Extraction of Tree Crowns from High Resolution Imagery over Eucalypt Dominant Tropical Savannas

Timothy Whiteside, Guy Boggs, Stefan Maier

    Research output: Contribution to journalArticle

    Abstract

    High spatial resolution satellite imagery provides data that enable the analysis of detailed landscape information, including tree crowns. The inherent characteristics of Eucalypt crowns are challenging to remotely sensed tree crown extraction. This paper develops and applies an object-based tree crown delineation approach suitable for estimating canopy cover of Eucalypts in tropical savannas. A two level segmentation was undertaken upon QuickBird data. First, a broad segmentation masked out non-Eucalypt dominant communities; and second, a finer segmentation and ruleset identified seed objects within crowns, and then expanded these objects to cover entire crown extents. Of the 1,604 tree crowns manually observed within the scene, 84.3 percent were detected by the automated seed identification process. Seventy-five percent of tree crowns extracted through the region growing process show strong overlap with their corresponding reference crowns. Results indicate the potential of this method for delineating tree crowns from Eucalypt dominant savanna and the use of this information to estimate canopy cover and tree distribution patterns.
    Original languageEnglish
    Pages (from-to)813-824
    Number of pages12
    JournalPhotogrammetric Engineering and Remote Sensing
    Volume77
    Issue number8
    Publication statusPublished - 2011

    Fingerprint Dive into the research topics of 'Extraction of Tree Crowns from High Resolution Imagery over Eucalypt Dominant Tropical Savannas'. Together they form a unique fingerprint.

  • Cite this