Object-Based Time-Constrained Dynamic Time Warping Classification of Crops Using Sentinel-2

Ovidiu Csillik (Corresponding Author), M. Belgiu, Gregory P. Asner, Maggi Kelly

Research output: Contribution to journalArticleAcademicpeer-review

2 Downloads (Pure)

Abstract

The increasing volume of remote sensing data with improved spatial and temporal resolutions generates unique opportunities for monitoring and mapping of crops. We compared multiple single-band and multi-band object-based time-constrained Dynamic Time Warping (DTW) classifications for crop mapping based on Sentinel-2 time series of vegetation indices. We tested it on two complex and intensively managed agricultural areas in California and Texas. DTW is a time-flexible method for comparing two temporal patterns by considering their temporal distortions in their alignment. For crop mapping, using time constraints in computing DTW is recommended in order to consider the seasonality of crops. We tested different time constraints in DTW (15, 30, 45, and 60 days) and compared the results with those obtained by using Euclidean distance or a DTW without time constraint. Best classification results were for time delays of both 30 and 45 days in California: 79.5% for single-band DTWs and 85.6% for multi-band DTWs. In Texas, 45 days was best for single-band DTW (89.1%), while 30 days yielded best results for multi-band DTW (87.6%). Using temporal information from five vegetation indices instead of one increased the overall accuracy in California with 6.1%. We discuss the implications of DTW dissimilarity values in understanding the classification errors. Considering the possible sources of errors and their propagation throughout our analysis, we had combined errors of 22.2% and 16.8% for California and 24.6% and 25.4% for Texas study areas. The proposed workflow is the first implementation of DTW in an object-based image analysis (OBIA) environment and represents a promising step towards generating fast, accurate, and ready-to-use agricultural data products.
Original languageEnglish
Pages (from-to)1-26
Number of pages26
JournalRemote sensing
Volume11
Issue number10
DOIs
Publication statusPublished - 27 May 2019

Fingerprint

crop
vegetation index
image analysis
seasonality
agricultural land
time series
remote sensing
monitoring

Keywords

  • agricultural mapping; DTW; eCognition; land use/land cover mapping; object-based image analysis; satellite image time series
  • ITC-ISI-JOURNAL-ARTICLE
  • ITC-GOLD

Cite this

Csillik, Ovidiu ; Belgiu, M. ; Asner, Gregory P. ; Kelly, Maggi. / Object-Based Time-Constrained Dynamic Time Warping Classification of Crops Using Sentinel-2. In: Remote sensing. 2019 ; Vol. 11, No. 10. pp. 1-26.
@article{cb660361d4bc4e2e8d76a6df65d661ba,
title = "Object-Based Time-Constrained Dynamic Time Warping Classification of Crops Using Sentinel-2",
abstract = "The increasing volume of remote sensing data with improved spatial and temporal resolutions generates unique opportunities for monitoring and mapping of crops. We compared multiple single-band and multi-band object-based time-constrained Dynamic Time Warping (DTW) classifications for crop mapping based on Sentinel-2 time series of vegetation indices. We tested it on two complex and intensively managed agricultural areas in California and Texas. DTW is a time-flexible method for comparing two temporal patterns by considering their temporal distortions in their alignment. For crop mapping, using time constraints in computing DTW is recommended in order to consider the seasonality of crops. We tested different time constraints in DTW (15, 30, 45, and 60 days) and compared the results with those obtained by using Euclidean distance or a DTW without time constraint. Best classification results were for time delays of both 30 and 45 days in California: 79.5{\%} for single-band DTWs and 85.6{\%} for multi-band DTWs. In Texas, 45 days was best for single-band DTW (89.1{\%}), while 30 days yielded best results for multi-band DTW (87.6{\%}). Using temporal information from five vegetation indices instead of one increased the overall accuracy in California with 6.1{\%}. We discuss the implications of DTW dissimilarity values in understanding the classification errors. Considering the possible sources of errors and their propagation throughout our analysis, we had combined errors of 22.2{\%} and 16.8{\%} for California and 24.6{\%} and 25.4{\%} for Texas study areas. The proposed workflow is the first implementation of DTW in an object-based image analysis (OBIA) environment and represents a promising step towards generating fast, accurate, and ready-to-use agricultural data products.",
keywords = "agricultural mapping; DTW; eCognition; land use/land cover mapping; object-based image analysis; satellite image time series, ITC-ISI-JOURNAL-ARTICLE, ITC-GOLD",
author = "Ovidiu Csillik and M. Belgiu and Asner, {Gregory P.} and Maggi Kelly",
year = "2019",
month = "5",
day = "27",
doi = "10.3390/rs11101257",
language = "English",
volume = "11",
pages = "1--26",
journal = "Remote sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "10",

}

Object-Based Time-Constrained Dynamic Time Warping Classification of Crops Using Sentinel-2. / Csillik, Ovidiu (Corresponding Author); Belgiu, M.; Asner, Gregory P.; Kelly, Maggi.

In: Remote sensing, Vol. 11, No. 10, 27.05.2019, p. 1-26.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Object-Based Time-Constrained Dynamic Time Warping Classification of Crops Using Sentinel-2

AU - Csillik, Ovidiu

AU - Belgiu, M.

AU - Asner, Gregory P.

AU - Kelly, Maggi

PY - 2019/5/27

Y1 - 2019/5/27

N2 - The increasing volume of remote sensing data with improved spatial and temporal resolutions generates unique opportunities for monitoring and mapping of crops. We compared multiple single-band and multi-band object-based time-constrained Dynamic Time Warping (DTW) classifications for crop mapping based on Sentinel-2 time series of vegetation indices. We tested it on two complex and intensively managed agricultural areas in California and Texas. DTW is a time-flexible method for comparing two temporal patterns by considering their temporal distortions in their alignment. For crop mapping, using time constraints in computing DTW is recommended in order to consider the seasonality of crops. We tested different time constraints in DTW (15, 30, 45, and 60 days) and compared the results with those obtained by using Euclidean distance or a DTW without time constraint. Best classification results were for time delays of both 30 and 45 days in California: 79.5% for single-band DTWs and 85.6% for multi-band DTWs. In Texas, 45 days was best for single-band DTW (89.1%), while 30 days yielded best results for multi-band DTW (87.6%). Using temporal information from five vegetation indices instead of one increased the overall accuracy in California with 6.1%. We discuss the implications of DTW dissimilarity values in understanding the classification errors. Considering the possible sources of errors and their propagation throughout our analysis, we had combined errors of 22.2% and 16.8% for California and 24.6% and 25.4% for Texas study areas. The proposed workflow is the first implementation of DTW in an object-based image analysis (OBIA) environment and represents a promising step towards generating fast, accurate, and ready-to-use agricultural data products.

AB - The increasing volume of remote sensing data with improved spatial and temporal resolutions generates unique opportunities for monitoring and mapping of crops. We compared multiple single-band and multi-band object-based time-constrained Dynamic Time Warping (DTW) classifications for crop mapping based on Sentinel-2 time series of vegetation indices. We tested it on two complex and intensively managed agricultural areas in California and Texas. DTW is a time-flexible method for comparing two temporal patterns by considering their temporal distortions in their alignment. For crop mapping, using time constraints in computing DTW is recommended in order to consider the seasonality of crops. We tested different time constraints in DTW (15, 30, 45, and 60 days) and compared the results with those obtained by using Euclidean distance or a DTW without time constraint. Best classification results were for time delays of both 30 and 45 days in California: 79.5% for single-band DTWs and 85.6% for multi-band DTWs. In Texas, 45 days was best for single-band DTW (89.1%), while 30 days yielded best results for multi-band DTW (87.6%). Using temporal information from five vegetation indices instead of one increased the overall accuracy in California with 6.1%. We discuss the implications of DTW dissimilarity values in understanding the classification errors. Considering the possible sources of errors and their propagation throughout our analysis, we had combined errors of 22.2% and 16.8% for California and 24.6% and 25.4% for Texas study areas. The proposed workflow is the first implementation of DTW in an object-based image analysis (OBIA) environment and represents a promising step towards generating fast, accurate, and ready-to-use agricultural data products.

KW - agricultural mapping; DTW; eCognition; land use/land cover mapping; object-based image analysis; satellite image time series

KW - ITC-ISI-JOURNAL-ARTICLE

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2019/isi/belgiu_obj.pdf

U2 - 10.3390/rs11101257

DO - 10.3390/rs11101257

M3 - Article

VL - 11

SP - 1

EP - 26

JO - Remote sensing

JF - Remote sensing

SN - 2072-4292

IS - 10

ER -