Vegetation filtering of waveform terrestrial laser scanner data for DTM production

In this article, we present an investigation regarding the differences between a full-waveform and a discrete-return terrestrial laser scanner employed in a survey of a mountain area with dense vegetation. The Riegl LMS-Z620 provides discrete returns whereas the Riegl VZ-400 provides multiple returns with associated width and amplitude of the peaks extracted by online waveform processing. The uncertainty about the stability of the terrain underlying the mountain slope, which was affected by a landslide in 1966, gives a particular importance to an accurate representation of the terrain surface, thus to a robust filtering of the vegetation component. The VZ-400 scans were pre-filtered by exploiting the "calibrated relative reflectance" readings and the multi-target capability provided by this laser scanning system. In the next step, two spatial filters were applied to both georeferenced 3D models in order to eliminate vegetation using an iterative filter and a custom morphological filter. Results show that the use of the iterative morphological filter performs quite well in eliminating the vegetation from both datasets. Vegetation in sloped terrain does still limit the complete removal of the above-ground elements, thus a completely automatic procedure is still not applicable. Stem and canopy growing direction with respect to ground is a factor which should be taken into account in future developments of the procedure. Differences between the two results show that a higher point density is obtained from the VZ-400 due to its multi-return capabilities and the added characteristics extracted from the online waveform processing give added value for filtering more accurately. Results demonstrate that a TLS with multi-target capability can potentially provide a more detailed DTM in presence of dense vegetation. © 2013 Società Italiana di Fotogrammetria e Topografia (SIFET).