Mangrove tree crown delineation from high-resolution imagery

Muditha Kumari Heenkenda Mudalige, Karen Joyce, Stefan Maier

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    Mangroves are very dense, spatially heterogeneous, and have limited height variations between neighboring trees. Delineating individual tree crowns is thus very challenging. This study compared methods for isolating mangrove crowns using object based image analysis. A combination of WorldView-2 imagery, a digital surface model, a local maximum filtering technique, and a region growing approach achieved 92 percent overall accuracy in extracting tree crowns. The more traditionally used inverse watershed segmentation method showed low accuracy (35 percent), demonstrating that this method is better suited to homogeneous forests with reasonable height variations between trees. The main challenges with each of the methods tested were the limited height variation between surrounding trees and multiple upward pointing branches of trees. In summary, mangrove tree crowns can be delineated from appropriately parameterized object based algorithms with a combination of high-resolution satellite images and a digital surface model. We recommend partitioning the imagery into homogeneous species stands for best results. � 2015 American Society for Photogrammetry and Remote Sensing.
    Original languageEnglish
    Pages (from-to)471-479
    Number of pages9
    JournalPhotogrammetric Engineering and Remote Sensing
    Volume81
    Issue number6
    DOIs
    Publication statusPublished - 2015

    Fingerprint

    mangrove
    imagery
    Photogrammetry
    Watersheds
    Image analysis
    Remote sensing
    Satellites
    photogrammetry
    image analysis
    segmentation
    partitioning
    watershed
    remote sensing
    method

    Cite this

    Heenkenda Mudalige, Muditha Kumari ; Joyce, Karen ; Maier, Stefan. / Mangrove tree crown delineation from high-resolution imagery. In: Photogrammetric Engineering and Remote Sensing. 2015 ; Vol. 81, No. 6. pp. 471-479.
    @article{eaca39f4b2b345c28310fcc6821e8ad9,
    title = "Mangrove tree crown delineation from high-resolution imagery",
    abstract = "Mangroves are very dense, spatially heterogeneous, and have limited height variations between neighboring trees. Delineating individual tree crowns is thus very challenging. This study compared methods for isolating mangrove crowns using object based image analysis. A combination of WorldView-2 imagery, a digital surface model, a local maximum filtering technique, and a region growing approach achieved 92 percent overall accuracy in extracting tree crowns. The more traditionally used inverse watershed segmentation method showed low accuracy (35 percent), demonstrating that this method is better suited to homogeneous forests with reasonable height variations between trees. The main challenges with each of the methods tested were the limited height variation between surrounding trees and multiple upward pointing branches of trees. In summary, mangrove tree crowns can be delineated from appropriately parameterized object based algorithms with a combination of high-resolution satellite images and a digital surface model. We recommend partitioning the imagery into homogeneous species stands for best results. � 2015 American Society for Photogrammetry and Remote Sensing.",
    keywords = "Image segmentation, Inverse problems, Plants (botany), Digital surface models, High resolution imagery, High resolution satellite images, Individual tree crown, Local maximum filtering, Object based image analysis, Overall accuracies, Watershed segmentation, Forestry, accuracy assessment, algorithm, canopy architecture, digital image, heterogeneity, homogeneity, image analysis, image resolution, mangrove, numerical model, segmentation, stand structure, WorldView, Algorithms, Forests, Mangrove, Remote Sensing, Rhizophoraceae",
    author = "{Heenkenda Mudalige}, {Muditha Kumari} and Karen Joyce and Stefan Maier",
    year = "2015",
    doi = "10.14358/PERS.81.6.471",
    language = "English",
    volume = "81",
    pages = "471--479",
    journal = "Photogrammetric Engineering and Remote Sensing",
    issn = "0099-1112",
    publisher = "American Society for Photogrammetry and Remote Sensing",
    number = "6",

    }

    Mangrove tree crown delineation from high-resolution imagery. / Heenkenda Mudalige, Muditha Kumari ; Joyce, Karen; Maier, Stefan.

    In: Photogrammetric Engineering and Remote Sensing, Vol. 81, No. 6, 2015, p. 471-479.

    Research output: Contribution to journalArticleResearchpeer-review

    TY - JOUR

    T1 - Mangrove tree crown delineation from high-resolution imagery

    AU - Heenkenda Mudalige, Muditha Kumari

    AU - Joyce, Karen

    AU - Maier, Stefan

    PY - 2015

    Y1 - 2015

    N2 - Mangroves are very dense, spatially heterogeneous, and have limited height variations between neighboring trees. Delineating individual tree crowns is thus very challenging. This study compared methods for isolating mangrove crowns using object based image analysis. A combination of WorldView-2 imagery, a digital surface model, a local maximum filtering technique, and a region growing approach achieved 92 percent overall accuracy in extracting tree crowns. The more traditionally used inverse watershed segmentation method showed low accuracy (35 percent), demonstrating that this method is better suited to homogeneous forests with reasonable height variations between trees. The main challenges with each of the methods tested were the limited height variation between surrounding trees and multiple upward pointing branches of trees. In summary, mangrove tree crowns can be delineated from appropriately parameterized object based algorithms with a combination of high-resolution satellite images and a digital surface model. We recommend partitioning the imagery into homogeneous species stands for best results. � 2015 American Society for Photogrammetry and Remote Sensing.

    AB - Mangroves are very dense, spatially heterogeneous, and have limited height variations between neighboring trees. Delineating individual tree crowns is thus very challenging. This study compared methods for isolating mangrove crowns using object based image analysis. A combination of WorldView-2 imagery, a digital surface model, a local maximum filtering technique, and a region growing approach achieved 92 percent overall accuracy in extracting tree crowns. The more traditionally used inverse watershed segmentation method showed low accuracy (35 percent), demonstrating that this method is better suited to homogeneous forests with reasonable height variations between trees. The main challenges with each of the methods tested were the limited height variation between surrounding trees and multiple upward pointing branches of trees. In summary, mangrove tree crowns can be delineated from appropriately parameterized object based algorithms with a combination of high-resolution satellite images and a digital surface model. We recommend partitioning the imagery into homogeneous species stands for best results. � 2015 American Society for Photogrammetry and Remote Sensing.

    KW - Image segmentation

    KW - Inverse problems

    KW - Plants (botany)

    KW - Digital surface models

    KW - High resolution imagery

    KW - High resolution satellite images

    KW - Individual tree crown

    KW - Local maximum filtering

    KW - Object based image analysis

    KW - Overall accuracies

    KW - Watershed segmentation

    KW - Forestry

    KW - accuracy assessment

    KW - algorithm

    KW - canopy architecture

    KW - digital image

    KW - heterogeneity

    KW - homogeneity

    KW - image analysis

    KW - image resolution

    KW - mangrove

    KW - numerical model

    KW - segmentation

    KW - stand structure

    KW - WorldView

    KW - Algorithms

    KW - Forests

    KW - Mangrove

    KW - Remote Sensing

    KW - Rhizophoraceae

    U2 - 10.14358/PERS.81.6.471

    DO - 10.14358/PERS.81.6.471

    M3 - Article

    VL - 81

    SP - 471

    EP - 479

    JO - Photogrammetric Engineering and Remote Sensing

    JF - Photogrammetric Engineering and Remote Sensing

    SN - 0099-1112

    IS - 6

    ER -