Using semi-global matching point clouds to estimate growing stock at the plot and stand levels: Application for a broadleaf-dominated forest in central Europe

Keyphrases

• Point Cloud 100%
• Semi-global Matching 100%
• Central Europe 100%
• Linear Regression Model 100%
• Random Forest Regression 100%
• Stand Level 100%
• Plot Level 100%
• Inventory Plot 100%
• Growth Stocks 100%
• Broadleaves 100%
• Training Data 33%
• Stereo Images 33%
• Model Performance 33%
• Terrain Elevation 33%
• Amount of Training 33%
• Dense Point Cloud 33%
• Orthoimage 33%
• Spectral Information 33%
• Image-based Point Cloud 33%
• Root Mean Square Error 33%
• Evaluation Model 33%
• Southern Germany 33%
• Modeling Approach 33%
• Airborne Laser Scanner 33%
• Airborne Laser Scanner Data 33%
• Forest Inventory 33%
• DATAPLOT 33%
• Explanatory Variables 33%
• Forest Management 33%
• Canopy Height 33%
• Forest Attributes 33%
• Stand Size 33%
• Dense Subset 33%
• Aerial Stereo Imagery 33%
• Height Information 33%
• Relative Root Mean Square Error (RRMSE) 33%

Earth and Planetary Sciences

• Central Europe 100%
• Airborne Laser 100%
• Germany 50%
• Forest Inventory 50%
• Stereo Image 50%