Identification and area estimation of agricultural crops by computer classification of LANDSAT MSS data

Marvin E. Bauer; Jan E. Cipra; Paul E. Anuta; Jeanne B. Etheridge

doi:10.1016/0034-4257(79)90025-7

Identification and area estimation of agricultural crops by computer classification of LANDSAT MSS data

Marvin E. Bauer, Jan E. Cipra, Paul E. Anuta, Jeanne B. Etheridge

Forest Resources

Research output: Contribution to journal › Article › peer-review

32 Scopus citations

Abstract

LANDSAT Multispectral Scanner (MSS) data covering a three-county area in northern Illinois were classified using computer-aided techniques as corn, soybeans, or "other." Recognition of test fields was 80% accurate. County estimates of the area of corn and soybeans agreed closely with those made by the USDA. Results of the use of a priori information in classification, techniques to produce unbiased area estimates, and the use of temporal and spatial features for classification are discussed. The extendability, variability, and size of training sets, wavelength band selection, and spectral characteristics of crops were also investigated.

Original language	English (US)
Pages (from-to)	77-92
Number of pages	16
Journal	Remote Sensing of Environment
Volume	8
Issue number	1
DOIs	https://doi.org/10.1016/0034-4257(79)90025-7
State	Published - Feb 1979

Bibliographical note

Funding Information:
This paper reports on work sponsored by the National Aeronautics and Space Administration, Goddard Space Flight Center, Contract NAS5-21773. Journal Paper No. 7032, Purdue University Agricultural Experiment Station.

Access

10.1016/0034-4257(79)90025-7

OpenUrl availability

Full text

Cite this

@article{b92eb64e20184155ada8fb6a52eab4d5,

title = "Identification and area estimation of agricultural crops by computer classification of LANDSAT MSS data",

abstract = "LANDSAT Multispectral Scanner (MSS) data covering a three-county area in northern Illinois were classified using computer-aided techniques as corn, soybeans, or {"}other.{"} Recognition of test fields was 80% accurate. County estimates of the area of corn and soybeans agreed closely with those made by the USDA. Results of the use of a priori information in classification, techniques to produce unbiased area estimates, and the use of temporal and spatial features for classification are discussed. The extendability, variability, and size of training sets, wavelength band selection, and spectral characteristics of crops were also investigated.",

author = "Bauer, {Marvin E.} and Cipra, {Jan E.} and Anuta, {Paul E.} and Etheridge, {Jeanne B.}",

note = "Funding Information: This paper reports on work sponsored by the National Aeronautics and Space Administration, Goddard Space Flight Center, Contract NAS5-21773. Journal Paper No. 7032, Purdue University Agricultural Experiment Station.",

year = "1979",

month = feb,

doi = "10.1016/0034-4257(79)90025-7",

language = "English (US)",

volume = "8",

pages = "77--92",

journal = "Remote Sensing of Environment",

issn = "0034-4257",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Identification and area estimation of agricultural crops by computer classification of LANDSAT MSS data

AU - Bauer, Marvin E.

AU - Cipra, Jan E.

AU - Anuta, Paul E.

AU - Etheridge, Jeanne B.

N1 - Funding Information: This paper reports on work sponsored by the National Aeronautics and Space Administration, Goddard Space Flight Center, Contract NAS5-21773. Journal Paper No. 7032, Purdue University Agricultural Experiment Station.

PY - 1979/2

Y1 - 1979/2

N2 - LANDSAT Multispectral Scanner (MSS) data covering a three-county area in northern Illinois were classified using computer-aided techniques as corn, soybeans, or "other." Recognition of test fields was 80% accurate. County estimates of the area of corn and soybeans agreed closely with those made by the USDA. Results of the use of a priori information in classification, techniques to produce unbiased area estimates, and the use of temporal and spatial features for classification are discussed. The extendability, variability, and size of training sets, wavelength band selection, and spectral characteristics of crops were also investigated.

AB - LANDSAT Multispectral Scanner (MSS) data covering a three-county area in northern Illinois were classified using computer-aided techniques as corn, soybeans, or "other." Recognition of test fields was 80% accurate. County estimates of the area of corn and soybeans agreed closely with those made by the USDA. Results of the use of a priori information in classification, techniques to produce unbiased area estimates, and the use of temporal and spatial features for classification are discussed. The extendability, variability, and size of training sets, wavelength band selection, and spectral characteristics of crops were also investigated.

UR - http://www.scopus.com/inward/record.url?scp=0018434472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0018434472&partnerID=8YFLogxK

U2 - 10.1016/0034-4257(79)90025-7

DO - 10.1016/0034-4257(79)90025-7

M3 - Article

AN - SCOPUS:0018434472

SN - 0034-4257

VL - 8

SP - 77

EP - 92

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

IS - 1

ER -

Identification and area estimation of agricultural crops by computer classification of LANDSAT MSS data

Abstract

Bibliographical note

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this