Object-based habitat mapping of reedbeds using country-wide airborne laser scanning point clouds

Abstract : Recent advances of Light Detection and Ranging (LiDAR) have facilitated the accurate mapping of ecosystem structure at local and landscape scales. Moreover, the increasing availability of openly accessible Airborne Laser Scanning (ALS) point clouds provides new opportunities for mapping the fine-scale extent and distribution of ecosystems and habitats across broad spatial extents. However, processing of such massive amounts of ALS data is still challenging because it requires computationally efficient software and tools for data handling. Here, we develop an open-source object-based approach for the fine-scale identification and delineation of reedbeds which should permit their mapping across broad spatial extents using country-wide ALS data. Reedbeds are wetlands dominated by the common reed (Phragmites australis) and constitute a major habitat for breeding and migratory birds, thus being of high conservation value in Europe. We apply a region growing segmentation algorithm to automatically classify ALS point clouds into structurally similar vegetation patches and apply it to selected wetland areas in the Netherlands (Giethoon and Naardermeer). Our workflow consists of four steps. In a first step, we derive the most commonly used neighborhood-related LiDAR metrics such as roughness of the vegetation top, descriptive statistics of vegetation height and echo ratio. In a second step, these calculated LiDAR metrics are used to classify the point cloud into ground, vegetation, buildings and water classes. In a third step, an object-based analysis is applied to the vegetation class using a region growing segmentation algorithm for delineating homogenous patches. In a fourth step, the segments are classified into reedbed and non-reedbed vegetation using additional object-related features such as distance from a water body, area and shape of the object. For validation, vegetation plots and available high resolution aerial orthophotos (e.g. DKLN-NL) are used. The vegetation plots come from the Dutch Vegetation Database which uses the Darwin Core Archive (DwC-A) as an open-access (meta)data standard. This allows access to standardized vegetation sampling inventories from various habitats across the Netherlands, and hence provides the opportunity to test the methodology at a country-wide scale. Our results demonstrate that an object-based approach allows the extraction of fine-scale boundaries and delineation of patches of reedbeds as well as their separation from woody vegetation elements such as stand-alone trees within reedbeds. Accuracy assessment indicates a good performance which allows for successful upscaling to broad spatial extents. We further outline how the developed workflow can be built into a new open-source software for processing country-wide ALS data using scalable computing. The fine-scale mapping of reedbed habitats will complement available land cover maps which usually lack information on small and scattered habitats such as reedbeds. Reedbed habitat maps will also provide the necessary spatially-explicit information for predicting species distributions of threatened wetland birds (e.g. Great Bittern and many reed-dwelling warblers) which are a prime target for nature conservation in Europe.
Complete list of metadatas

http://hal.univ-reunion.fr/hal-01960403
Contributor : Réunion Univ <>
Submitted on : Wednesday, December 19, 2018 - 1:32:11 PM
Last modification on : Tuesday, April 16, 2019 - 12:42:08 PM

Identifiers

  • HAL Id : hal-01960403, version 1

Collections

Citation

Zsófia Koma, Arie C. Seijmonsbergen, Christiaan Meijer, Willem Bouten, W. Daniel Kissling. Object-based habitat mapping of reedbeds using country-wide airborne laser scanning point clouds. GEOBIA 2018 - From pixels to ecosystems and global sustainability ​, Centre d'Etudes Spatiales de la BIOsphère (CESBIO); Office national d'études et de recherches aérospatiales (ONERA); Espace pour le développement (ESPACE DEV); Société T.E.T.I.S, Jun 2018, Montpellier, France. ⟨hal-01960403⟩

Share

Metrics

Record views

35