Object-oriented crop classification using multitemporal ETM plus SLC-off imagery and random forest

被引：81

作者：

Long, John A. ^{[1
]}

Lawrence, Rick L. ^{[1
]}

Greenwood, Mark C. ^{[2
]}

Marshall, Lucy ^{[1
]}

Miller, Perry R. ^{[1
]}

机构：

[1] Montana State Univ, Dept Land Resources & Environm Sci, Bozeman, MT 59715 USA

[2] Montana State Univ, Dept Math Sci, Bozeman, MT 59715 USA

来源：

GISCIENCE & REMOTE SENSING | 2013年 / 50卷 / 04期

关键词：

remote sensing; agriculture; classification; multitemporal; multispectral; object-oriented; random forest; Enhanced Thematic Mapper Plus; Landsat; LAND-USE CLASSIFICATION; TIME-SERIES; FILLING GAPS; SEGMENTATION; REGRESSION;

D O I：

10.1080/15481603.2013.817150

中图分类号：

P9 [自然地理学];

学科分类号：

0705 ; 070501 ;

摘要：

The utility of Enhanced Thematic Mapper Plus (ETM+) has been diminished since the 2003 scan-line corrector (SLC) failure. Uncorrected images have data gaps of approximately 22% and gap-filling schemes have been developed to improve their usability. We present a method to classify a northeast Montana agricultural landscape using ETM+ SLC-off imagery without gap-filling. We use multitemporal data analysis and employ an object-oriented approach to define objects, agricultural fields, with cadastral data. This approach was assessed by comparison to a pixel-based approach. Results indicate that an ETM+ SLC-off image can be classified with better than 85% overall accuracy without gap-filling.

引用

页码：418 / 436

页数：19

共 48 条

[1] Improvements in land use mapping for irrigated agriculture from satellite sensor data using a multi-stage maximum likelihood classification [J].

Abou El-Magd, I ;

Tanton, TW .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (21) :4197-4206

[2] Discriminating the papyrus vegetation (Cyperus papyrus L.) and its co-existent species using random forest and hyperspectral data resampled to HYMAP [J].

Adam, E. M. ;

Mutanga, O. ;

Rugege, D. ;

Ismail, R. .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 2012, 33 (02) :552-569

[3]

[Anonymous], 2009, ASSESSING ACCURACY R

[4] Landsat-7 long-term acquisition plan: Development and validation [J].

Arvidson, Terry ;

Goward, Samuel ;

Gasch, John ;

Williams, Darrel .

PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING, 2006, 72 (10) :1137-1146

[5] Land-use classification of multispectral aerial images using artificial neural networks [J].

Ashish, D. ;

McClendon, R. W. ;

Hoogenboom, G. .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 2009, 30 (08) :1989-2004

[6]

Boloorani A. D., 2008, P SPIE IS T IM PROC

[7] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[8] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[9] Random Forest characterization of upland vegetation and management burning from aerial imagery [J].

Chapman, Daniel S. ;

Bonn, Aletta ;

Kunin, William E. ;

Cornell, Stephen J. .

JOURNAL OF BIOGEOGRAPHY, 2010, 37 (01) :37-46

[10]

Chen F., 2010, P 18 INT C GEOINF

← 1 2 3 4 5 →