A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Classification of vegetation in an open landscape using full-waveform airborne laser scanner data
We classify vegetation in an open landscape using only ALS-based variables. * 24 classes ([kappa]: 0.51) based on plant associations are aggregated at 3 levels. * We achieve an accuracy of [kappa]: 0.79 for the five main vegetation classes. * Natura 2000 habitats are classified with an accuracy of [kappa]: 0.69. * DTM-based variables increase the overall accuracies at all levels of aggregation.
Classification of vegetation in an open landscape using full-waveform airborne laser scanner data
We classify vegetation in an open landscape using only ALS-based variables. * 24 classes ([kappa]: 0.51) based on plant associations are aggregated at 3 levels. * We achieve an accuracy of [kappa]: 0.79 for the five main vegetation classes. * Natura 2000 habitats are classified with an accuracy of [kappa]: 0.69. * DTM-based variables increase the overall accuracies at all levels of aggregation.
Classification of vegetation in an open landscape using full-waveform airborne laser scanner data
Alexander, Cici (author) / Deak, BalaZs / Kania, Adam / Mucke, Werner / Heilmeier, Hermann
2015
Article (Journal)
English
Contextual segment-based classification of airborne laser scanner data
| Online Contents | 2017