Towards building a Crowd-Sourced Sky Map

Dustin Lang, David W. Hogg, Bernhard Schölkopf

    Research output: Contribution to journalArticle

    Abstract

    We describe a system that builds a high dynamic-range and wide-angle image of the night sky by combining a large set of input images. The method makes use of pixelrank information in the individual input images to improve a "consensus" pixel rank in the combined image. Because it only makes use of ranks and the complexity of the algorithm is linear in the number of images, the method is useful for large sets of uncalibrated images that might have undergone unknown non-linear tone mapping transformations for visualization or aesthetic reasons. We apply the method to images of the night sky (of unknown provenance) discovered on the Web. The method permits discovery of astronomical objects or features that are not visible in any of the input images taken individually. More importantly, however, it permits scientific exploitation of a huge source of astronomical images that would not be available to astronomical research without our automatic system.

    Original languageEnglish (US)
    Pages (from-to)549-557
    Number of pages9
    JournalJournal of Machine Learning Research
    Volume33
    StatePublished - 2014

    Fingerprint

    Visualization
    Pixels
    Large Set
    Unknown
    High Dynamic Range
    Provenance
    Exploitation
    Pixel
    Angle

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Control and Systems Engineering
    • Statistics and Probability

    Cite this

    Lang, D., Hogg, D. W., & Schölkopf, B. (2014). Towards building a Crowd-Sourced Sky Map. Journal of Machine Learning Research, 33, 549-557.

    Towards building a Crowd-Sourced Sky Map. / Lang, Dustin; Hogg, David W.; Schölkopf, Bernhard.

    In: Journal of Machine Learning Research, Vol. 33, 2014, p. 549-557.

    Research output: Contribution to journalArticle

    Lang, D, Hogg, DW & Schölkopf, B 2014, 'Towards building a Crowd-Sourced Sky Map', Journal of Machine Learning Research, vol. 33, pp. 549-557.
    Lang D, Hogg DW, Schölkopf B. Towards building a Crowd-Sourced Sky Map. Journal of Machine Learning Research. 2014;33:549-557.
    Lang, Dustin ; Hogg, David W. ; Schölkopf, Bernhard. / Towards building a Crowd-Sourced Sky Map. In: Journal of Machine Learning Research. 2014 ; Vol. 33. pp. 549-557.
    @article{1452b9f759be4584a61a949402d7fb43,
    title = "Towards building a Crowd-Sourced Sky Map",
    abstract = "We describe a system that builds a high dynamic-range and wide-angle image of the night sky by combining a large set of input images. The method makes use of pixelrank information in the individual input images to improve a {"}consensus{"} pixel rank in the combined image. Because it only makes use of ranks and the complexity of the algorithm is linear in the number of images, the method is useful for large sets of uncalibrated images that might have undergone unknown non-linear tone mapping transformations for visualization or aesthetic reasons. We apply the method to images of the night sky (of unknown provenance) discovered on the Web. The method permits discovery of astronomical objects or features that are not visible in any of the input images taken individually. More importantly, however, it permits scientific exploitation of a huge source of astronomical images that would not be available to astronomical research without our automatic system.",
    author = "Dustin Lang and Hogg, {David W.} and Bernhard Sch{\"o}lkopf",
    year = "2014",
    language = "English (US)",
    volume = "33",
    pages = "549--557",
    journal = "Journal of Machine Learning Research",
    issn = "1532-4435",
    publisher = "Microtome Publishing",

    }

    TY - JOUR

    T1 - Towards building a Crowd-Sourced Sky Map

    AU - Lang, Dustin

    AU - Hogg, David W.

    AU - Schölkopf, Bernhard

    PY - 2014

    Y1 - 2014

    N2 - We describe a system that builds a high dynamic-range and wide-angle image of the night sky by combining a large set of input images. The method makes use of pixelrank information in the individual input images to improve a "consensus" pixel rank in the combined image. Because it only makes use of ranks and the complexity of the algorithm is linear in the number of images, the method is useful for large sets of uncalibrated images that might have undergone unknown non-linear tone mapping transformations for visualization or aesthetic reasons. We apply the method to images of the night sky (of unknown provenance) discovered on the Web. The method permits discovery of astronomical objects or features that are not visible in any of the input images taken individually. More importantly, however, it permits scientific exploitation of a huge source of astronomical images that would not be available to astronomical research without our automatic system.

    AB - We describe a system that builds a high dynamic-range and wide-angle image of the night sky by combining a large set of input images. The method makes use of pixelrank information in the individual input images to improve a "consensus" pixel rank in the combined image. Because it only makes use of ranks and the complexity of the algorithm is linear in the number of images, the method is useful for large sets of uncalibrated images that might have undergone unknown non-linear tone mapping transformations for visualization or aesthetic reasons. We apply the method to images of the night sky (of unknown provenance) discovered on the Web. The method permits discovery of astronomical objects or features that are not visible in any of the input images taken individually. More importantly, however, it permits scientific exploitation of a huge source of astronomical images that would not be available to astronomical research without our automatic system.

    UR - http://www.scopus.com/inward/record.url?scp=84955473897&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84955473897&partnerID=8YFLogxK

    M3 - Article

    AN - SCOPUS:84955473897

    VL - 33

    SP - 549

    EP - 557

    JO - Journal of Machine Learning Research

    JF - Journal of Machine Learning Research

    SN - 1532-4435

    ER -