Enhancing the Accuracy of Land Cover Classification by Airborne LiDAR Data and WorldView-2 Satellite Imagery

The Full Waveform LiDAR system has been developed and used commercially all over the world. It acts to record complete time of a laser pulse high-resolution sampling interval compared traditional multiple-echo LiDAR, which only provides signals within single target range. This study area mainly collects data from Riegl LMS-Q680i WorldView-2 satellite imagery, focuses on buildings, vegetation, grassland, asphalt roads other ground types as surface objects. amplitude width are selected waveform basic parameters. parameter topography is slope, height classification parameters test 0–0.5 m, 0.5–2.5 2.5 m. To eliminate noise, neighborhood average applied values analyzed accuracy comparison. survey uses Decision Tree method. Comparing between non-neighborhood average, improves by 7%, Kappa 5.92%. NDVI image utilized distinguish artificial natural ground. results show that with previous can improve 5%, 4.25%. By adding NIR-2 imagery analysis, overall improved 2%, value 1.21%. article shows utilizing analysis effectively land covers.