Cloud classification of satellite image performed in two stages

Hiroshi Ikeda, Mitsuharu Matsumoto, Shuji Hashimoto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    To understand a comprehensive atmospheric state, it is important to classify clouds in satellite images into appropriate classes. Many researches utilizing various features concerning the cloud texture have been reported in cloud classification. However, some clouds can not be classified uniquely only with the texture features. According to the knowledge of the experts, they classify the clouds in two stages. They firstly categorize the clouds into the provisional classes according to the brightnesses of the satellite images. They then classify each provisional class into the objective class based on the texture, shape and velocity of the cloud employing the meteorological knowledge about the time and location of the image. In this paper, we propose a novel method for the cloud classification that consists of two stages and utilizes cloud movement as human experts adopt. We firstly classify the clouds into 20 classes based on their brightnesses of the two-band spectral images. We then closely analyze the classes according to five features such as the brightnesses, deviations of brightness and cloud velocity estimated by varying window size adaptively. The experimental results are shown to verify the proposed method.

    Original languageEnglish
    Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
    Volume6497
    DOIs
    Publication statusPublished - 2007
    EventImage Processing: Algorithms and Systems V - San Jose, CA
    Duration: 2007 Jan 292007 Jan 30

    Other

    OtherImage Processing: Algorithms and Systems V
    CitySan Jose, CA
    Period07/1/2907/1/30

    Fingerprint

    Luminance
    Satellites
    Textures
    brightness
    textures
    spectral bands
    deviation

    Keywords

    • Cloud classification
    • Cloud movement
    • Variable window size

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Condensed Matter Physics

    Cite this

    Ikeda, H., Matsumoto, M., & Hashimoto, S. (2007). Cloud classification of satellite image performed in two stages. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6497). [64970A] https://doi.org/10.1117/12.703300

    Cloud classification of satellite image performed in two stages. / Ikeda, Hiroshi; Matsumoto, Mitsuharu; Hashimoto, Shuji.

    Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6497 2007. 64970A.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ikeda, H, Matsumoto, M & Hashimoto, S 2007, Cloud classification of satellite image performed in two stages. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6497, 64970A, Image Processing: Algorithms and Systems V, San Jose, CA, 07/1/29. https://doi.org/10.1117/12.703300
    Ikeda H, Matsumoto M, Hashimoto S. Cloud classification of satellite image performed in two stages. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6497. 2007. 64970A https://doi.org/10.1117/12.703300
    Ikeda, Hiroshi ; Matsumoto, Mitsuharu ; Hashimoto, Shuji. / Cloud classification of satellite image performed in two stages. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6497 2007.
    @inproceedings{15c4b7820ee4435f926f33ea993469ba,
    title = "Cloud classification of satellite image performed in two stages",
    abstract = "To understand a comprehensive atmospheric state, it is important to classify clouds in satellite images into appropriate classes. Many researches utilizing various features concerning the cloud texture have been reported in cloud classification. However, some clouds can not be classified uniquely only with the texture features. According to the knowledge of the experts, they classify the clouds in two stages. They firstly categorize the clouds into the provisional classes according to the brightnesses of the satellite images. They then classify each provisional class into the objective class based on the texture, shape and velocity of the cloud employing the meteorological knowledge about the time and location of the image. In this paper, we propose a novel method for the cloud classification that consists of two stages and utilizes cloud movement as human experts adopt. We firstly classify the clouds into 20 classes based on their brightnesses of the two-band spectral images. We then closely analyze the classes according to five features such as the brightnesses, deviations of brightness and cloud velocity estimated by varying window size adaptively. The experimental results are shown to verify the proposed method.",
    keywords = "Cloud classification, Cloud movement, Variable window size",
    author = "Hiroshi Ikeda and Mitsuharu Matsumoto and Shuji Hashimoto",
    year = "2007",
    doi = "10.1117/12.703300",
    language = "English",
    isbn = "0819466107",
    volume = "6497",
    booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

    }

    TY - GEN

    T1 - Cloud classification of satellite image performed in two stages

    AU - Ikeda, Hiroshi

    AU - Matsumoto, Mitsuharu

    AU - Hashimoto, Shuji

    PY - 2007

    Y1 - 2007

    N2 - To understand a comprehensive atmospheric state, it is important to classify clouds in satellite images into appropriate classes. Many researches utilizing various features concerning the cloud texture have been reported in cloud classification. However, some clouds can not be classified uniquely only with the texture features. According to the knowledge of the experts, they classify the clouds in two stages. They firstly categorize the clouds into the provisional classes according to the brightnesses of the satellite images. They then classify each provisional class into the objective class based on the texture, shape and velocity of the cloud employing the meteorological knowledge about the time and location of the image. In this paper, we propose a novel method for the cloud classification that consists of two stages and utilizes cloud movement as human experts adopt. We firstly classify the clouds into 20 classes based on their brightnesses of the two-band spectral images. We then closely analyze the classes according to five features such as the brightnesses, deviations of brightness and cloud velocity estimated by varying window size adaptively. The experimental results are shown to verify the proposed method.

    AB - To understand a comprehensive atmospheric state, it is important to classify clouds in satellite images into appropriate classes. Many researches utilizing various features concerning the cloud texture have been reported in cloud classification. However, some clouds can not be classified uniquely only with the texture features. According to the knowledge of the experts, they classify the clouds in two stages. They firstly categorize the clouds into the provisional classes according to the brightnesses of the satellite images. They then classify each provisional class into the objective class based on the texture, shape and velocity of the cloud employing the meteorological knowledge about the time and location of the image. In this paper, we propose a novel method for the cloud classification that consists of two stages and utilizes cloud movement as human experts adopt. We firstly classify the clouds into 20 classes based on their brightnesses of the two-band spectral images. We then closely analyze the classes according to five features such as the brightnesses, deviations of brightness and cloud velocity estimated by varying window size adaptively. The experimental results are shown to verify the proposed method.

    KW - Cloud classification

    KW - Cloud movement

    KW - Variable window size

    UR - http://www.scopus.com/inward/record.url?scp=34548237412&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34548237412&partnerID=8YFLogxK

    U2 - 10.1117/12.703300

    DO - 10.1117/12.703300

    M3 - Conference contribution

    AN - SCOPUS:34548237412

    SN - 0819466107

    SN - 9780819466105

    VL - 6497

    BT - Proceedings of SPIE - The International Society for Optical Engineering

    ER -