2012
DOI: 10.5194/isprsarchives-xxxix-b7-421-2012
|View full text |Cite
|
Sign up to set email alerts
|

Large Area Land Cover Classification With Landsat Etm+ Images Based on Decision Tree

Abstract: Commission VII, WG VII/6: Remote Sensing Data Fusion KEY WORDS: land cover classification, decision tree, C5.0, MLC ABSTRACT:Traditional land classification techniques for large areas that use LANDSAT TM imagery are typically limited to the fixed spatial resolution of the sensors. For modeling habitat characteristics is often difficult when a study area is large and diverse and complete sampling of environmental variables is unrealistic. We also did some researches on this field, in this paper we firstly intro… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
7
0
1

Year Published

2014
2014
2023
2023

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(8 citation statements)
references
References 13 publications
(10 reference statements)
0
7
0
1
Order By: Relevance
“…Researchers have attempted to solve problems associated with classification of multispectral imagery by utilizing Neural networks (e.g. Basse, Omrani, Charif, Gerber, & B odis, 2014;Joshi, Leeuw, Skidmore, Duren, & van Oosten, 2006), Evidential reasoning (Franklin, Peddle, Dechka, & Stenhouse, 2002), Decision trees (Zhai, Sun, Sang, Yang, & Jia, 2012) and expert systems (Smirnov, Levashova, & Shilov, 2015;Weng, 2011), markov random (Li, 2009), hybrid classifier (Were et al, 2013), integration of GIS or other ancillary data (Rozenstein & Karnieli, 2011), image fusion (Ehlers, Klonus, JohanÅstrand, & Rosso, 2010) thereby integrating multisource information in the classification. Lu and Weng (2007) discussed in detail several issues affecting the success of a classification among them: the selected remote sensing data, image processing, classification procedure and complexity of the landscape.…”
Section: Application Of Digital Image Processing In Lulc Classificationmentioning
confidence: 99%
“…Researchers have attempted to solve problems associated with classification of multispectral imagery by utilizing Neural networks (e.g. Basse, Omrani, Charif, Gerber, & B odis, 2014;Joshi, Leeuw, Skidmore, Duren, & van Oosten, 2006), Evidential reasoning (Franklin, Peddle, Dechka, & Stenhouse, 2002), Decision trees (Zhai, Sun, Sang, Yang, & Jia, 2012) and expert systems (Smirnov, Levashova, & Shilov, 2015;Weng, 2011), markov random (Li, 2009), hybrid classifier (Were et al, 2013), integration of GIS or other ancillary data (Rozenstein & Karnieli, 2011), image fusion (Ehlers, Klonus, JohanÅstrand, & Rosso, 2010) thereby integrating multisource information in the classification. Lu and Weng (2007) discussed in detail several issues affecting the success of a classification among them: the selected remote sensing data, image processing, classification procedure and complexity of the landscape.…”
Section: Application Of Digital Image Processing In Lulc Classificationmentioning
confidence: 99%
“…To construct decision trees with C5.0, the selection of a certain number of training samples is very important, and according to Zhia et al [52] it is more vital to have a representative set of samples than a large number of samples. As the focus of the classification is to distinguish between grasslands and nongrasslands, a minimum of 200 sample objects per WU belonging to both classes were selected manually.…”
Section: G Classificationmentioning
confidence: 99%
“…Ltd., NSW, Australia) was used to create a decision tree and to deduce a set of decision rules from training data, based on the concept of information entropy [45]. The C5.0 algorithm has already been successfully applied to a wide range of land cover classification and crop identification problems [48]- [52]. C5.0 uses the information gain ratio to estimate the splits at each internal node of the tree and to select the features that form the classifier [47].…”
Section: G Classificationmentioning
confidence: 99%
“…The decision tree method is very popular in land cover classifications thanks to its flexibility, simplicity and ease of interpretation (Brown de Colstoun et al, 2003). The accuracies obtained through decision trees are also similar to or better than other classification methods (Brown de Colstoun et al, 2003;Zhai et al, 2012).…”
Section: Introductionmentioning
confidence: 96%
“…They achieved an overall accuracy (OC) of 80.0%, but noted that certain classes had been hardcoded by the expert system, resulting in 100% accuracy for those classes. Zhai et al, (2012) used the C5.0 decision tree algorithm to classify 18 Landsat Enhanced Thematic Mapper (ETM) scenes, having used only a few of the scenes to develop rules. Using spectral data from one season, as well as normalised difference vegetation index (NDVI) and tasseled cap components, an accuracy of 78.87% was achieved.…”
Section: Introductionmentioning
confidence: 99%