Cloud detection of optical satellite images using support vector machine

Kuan Yi Lee, Chao Hung Lin

研究成果: Conference article

6 引文 (Scopus)

摘要

Cloud covers are generally present in optical remote-sensing images, which limit the usage of acquired images and increase the difficulty of data analysis, such as image compositing, correction of atmosphere effects, calculations of vegetation induces, land cover classification, and land cover change detection. In previous studies, thresholding is a common and useful method in cloud detection. However, a selected threshold is usually suitable for certain cases or local study areas, and it may be failed in other cases. In other words, thresholding-based methods are data-sensitive. Besides, there are many exceptions to control, and the environment is changed dynamically. Using the same threshold value on various data is not effective. In this study, a threshold-free method based on Support Vector Machine (SVM) is proposed, which can avoid the abovementioned problems. A statistical model is adopted to detect clouds instead of a subjective thresholding-based method, which is the main idea of this study. The features used in a classifier is the key to a successful classification. As a result, Automatic Cloud Cover Assessment (AC CA) algorithm, which is based on physical characteristics of clouds, is used to distinguish the clouds and other objects. In the same way, the algorithm called Fmask (Zhu et al, 2012) uses a lot of thresholds and criteria to screen clouds, cloud shadows, and snow. Therefore, the algorithm of feature extraction is based on the ACCA algorithm and Fmask. Spatial and temporal information are also important for satellite images. Consequently, co-occurrence matrix and temporal variance with uniformity of the major principal axis are used in proposed method. We aim to classify images into three groups: cloud, non-cloud and the others. In experiments, images acquired by the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and images containing the landscapes of agriculture, snow area, and island are tested. Experiment results demonstrate the detection accuracy of the proposed method is better than related methods.

指紋

Support vector machines
Satellites
Snow
cloud cover
land cover
Agriculture
snow
Feature extraction
Remote sensing
Classifiers
Experiments
experiment
method
satellite image
support vector machine
detection
Landsat
data analysis
agriculture
remote sensing

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Geography, Planning and Development

引用此文

@article{1dd975949269431181e4da6bf0bf2dbb,
title = "Cloud detection of optical satellite images using support vector machine",
abstract = "Cloud covers are generally present in optical remote-sensing images, which limit the usage of acquired images and increase the difficulty of data analysis, such as image compositing, correction of atmosphere effects, calculations of vegetation induces, land cover classification, and land cover change detection. In previous studies, thresholding is a common and useful method in cloud detection. However, a selected threshold is usually suitable for certain cases or local study areas, and it may be failed in other cases. In other words, thresholding-based methods are data-sensitive. Besides, there are many exceptions to control, and the environment is changed dynamically. Using the same threshold value on various data is not effective. In this study, a threshold-free method based on Support Vector Machine (SVM) is proposed, which can avoid the abovementioned problems. A statistical model is adopted to detect clouds instead of a subjective thresholding-based method, which is the main idea of this study. The features used in a classifier is the key to a successful classification. As a result, Automatic Cloud Cover Assessment (AC CA) algorithm, which is based on physical characteristics of clouds, is used to distinguish the clouds and other objects. In the same way, the algorithm called Fmask (Zhu et al, 2012) uses a lot of thresholds and criteria to screen clouds, cloud shadows, and snow. Therefore, the algorithm of feature extraction is based on the ACCA algorithm and Fmask. Spatial and temporal information are also important for satellite images. Consequently, co-occurrence matrix and temporal variance with uniformity of the major principal axis are used in proposed method. We aim to classify images into three groups: cloud, non-cloud and the others. In experiments, images acquired by the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and images containing the landscapes of agriculture, snow area, and island are tested. Experiment results demonstrate the detection accuracy of the proposed method is better than related methods.",
author = "Lee, {Kuan Yi} and Lin, {Chao Hung}",
year = "2016",
month = "1",
day = "1",
doi = "10.5194/isprsarchives-XLI-B7-289-2016",
language = "English",
volume = "41",
pages = "289--293",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
issn = "1682-1750",

}

TY - JOUR

T1 - Cloud detection of optical satellite images using support vector machine

AU - Lee, Kuan Yi

AU - Lin, Chao Hung

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Cloud covers are generally present in optical remote-sensing images, which limit the usage of acquired images and increase the difficulty of data analysis, such as image compositing, correction of atmosphere effects, calculations of vegetation induces, land cover classification, and land cover change detection. In previous studies, thresholding is a common and useful method in cloud detection. However, a selected threshold is usually suitable for certain cases or local study areas, and it may be failed in other cases. In other words, thresholding-based methods are data-sensitive. Besides, there are many exceptions to control, and the environment is changed dynamically. Using the same threshold value on various data is not effective. In this study, a threshold-free method based on Support Vector Machine (SVM) is proposed, which can avoid the abovementioned problems. A statistical model is adopted to detect clouds instead of a subjective thresholding-based method, which is the main idea of this study. The features used in a classifier is the key to a successful classification. As a result, Automatic Cloud Cover Assessment (AC CA) algorithm, which is based on physical characteristics of clouds, is used to distinguish the clouds and other objects. In the same way, the algorithm called Fmask (Zhu et al, 2012) uses a lot of thresholds and criteria to screen clouds, cloud shadows, and snow. Therefore, the algorithm of feature extraction is based on the ACCA algorithm and Fmask. Spatial and temporal information are also important for satellite images. Consequently, co-occurrence matrix and temporal variance with uniformity of the major principal axis are used in proposed method. We aim to classify images into three groups: cloud, non-cloud and the others. In experiments, images acquired by the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and images containing the landscapes of agriculture, snow area, and island are tested. Experiment results demonstrate the detection accuracy of the proposed method is better than related methods.

AB - Cloud covers are generally present in optical remote-sensing images, which limit the usage of acquired images and increase the difficulty of data analysis, such as image compositing, correction of atmosphere effects, calculations of vegetation induces, land cover classification, and land cover change detection. In previous studies, thresholding is a common and useful method in cloud detection. However, a selected threshold is usually suitable for certain cases or local study areas, and it may be failed in other cases. In other words, thresholding-based methods are data-sensitive. Besides, there are many exceptions to control, and the environment is changed dynamically. Using the same threshold value on various data is not effective. In this study, a threshold-free method based on Support Vector Machine (SVM) is proposed, which can avoid the abovementioned problems. A statistical model is adopted to detect clouds instead of a subjective thresholding-based method, which is the main idea of this study. The features used in a classifier is the key to a successful classification. As a result, Automatic Cloud Cover Assessment (AC CA) algorithm, which is based on physical characteristics of clouds, is used to distinguish the clouds and other objects. In the same way, the algorithm called Fmask (Zhu et al, 2012) uses a lot of thresholds and criteria to screen clouds, cloud shadows, and snow. Therefore, the algorithm of feature extraction is based on the ACCA algorithm and Fmask. Spatial and temporal information are also important for satellite images. Consequently, co-occurrence matrix and temporal variance with uniformity of the major principal axis are used in proposed method. We aim to classify images into three groups: cloud, non-cloud and the others. In experiments, images acquired by the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and images containing the landscapes of agriculture, snow area, and island are tested. Experiment results demonstrate the detection accuracy of the proposed method is better than related methods.

UR - http://www.scopus.com/inward/record.url?scp=84979619286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979619286&partnerID=8YFLogxK

U2 - 10.5194/isprsarchives-XLI-B7-289-2016

DO - 10.5194/isprsarchives-XLI-B7-289-2016

M3 - Conference article

AN - SCOPUS:84979619286

VL - 41

SP - 289

EP - 293

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

ER -