SEMANTIC CLASSIFICATION OF SANDSTONE LANDSCAPE POINT CLOUD BASED ON NEIGHBOURHOOD FEATURES
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11310%2F20%3A10413794" target="_blank" >RIV/00216208:11310/20:10413794 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/333/2020/isprs-archives-XLIII-B2-2020-333-2020.pdf" target="_blank" >https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/333/2020/isprs-archives-XLIII-B2-2020-333-2020.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.5194/isprs-archives-XLIII-B2-2020-333-2020" target="_blank" >10.5194/isprs-archives-XLIII-B2-2020-333-2020</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
SEMANTIC CLASSIFICATION OF SANDSTONE LANDSCAPE POINT CLOUD BASED ON NEIGHBOURHOOD FEATURES
Popis výsledku v původním jazyce
The technology of airborne laser scanning enables fast and accurate gathering spatial data containing also echoes from the terrain below the vegetation canopy that is beneficial for topographic mapping of wooded sandstone landscapes in Czechia, Poland, and Germany. The challengeable task is to determine the ground points in the point cloud because commonly used filtration methods do not successfully distinguish between vegetation and rock pillars and faces. In this paper, we replace filtration with classification approach using the features derived from characteristics of points within a neighbourhood of optimized sizes, such as eigenvalue-based features and echo ratio. Random Forest classifier is trained and tested on the manually labelled dataset with a density of almost 650 points/m2 from the Adršpach-Teplice Rocks. The overall accuracy reaches 87% but recall and precision of non-ground points are unsatisfactory. Misclassified non-ground points are located also within trees, thus we do not consider the result as suitable for DTM processing without further processing.
Název v anglickém jazyce
SEMANTIC CLASSIFICATION OF SANDSTONE LANDSCAPE POINT CLOUD BASED ON NEIGHBOURHOOD FEATURES
Popis výsledku anglicky
The technology of airborne laser scanning enables fast and accurate gathering spatial data containing also echoes from the terrain below the vegetation canopy that is beneficial for topographic mapping of wooded sandstone landscapes in Czechia, Poland, and Germany. The challengeable task is to determine the ground points in the point cloud because commonly used filtration methods do not successfully distinguish between vegetation and rock pillars and faces. In this paper, we replace filtration with classification approach using the features derived from characteristics of points within a neighbourhood of optimized sizes, such as eigenvalue-based features and echo ratio. Random Forest classifier is trained and tested on the manually labelled dataset with a density of almost 650 points/m2 from the Adršpach-Teplice Rocks. The overall accuracy reaches 87% but recall and precision of non-ground points are unsatisfactory. Misclassified non-ground points are located also within trees, thus we do not consider the result as suitable for DTM processing without further processing.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10508 - Physical geography
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2020
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
ISBN
—
ISSN
1682-1750
e-ISSN
—
Počet stran výsledku
6
Strana od-do
333-338
Název nakladatele
Copernicus GmbH (Copernicus Publications)
Místo vydání
Germany
Místo konání akce
Nice, France (online)
Datum konání akce
31. 8. 2020
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—