2017
DOI: 10.1109/mgrs.2016.2641240
|View full text |Cite
|
Sign up to set email alerts
|

Remote Sensing Image Classification: A survey of support-vector-machine-based advanced techniques

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

1
83
0
2

Year Published

2017
2017
2024
2024

Publication Types

Select...
5
2
2

Relationship

0
9

Authors

Journals

citations
Cited by 171 publications
(86 citation statements)
references
References 110 publications
1
83
0
2
Order By: Relevance
“…Methods Thomas et al, 2003Lu et al, 2004Ma et al, 2017Maulik and Chakraborty, 2017Guisan and Thuiller, 2005Elith and Leathwick, 2009Franklin, 2010Li and Wang, 2013Morris et al, 2016Ashraf et al, 2017de Rivera and López-Quílez, 2017 can be approached from two perspectives: the data collection methods and the map production methods. Developments in data collection techniques in the last few decades have increased the types, amount and quality of data that can be collected for marine environmental characterization, particularly in terms of remotely sensed data (Brown et al, 2011;Kachelriess et al, 2014;Lecours et al, 2016b).…”
Section: Marine Habitat Mappingmentioning
confidence: 99%
“…Methods Thomas et al, 2003Lu et al, 2004Ma et al, 2017Maulik and Chakraborty, 2017Guisan and Thuiller, 2005Elith and Leathwick, 2009Franklin, 2010Li and Wang, 2013Morris et al, 2016Ashraf et al, 2017de Rivera and López-Quílez, 2017 can be approached from two perspectives: the data collection methods and the map production methods. Developments in data collection techniques in the last few decades have increased the types, amount and quality of data that can be collected for marine environmental characterization, particularly in terms of remotely sensed data (Brown et al, 2011;Kachelriess et al, 2014;Lecours et al, 2016b).…”
Section: Marine Habitat Mappingmentioning
confidence: 99%
“…They concluded that SVM-based classification methods perform better in terms of accuracy, speed, and memory requirements, and can operate effectively and accurately in cases where training samples are limited, which is generally the case for satellite image classification problems. They also noted the constraints that should be considered in SVM, such as the need to appropriately define the kernel function, the representation efficiency of the training sample, and the consistency of statistical distributions between classes [19].In most satellite image classification scenarios, higher accuracies (over 85%) are attained when the major land cover (LC) classes, such as vegetation, water, and urban classes are the concern [20,21]. Achieving high accuracies becomes challenging when the higher-level class definitions are the concern, due to the spectral and spatial similarities [22].…”
mentioning
confidence: 99%
“…They concluded that SVM-based classification methods perform better in terms of accuracy, speed, and memory requirements, and can operate effectively and accurately in cases where training samples are limited, which is generally the case for satellite image classification problems. They also noted the constraints that should be considered in SVM, such as the need to appropriately define the kernel function, the representation efficiency of the training sample, and the consistency of statistical distributions between classes [19].…”
mentioning
confidence: 99%
“…Найбільш поширеними методами машинного навчання для задач кла-сифікації [7] є штучні нейронні мережі (artificial neural network) [1], логісти-чна регресія [1], метод опорних векторів Support Vector Machine (SVM) [1] та random forest [8].…”
Section: т а б л и ц я 1 різновидності підходів до класифікації залunclassified