UNSUPERVISED SEGMENTATION OF SMALLHOLDER FIELDS IN MOZAMBIQUE USING PLANETSCOPE IMAGERY

M.C.A. Picoli*, J. Radoux, X. Tong, A. Bey, P. Rufin, M. Brandt, R. Fensholt, P. Meyfroidt

*Corresponding author for this work

    Research output: Contribution to journalConference articleResearchpeer-review

    2 Citations (Scopus)
    14 Downloads (Pure)

    Abstract

    Smallholders produce about a third of the global crop production. Supporting these smallholder farms is an important lever for poverty alleviation. Farm and field sizes are key indicators of many smallholder dynamics, including fragmentation, farm consolidation, and interactions between smallholders, medium-scale commercial farming, and large enterprises. Despite the socio-economic, environmental, and political importance of these dynamics, spatially explicit data on farms and field sizes are still lacking. Identifying small-scale agriculture using satellite imagery is challenging due to the heterogeneity in the crop types and management practices. This study compared three unsupervised segmentation approaches that have not been widely explored for delineating smallholder fields: mean shift, multiresolution segmentation, and simple non-iterative clustering (SNIC), using PlanetScope imagery. The study area is located in northern Mozambique, where 71% of the farms cover less than 2 ha. The results were evaluated using four segmentation accuracy metrics based on object geometries: Area Fit Index (AFI), Quality Rate (QR), Oversegmentation (OS), and Undersegmentation (US). The results showed that the multiresolution segmentation algorithm outperformed the other methods to delineate smallholder fields. This work will support future regional-scale mapping efforts.

    Original languageEnglish
    JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
    Volume43
    Issue numberB3-2022
    Pages (from-to)975-981
    Number of pages7
    ISSN1682-1750
    DOIs
    Publication statusPublished - 2022
    Event2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission III - Nice, France
    Duration: 6 Jun 202211 Jun 2022

    Conference

    Conference2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission III
    Country/TerritoryFrance
    CityNice
    Period06/06/202211/06/2022

    Bibliographical note

    Publisher Copyright:
    © Authors 2022

    Keywords

    • mean shift
    • multiresolution
    • Object-based image analysis (OBIA)
    • smallholders
    • SNIC

    Cite this