東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

A comparison of pixel based and obje...

Florida Atlantic University.

Linked to FindBook

Google Book

Amazon

博客來

A comparison of pixel based and object based vegetation community classification in the Arthur R. Marshall Loxahatchee National Wildlife Refuge.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	A comparison of pixel based and object based vegetation community classification in the Arthur R. Marshall Loxahatchee National Wildlife Refuge./
Author:	Barone, Dorianne M.
Description:	74 p.
Notes:	Adviser: Charles Roberts.
Contained By:	Masters Abstracts International46-05.
Subject:	Physical Geography. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1452448
ISBN:	9780549496489

A comparison of pixel based and object based vegetation community classification in the Arthur R. Marshall Loxahatchee National Wildlife Refuge.
Barone, Dorianne M.

A comparison of pixel based and object based vegetation community classification in the Arthur R. Marshall Loxahatchee National Wildlife Refuge. - 74 p.

Adviser: Charles Roberts.

Thesis (M.S.)--Florida Atlantic University, 2008.

Pixel based and object based vegetation community classification methods were performed using 30 meter spatial resolution Landsat satellite imagery of the Arthur R. Marshall Loxahatchee National Wildlife Refuge (Refuge), a remnant of the northern Everglades. Supervised classification procedures using maximum likelihood and parallelepiped algorithms were used to produce thematic maps with the following vegetation communities: wet prairie, sawgrass, cattail, tree island, brush, aquatic/open water. Spectral data, as well as NDVI, texture and principal component data were used to produce vegetation community classification maps. The accuracy levels of the thematic maps produced were calculated and compared to one another. The pixel based approach using the parallelepiped classification algorithm on the spectral and NDVI dataset had the highest accuracy level. A generalized form of this classification using only three vegetation communities (all wet prairie, tree island/brush and aquatic/open water) was compared to a previously published classification which used 1987 SPOT imagery in order to extract information on possible vegetation community transitions that are occurring within the Refuge. Results of the study indicate that 30 meter spatial resolution may be useful for understanding broad vegetation community trends but not species level trends. Pixel based procedures provide a more accurate classification than object based procedures for this landscape when using 30 meter imagery. Lastly, since 1987 there may be a trend of tree island/brush communities replacing wet prairie communities in the northern part of the Refuge and a transition to wet prairie communities in place of tree island/brush communities in the southern portion of the Refuge.

ISBN: 9780549496489Subjects--Topical Terms:

893400
Physical Geography.

A comparison of pixel based and object based vegetation community classification in the Arthur R. Marshall Loxahatchee National Wildlife Refuge.
LDR:02699nam 2200277 a 45 001 856244
005 20100708
008 100708s2008 eng d
020 $a 9780549496489
035 $a (UMI)AAI1452448
035 $a AAI1452448
040 $a UMI $c UMI
100 1 $a Barone, Dorianne M. $3 1023027
245 1 2 $a A comparison of pixel based and object based vegetation community classification in the Arthur R. Marshall Loxahatchee National Wildlife Refuge.
300 $a 74 p.
500 $a Adviser: Charles Roberts.
500 $a Source: Masters Abstracts International, Volume: 46-05, page: 2618.
502 $a Thesis (M.S.)--Florida Atlantic University, 2008.
520 $a Pixel based and object based vegetation community classification methods were performed using 30 meter spatial resolution Landsat satellite imagery of the Arthur R. Marshall Loxahatchee National Wildlife Refuge (Refuge), a remnant of the northern Everglades. Supervised classification procedures using maximum likelihood and parallelepiped algorithms were used to produce thematic maps with the following vegetation communities: wet prairie, sawgrass, cattail, tree island, brush, aquatic/open water. Spectral data, as well as NDVI, texture and principal component data were used to produce vegetation community classification maps. The accuracy levels of the thematic maps produced were calculated and compared to one another. The pixel based approach using the parallelepiped classification algorithm on the spectral and NDVI dataset had the highest accuracy level. A generalized form of this classification using only three vegetation communities (all wet prairie, tree island/brush and aquatic/open water) was compared to a previously published classification which used 1987 SPOT imagery in order to extract information on possible vegetation community transitions that are occurring within the Refuge. Results of the study indicate that 30 meter spatial resolution may be useful for understanding broad vegetation community trends but not species level trends. Pixel based procedures provide a more accurate classification than object based procedures for this landscape when using 30 meter imagery. Lastly, since 1987 there may be a trend of tree island/brush communities replacing wet prairie communities in the northern part of the Refuge and a transition to wet prairie communities in place of tree island/brush communities in the southern portion of the Refuge.
590 $a School code: 0119.
650 4 $a Physical Geography. $3 893400
650 4 $a Remote Sensing. $3 1018559
690 $a 0368
690 $a 0799
710 2 0 $a Florida Atlantic University. $3 1017837
773 0 $t Masters Abstracts International $g 46-05.
790 $a 0119
790 1 0 $a Roberts, Charles, $e advisor
791 $a M.S.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1452448