LAND-COVER DISCRIMINATION IN SPOT HRV IMAGERY USING AN ARTIFICIAL NEURAL NETWORK - A 20-CLASS EXPERIMENT

被引：91

作者：

KANELLOPOULOS, I

VARFIS, A

WILKINSON, GG

MEGIER, J

机构：

[1] Commission of the European Communities, Joint Research Centre, Ispra, Varese

来源：

INTERNATIONAL JOURNAL OF REMOTE SENSING | 1992年 / 13卷 / 05期

关键词：

D O I：

10.1080/01431169208904164

中图分类号：

TP7 [遥感技术];

学科分类号：

081102 ; 0816 ; 081602 ; 083002 ; 1404 ;

摘要：

An artificial neural network based on the multilayer-perceptron model has been used to classify two-date multispectral SPOT High Resolution Visible (HRV) imagery on a test site in the Departement Ardeche, France. A large network consisting of 98 nodes was trained successfully to classify 20 land-cover classes. A ground dataset comprising 1881 pixels was used to verify the accuracy of the classifier. The average accuracy achieved over all classes in the verification dataset was 81 per cent, exceeding the performance of a maximum-likelihood classifier by 28 per cent.

引用

页码：917 / 924

页数：8

共 12 条

[1] NEURAL NETWORK APPROACHES VERSUS STATISTICAL-METHODS IN CLASSIFICATION OF MULTISOURCE REMOTE-SENSING DATA
BENEDIKTSSON, JA
SWAIN, PH
ERSOY, OK
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1990, 28 (04): : 540 - 552
[2] DECATUR SE, 1989, P INT JOINT C NEUR N, V1, P283
[3] ERSOY OK, 1989, P INT JOINT C NEURAL, V2, P624
[4] HEPNER GF, 1990, PHOTOGRAMM ENG REM S, V56, P469
[5] HOWALD KJ, 1989, 1989 ASPRS ACSM FALL, P207
[6] KEY J, 1989, PHOTOGRAMM ENG REM S, V55, P1331
[7] A NEURAL NETWORK APPROACH TO CLOUD CLASSIFICATION
LEE, J
WEGER, RC
SENGUPTA, SK
WELCH, RM
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1990, 28 (05): : 846 - 855
[8] LIPPMANN RP, 1987, IEEE ASSP MAGAZINE, V2, P4
[9] MCCLELLAND GE, 1989, P INT JOINT C NEUR N, V1, P151
[10] Rumelhart DE, 1986, ENCY DATABASE SYST, P45

← 1 2 →