to the middle Hexi Corridor in northwest China using 250-m 8-day composite moderate-resolution imaging spectroradiometer (MODIS) enhanced vegetation index (EVI) time series datasets in 2012. The CIWJ method was shown to be efficient in crop field mapping, with an overall accuracy of 83.6 % and kappa coefficient of 0.7009, assessed with 30 m Chinese Environmental Disaster Reduction Satellite (HJ-1)-derived data. Compared with methods utilizing information on either frequency or time, the CIWJ method demonstrates tremendous potential for efficient crop mapping and for further applications. This method could be applied to either coarse or high spatial resolution images for agricultural crop identification, as well as other more general or specific land use classifications.

KW - Continuous wavelet transform

KW - Crop mapping

KW - JM distance

KW - SAWV

KW - TAWV

UR - http://www.scopus.com/inward/record.url?scp=84910009787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84910009787&partnerID=8YFLogxK

U2 - 10.1007/s10661-014-3977-1

DO - 10.1007/s10661-014-3977-1

M3 - Article

VL - 186

SP - 7929

EP - 7940

JO - Environmental Monitoring and Assessment

JF - Environmental Monitoring and Assessment

SN - 0167-6369

IS - 11

ER -