Automatic Cloud and Shadow Detection in Optical Satellite Imagery Without Using Thermal Bands-Application to Suomi NPP VIIRS Images over Fennoscandia

    Research output: Contribution to journalArticleScientificpeer-review

    6 Citations (Scopus)

    Abstract

    In land monitoring applications, clouds and shadows are considered noise that should be removed as automatically and quickly as possible, before further analysis. This paper presents a method to detect clouds and shadows in Suomi NPP satellite's VIIRS (Visible Infrared Imaging Radiometer Suite) satellite images. The proposed cloud and shadow detection method has two distinct features when compared to many other methods. First, the method does not use the thermal bands and can thus be applied to other sensors which do not contain thermal channels, such as Sentinel-2 data. Secondly, the method uses the ratio between blue and green reflectance to detect shadows. Seven hundred and forty-seven VIIRS images over Fennoscandia from August 2014 to April 2016 were processed to train and develop the method. Twenty four points from every tenth of the images were used in accuracy assessment. These 1752 points were interpreted visually to cloud, cloud shadow and clear classes, then compared to the output of the cloud and shadow detection. The comparison on VIIRS images showed 94.2% correct detection rates and 11.1% false alarms for clouds, and respectively 36.1% and 82.7% for shadows. The results on cloud detection were similar to state-of-the-art methods. Shadows showed correctly on the northern edge of the clouds, but many shadows were wrongly assigned to other classes in some cases (e.g., to water class on lake and forest boundary, or with shadows over cloud). This may be due to the low spatial resolution of VIIRS images, where shadows are only a few pixels wide and contain lots of mixed pixels.
    Original languageEnglish
    Article number806
    JournalRemote Sensing
    Volume9
    Issue number8
    DOIs
    Publication statusPublished - 2017
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    satellite imagery
    pixel
    VIIRS
    Suomi NPP
    detection
    accuracy assessment
    detection method
    train
    method
    reflectance
    spatial resolution
    sensor
    lake
    monitoring

    Keywords

    • cloud and shadow masking
    • optical satellite images
    • Suomi NPP VIIRS
    • Sentinel-2
    • surface reflectance
    • rule-based classification

    Cite this

    @article{cc51ab93e5974e74bfb85efb095022c0,
    title = "Automatic Cloud and Shadow Detection in Optical Satellite Imagery Without Using Thermal Bands-Application to Suomi NPP VIIRS Images over Fennoscandia",
    abstract = "In land monitoring applications, clouds and shadows are considered noise that should be removed as automatically and quickly as possible, before further analysis. This paper presents a method to detect clouds and shadows in Suomi NPP satellite's VIIRS (Visible Infrared Imaging Radiometer Suite) satellite images. The proposed cloud and shadow detection method has two distinct features when compared to many other methods. First, the method does not use the thermal bands and can thus be applied to other sensors which do not contain thermal channels, such as Sentinel-2 data. Secondly, the method uses the ratio between blue and green reflectance to detect shadows. Seven hundred and forty-seven VIIRS images over Fennoscandia from August 2014 to April 2016 were processed to train and develop the method. Twenty four points from every tenth of the images were used in accuracy assessment. These 1752 points were interpreted visually to cloud, cloud shadow and clear classes, then compared to the output of the cloud and shadow detection. The comparison on VIIRS images showed 94.2{\%} correct detection rates and 11.1{\%} false alarms for clouds, and respectively 36.1{\%} and 82.7{\%} for shadows. The results on cloud detection were similar to state-of-the-art methods. Shadows showed correctly on the northern edge of the clouds, but many shadows were wrongly assigned to other classes in some cases (e.g., to water class on lake and forest boundary, or with shadows over cloud). This may be due to the low spatial resolution of VIIRS images, where shadows are only a few pixels wide and contain lots of mixed pixels.",
    keywords = "cloud and shadow masking, optical satellite images, Suomi NPP VIIRS, Sentinel-2, surface reflectance, rule-based classification",
    author = "Eija Parmes and Yrj{\"o} Rauste and Matthieu Molinier and Kaj Andersson and Lauri Seitsonen",
    year = "2017",
    doi = "10.3390/rs9080806",
    language = "English",
    volume = "9",
    journal = "Remote Sensing",
    issn = "2072-4292",
    publisher = "MDPI",
    number = "8",

    }

    TY - JOUR

    T1 - Automatic Cloud and Shadow Detection in Optical Satellite Imagery Without Using Thermal Bands-Application to Suomi NPP VIIRS Images over Fennoscandia

    AU - Parmes, Eija

    AU - Rauste, Yrjö

    AU - Molinier, Matthieu

    AU - Andersson, Kaj

    AU - Seitsonen, Lauri

    PY - 2017

    Y1 - 2017

    N2 - In land monitoring applications, clouds and shadows are considered noise that should be removed as automatically and quickly as possible, before further analysis. This paper presents a method to detect clouds and shadows in Suomi NPP satellite's VIIRS (Visible Infrared Imaging Radiometer Suite) satellite images. The proposed cloud and shadow detection method has two distinct features when compared to many other methods. First, the method does not use the thermal bands and can thus be applied to other sensors which do not contain thermal channels, such as Sentinel-2 data. Secondly, the method uses the ratio between blue and green reflectance to detect shadows. Seven hundred and forty-seven VIIRS images over Fennoscandia from August 2014 to April 2016 were processed to train and develop the method. Twenty four points from every tenth of the images were used in accuracy assessment. These 1752 points were interpreted visually to cloud, cloud shadow and clear classes, then compared to the output of the cloud and shadow detection. The comparison on VIIRS images showed 94.2% correct detection rates and 11.1% false alarms for clouds, and respectively 36.1% and 82.7% for shadows. The results on cloud detection were similar to state-of-the-art methods. Shadows showed correctly on the northern edge of the clouds, but many shadows were wrongly assigned to other classes in some cases (e.g., to water class on lake and forest boundary, or with shadows over cloud). This may be due to the low spatial resolution of VIIRS images, where shadows are only a few pixels wide and contain lots of mixed pixels.

    AB - In land monitoring applications, clouds and shadows are considered noise that should be removed as automatically and quickly as possible, before further analysis. This paper presents a method to detect clouds and shadows in Suomi NPP satellite's VIIRS (Visible Infrared Imaging Radiometer Suite) satellite images. The proposed cloud and shadow detection method has two distinct features when compared to many other methods. First, the method does not use the thermal bands and can thus be applied to other sensors which do not contain thermal channels, such as Sentinel-2 data. Secondly, the method uses the ratio between blue and green reflectance to detect shadows. Seven hundred and forty-seven VIIRS images over Fennoscandia from August 2014 to April 2016 were processed to train and develop the method. Twenty four points from every tenth of the images were used in accuracy assessment. These 1752 points were interpreted visually to cloud, cloud shadow and clear classes, then compared to the output of the cloud and shadow detection. The comparison on VIIRS images showed 94.2% correct detection rates and 11.1% false alarms for clouds, and respectively 36.1% and 82.7% for shadows. The results on cloud detection were similar to state-of-the-art methods. Shadows showed correctly on the northern edge of the clouds, but many shadows were wrongly assigned to other classes in some cases (e.g., to water class on lake and forest boundary, or with shadows over cloud). This may be due to the low spatial resolution of VIIRS images, where shadows are only a few pixels wide and contain lots of mixed pixels.

    KW - cloud and shadow masking

    KW - optical satellite images

    KW - Suomi NPP VIIRS

    KW - Sentinel-2

    KW - surface reflectance

    KW - rule-based classification

    UR - http://www.scopus.com/inward/record.url?scp=85028319233&partnerID=8YFLogxK

    U2 - 10.3390/rs9080806

    DO - 10.3390/rs9080806

    M3 - Article

    VL - 9

    JO - Remote Sensing

    JF - Remote Sensing

    SN - 2072-4292

    IS - 8

    M1 - 806

    ER -