Detecting land-cover modifications from multi-resolution satellite image time series

Francois Petitjean, Jordi Inglada, Pierre Gancarski

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

    Abstract

    Frequent high-resolution images will be provided by new satellites such as Venμs, SENTINEL-2 and Landsat Data Continuity Mission. Methods to handle this new type of data are currently developed (see [1] for an example). However, a more frequent observation of the surface of the Earth may be required for some applications. Moreover, the temporal resolution may be reduced by meteorological artifacts. In this work, we propose to take advantage of the higher temporal resolution of satellites with a lower spatial resolution to detect land-cover modification at a high spatial resolution. The proposed approach does not use any fusion step of the high- and low-resolution images. We show that the low spatial resolution satellite image time series (SITS) can be used in order to inform about the stability and relevance of the high spatial resolution classification. Experiments include a wide variety of resolution ratios and study the use of each ratio for the assessment of high resolution classification maps (computed from the high spatial resolution SITS).

    Original languageEnglish
    Title of host publication2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings
    Subtitle of host publicationJuly 21–26, 2013, Melbourne, Australia
    Place of PublicationPiscataway, NJ
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages3447-3450
    Number of pages4
    ISBN (Electronic)9781479911141
    DOIs
    Publication statusPublished - 2013
    EventIEEE International Geoscience and Remote Sensing Symposium 2013 - Melbourne Convention and Exhibition Centre, Melbourne, Australia
    Duration: 21 Jul 201326 Jul 2013
    Conference number: 33rd
    http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6704876 (IEEE Conference Proceedings)

    Conference

    ConferenceIEEE International Geoscience and Remote Sensing Symposium 2013
    Abbreviated titleIGARSS 2013
    CountryAustralia
    CityMelbourne
    Period21/07/1326/07/13
    Internet address

    Keywords

    • Crops
    • Image classification
    • Remote Sensing
    • Time series analysis

    Cite this

    Petitjean, F., Inglada, J., & Gancarski, P. (2013). Detecting land-cover modifications from multi-resolution satellite image time series. In 2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings: July 21–26, 2013, Melbourne, Australia (pp. 3447-3450). [6723570] Piscataway, NJ: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IGARSS.2013.6723570
    Petitjean, Francois ; Inglada, Jordi ; Gancarski, Pierre. / Detecting land-cover modifications from multi-resolution satellite image time series. 2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings: July 21–26, 2013, Melbourne, Australia. Piscataway, NJ : IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 3447-3450
    @inproceedings{67bfe973d317454ea943363a0e6a214c,
    title = "Detecting land-cover modifications from multi-resolution satellite image time series",
    abstract = "Frequent high-resolution images will be provided by new satellites such as Venμs, SENTINEL-2 and Landsat Data Continuity Mission. Methods to handle this new type of data are currently developed (see [1] for an example). However, a more frequent observation of the surface of the Earth may be required for some applications. Moreover, the temporal resolution may be reduced by meteorological artifacts. In this work, we propose to take advantage of the higher temporal resolution of satellites with a lower spatial resolution to detect land-cover modification at a high spatial resolution. The proposed approach does not use any fusion step of the high- and low-resolution images. We show that the low spatial resolution satellite image time series (SITS) can be used in order to inform about the stability and relevance of the high spatial resolution classification. Experiments include a wide variety of resolution ratios and study the use of each ratio for the assessment of high resolution classification maps (computed from the high spatial resolution SITS).",
    keywords = "Crops, Image classification, Remote Sensing, Time series analysis",
    author = "Francois Petitjean and Jordi Inglada and Pierre Gancarski",
    year = "2013",
    doi = "10.1109/IGARSS.2013.6723570",
    language = "English",
    pages = "3447--3450",
    booktitle = "2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States of America",

    }

    Petitjean, F, Inglada, J & Gancarski, P 2013, Detecting land-cover modifications from multi-resolution satellite image time series. in 2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings: July 21–26, 2013, Melbourne, Australia., 6723570, IEEE, Institute of Electrical and Electronics Engineers, Piscataway, NJ, pp. 3447-3450, IEEE International Geoscience and Remote Sensing Symposium 2013, Melbourne, Australia, 21/07/13. https://doi.org/10.1109/IGARSS.2013.6723570

    Detecting land-cover modifications from multi-resolution satellite image time series. / Petitjean, Francois; Inglada, Jordi; Gancarski, Pierre.

    2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings: July 21–26, 2013, Melbourne, Australia. Piscataway, NJ : IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 3447-3450 6723570.

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

    TY - GEN

    T1 - Detecting land-cover modifications from multi-resolution satellite image time series

    AU - Petitjean, Francois

    AU - Inglada, Jordi

    AU - Gancarski, Pierre

    PY - 2013

    Y1 - 2013

    N2 - Frequent high-resolution images will be provided by new satellites such as Venμs, SENTINEL-2 and Landsat Data Continuity Mission. Methods to handle this new type of data are currently developed (see [1] for an example). However, a more frequent observation of the surface of the Earth may be required for some applications. Moreover, the temporal resolution may be reduced by meteorological artifacts. In this work, we propose to take advantage of the higher temporal resolution of satellites with a lower spatial resolution to detect land-cover modification at a high spatial resolution. The proposed approach does not use any fusion step of the high- and low-resolution images. We show that the low spatial resolution satellite image time series (SITS) can be used in order to inform about the stability and relevance of the high spatial resolution classification. Experiments include a wide variety of resolution ratios and study the use of each ratio for the assessment of high resolution classification maps (computed from the high spatial resolution SITS).

    AB - Frequent high-resolution images will be provided by new satellites such as Venμs, SENTINEL-2 and Landsat Data Continuity Mission. Methods to handle this new type of data are currently developed (see [1] for an example). However, a more frequent observation of the surface of the Earth may be required for some applications. Moreover, the temporal resolution may be reduced by meteorological artifacts. In this work, we propose to take advantage of the higher temporal resolution of satellites with a lower spatial resolution to detect land-cover modification at a high spatial resolution. The proposed approach does not use any fusion step of the high- and low-resolution images. We show that the low spatial resolution satellite image time series (SITS) can be used in order to inform about the stability and relevance of the high spatial resolution classification. Experiments include a wide variety of resolution ratios and study the use of each ratio for the assessment of high resolution classification maps (computed from the high spatial resolution SITS).

    KW - Crops

    KW - Image classification

    KW - Remote Sensing

    KW - Time series analysis

    UR - http://www.scopus.com/inward/record.url?scp=84894236011&partnerID=8YFLogxK

    U2 - 10.1109/IGARSS.2013.6723570

    DO - 10.1109/IGARSS.2013.6723570

    M3 - Conference Paper

    AN - SCOPUS:84894236011

    SP - 3447

    EP - 3450

    BT - 2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - Piscataway, NJ

    ER -

    Petitjean F, Inglada J, Gancarski P. Detecting land-cover modifications from multi-resolution satellite image time series. In 2013 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2013) - Proceedings: July 21–26, 2013, Melbourne, Australia. Piscataway, NJ: IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 3447-3450. 6723570 https://doi.org/10.1109/IGARSS.2013.6723570