Efficiency and accuracy of per-field classification for operational crop mapping

Research output: Contribution to journalArticleAcademicpeer-review

121 Citations (Scopus)

Abstract

A crop map of The Netherlands was created using a methodology that integrates multi-temporal and multi-sensor satellite imagery, statistical data on crop area and parcel boundaries from a 1 : 10 000 digital topographic map. In the first phase a crop field database was created by extracting static parcel boundaries from the digital topographic map and by adding dynamic crop boundaries using on-screen digitizing. In the next phase the crop type was determined from the spectral and phenological properties of each field. The resulting crop map has an accuracy larger than 80% for most individual crops and an overall accuracy of 90%. By comparing cost and man-hours it was demonstrated that per-field classification is more efficient than per-pixel classification and decreased the effort for classification from 1500 to 500 man-hours, but the effort for creating the crop field database was estimated at 2300 man-hours. The use of image segmentation techniques for deriving the crop field database was discussed. It was concluded that image segmentation cannot replace the use of a large-scale topographic map but, in the future, image segmentation may be used to map the dynamic crop boundaries within the topographic parcels.
Original languageEnglish
Pages (from-to)4091-4112
JournalInternational Journal of Remote Sensing
Volume25
Issue number20
DOIs
Publication statusPublished - 2004

Fingerprint

crop
segmentation
satellite imagery
sensor
cost

Keywords

  • land-cover classification
  • image segmentation
  • satellite images
  • integration
  • objects
  • example
  • system

Cite this

@article{9f59410cc5cb48d486b672b1ec1f9a82,
title = "Efficiency and accuracy of per-field classification for operational crop mapping",
abstract = "A crop map of The Netherlands was created using a methodology that integrates multi-temporal and multi-sensor satellite imagery, statistical data on crop area and parcel boundaries from a 1 : 10 000 digital topographic map. In the first phase a crop field database was created by extracting static parcel boundaries from the digital topographic map and by adding dynamic crop boundaries using on-screen digitizing. In the next phase the crop type was determined from the spectral and phenological properties of each field. The resulting crop map has an accuracy larger than 80{\%} for most individual crops and an overall accuracy of 90{\%}. By comparing cost and man-hours it was demonstrated that per-field classification is more efficient than per-pixel classification and decreased the effort for classification from 1500 to 500 man-hours, but the effort for creating the crop field database was estimated at 2300 man-hours. The use of image segmentation techniques for deriving the crop field database was discussed. It was concluded that image segmentation cannot replace the use of a large-scale topographic map but, in the future, image segmentation may be used to map the dynamic crop boundaries within the topographic parcels.",
keywords = "land-cover classification, image segmentation, satellite images, integration, objects, example, system",
author = "{de Wit}, A.J.W. and J.G.P.W. Clevers",
year = "2004",
doi = "10.1080/01431160310001619580",
language = "English",
volume = "25",
pages = "4091--4112",
journal = "International Journal of Remote Sensing",
issn = "0143-1161",
publisher = "Taylor & Francis",
number = "20",

}

Efficiency and accuracy of per-field classification for operational crop mapping. / de Wit, A.J.W.; Clevers, J.G.P.W.

In: International Journal of Remote Sensing, Vol. 25, No. 20, 2004, p. 4091-4112.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Efficiency and accuracy of per-field classification for operational crop mapping

AU - de Wit, A.J.W.

AU - Clevers, J.G.P.W.

PY - 2004

Y1 - 2004

N2 - A crop map of The Netherlands was created using a methodology that integrates multi-temporal and multi-sensor satellite imagery, statistical data on crop area and parcel boundaries from a 1 : 10 000 digital topographic map. In the first phase a crop field database was created by extracting static parcel boundaries from the digital topographic map and by adding dynamic crop boundaries using on-screen digitizing. In the next phase the crop type was determined from the spectral and phenological properties of each field. The resulting crop map has an accuracy larger than 80% for most individual crops and an overall accuracy of 90%. By comparing cost and man-hours it was demonstrated that per-field classification is more efficient than per-pixel classification and decreased the effort for classification from 1500 to 500 man-hours, but the effort for creating the crop field database was estimated at 2300 man-hours. The use of image segmentation techniques for deriving the crop field database was discussed. It was concluded that image segmentation cannot replace the use of a large-scale topographic map but, in the future, image segmentation may be used to map the dynamic crop boundaries within the topographic parcels.

AB - A crop map of The Netherlands was created using a methodology that integrates multi-temporal and multi-sensor satellite imagery, statistical data on crop area and parcel boundaries from a 1 : 10 000 digital topographic map. In the first phase a crop field database was created by extracting static parcel boundaries from the digital topographic map and by adding dynamic crop boundaries using on-screen digitizing. In the next phase the crop type was determined from the spectral and phenological properties of each field. The resulting crop map has an accuracy larger than 80% for most individual crops and an overall accuracy of 90%. By comparing cost and man-hours it was demonstrated that per-field classification is more efficient than per-pixel classification and decreased the effort for classification from 1500 to 500 man-hours, but the effort for creating the crop field database was estimated at 2300 man-hours. The use of image segmentation techniques for deriving the crop field database was discussed. It was concluded that image segmentation cannot replace the use of a large-scale topographic map but, in the future, image segmentation may be used to map the dynamic crop boundaries within the topographic parcels.

KW - land-cover classification

KW - image segmentation

KW - satellite images

KW - integration

KW - objects

KW - example

KW - system

U2 - 10.1080/01431160310001619580

DO - 10.1080/01431160310001619580

M3 - Article

VL - 25

SP - 4091

EP - 4112

JO - International Journal of Remote Sensing

JF - International Journal of Remote Sensing

SN - 0143-1161

IS - 20

ER -