URBAN TREE CLASSIFICATION USING FULL-WAVEFORM AIRBORNE LASER SCANNING

摘要: Vegetation mapping in urban environments plays an important role biological research and management. Airborne laser scanning provides detailed 3D geodata, which allows to classify single trees into different taxa. Until now, dealing with tree classification focused on forest environments. This study investigates the object-based of at taxonomic family level, using full-waveform airborne data captured city centre Vienna (Austria). The set is characterised by a variety taxa, including deciduous (beeches, mallows, plane soapberries) coniferous pine species. A workflow for object presented geometric radiometric features. derived features are related point density, crown shape characteristics. For derivation features, prior detection base performed. effects interfering objects (e.g. fences cars typical areas) feature characteristics subsequent accuracy investigated. applicability evaluated Random Forest exploratory analysis. most reliable achieved combination resulting 87.5% overall accuracy. By only, 86.3% can be achieved. influence identified, particular results indicate potential show its limitations due anthropogenic influences same time.