Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area

碩士 === 國立屏東科技大學 === 土木工程系碩士班 === 92 === Recently, as the widespread applications of remote sensing technique, the imagery of the satellite has the advantages of short revisiting cycle, comprehending the rapid change of land surface in large area, and the ability of observing by multi-spectral bands....

Full description

Bibliographic Details
Main Authors: Yan-Kai Fang, 方彥凱
Other Authors: Jen-Hwua Chen
Format: Others
Language:zh-TW
Published: 2004
Online Access:http://ndltd.ncl.edu.tw/handle/41598734829519254361
id ndltd-TW-092NPUST015013
record_format oai_dc
spelling ndltd-TW-092NPUST0150132016-12-22T04:11:29Z http://ndltd.ncl.edu.tw/handle/41598734829519254361 Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area 常態化植生指數標準差於土地利用分類之應用─以美濃中壇為例 Yan-Kai Fang 方彥凱 碩士 國立屏東科技大學 土木工程系碩士班 92 Recently, as the widespread applications of remote sensing technique, the imagery of the satellite has the advantages of short revisiting cycle, comprehending the rapid change of land surface in large area, and the ability of observing by multi-spectral bands. Contrast to traditional ground survey methods which are difficult and time consuming; it is more efficient to acquire land use information precisely by using remote sensing technology. The study area is located in Zhangtan workstation of Meinung area in this research. Utilizing the characteristics of different vegetation reflective spectrum, the Normalized Difference Vegetation Index (NDVI) was used to improve the classification accuracy. According to the standard spectrum of the vegetation, there are two peak values located in the near infrared and the short-wave infrared bands of SPOT 4 satellite. Those two bands were applied to the NDVI and compared their contribution in the classification accuracy in two rice growing periods. Results indicated that the classification accuracy of the short-wave infrared NDVI is better than that of near infrared. The User’s Accuracy of the paddy classification is 85.71 % using the short-wave NDVI in the image of Feb. 27, 2003. The Overall Classification Accuracy is 82.49%, and the Kappa Statistics is 0.7836. The User’s Accuracy of the paddy is 87.10 % using the short-wave NDVI in the image of Jul. 19, 2003. The Overall Classification Accuracy is 77.54%, and the Kappa Statistics is 0.7216. The spectrum values in the training area were exported to investigate the relation of each band in the classification. The result shows that short-wave NDVI is less dependent than other bands in the classification. In other words, the short-wave NDVI is a better band to be used in classification. Jen-Hwua Chen 陳鈞華 2004 學位論文 ; thesis 77 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立屏東科技大學 === 土木工程系碩士班 === 92 === Recently, as the widespread applications of remote sensing technique, the imagery of the satellite has the advantages of short revisiting cycle, comprehending the rapid change of land surface in large area, and the ability of observing by multi-spectral bands. Contrast to traditional ground survey methods which are difficult and time consuming; it is more efficient to acquire land use information precisely by using remote sensing technology. The study area is located in Zhangtan workstation of Meinung area in this research. Utilizing the characteristics of different vegetation reflective spectrum, the Normalized Difference Vegetation Index (NDVI) was used to improve the classification accuracy. According to the standard spectrum of the vegetation, there are two peak values located in the near infrared and the short-wave infrared bands of SPOT 4 satellite. Those two bands were applied to the NDVI and compared their contribution in the classification accuracy in two rice growing periods. Results indicated that the classification accuracy of the short-wave infrared NDVI is better than that of near infrared. The User’s Accuracy of the paddy classification is 85.71 % using the short-wave NDVI in the image of Feb. 27, 2003. The Overall Classification Accuracy is 82.49%, and the Kappa Statistics is 0.7836. The User’s Accuracy of the paddy is 87.10 % using the short-wave NDVI in the image of Jul. 19, 2003. The Overall Classification Accuracy is 77.54%, and the Kappa Statistics is 0.7216. The spectrum values in the training area were exported to investigate the relation of each band in the classification. The result shows that short-wave NDVI is less dependent than other bands in the classification. In other words, the short-wave NDVI is a better band to be used in classification.
author2 Jen-Hwua Chen
author_facet Jen-Hwua Chen
Yan-Kai Fang
方彥凱
author Yan-Kai Fang
方彥凱
spellingShingle Yan-Kai Fang
方彥凱
Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area
author_sort Yan-Kai Fang
title Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area
title_short Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area
title_full Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area
title_fullStr Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area
title_full_unstemmed Application on Land Cover Classification Using Normalized Difference Vegetation Indices ―A Case Study at Meinung Zhangtan Area
title_sort application on land cover classification using normalized difference vegetation indices ―a case study at meinung zhangtan area
publishDate 2004
url http://ndltd.ncl.edu.tw/handle/41598734829519254361
work_keys_str_mv AT yankaifang applicationonlandcoverclassificationusingnormalizeddifferencevegetationindicesacasestudyatmeinungzhangtanarea
AT fāngyànkǎi applicationonlandcoverclassificationusingnormalizeddifferencevegetationindicesacasestudyatmeinungzhangtanarea
AT yankaifang chángtàihuàzhíshēngzhǐshùbiāozhǔnchàyútǔdelìyòngfēnlèizhīyīngyòngyǐměinóngzhōngtánwèilì
AT fāngyànkǎi chángtàihuàzhíshēngzhǐshùbiāozhǔnchàyútǔdelìyòngfēnlèizhīyīngyòngyǐměinóngzhōngtánwèilì
_version_ 1718401542715867136