Airborne LiDAR for Detection and Characterization of Urban Objects and Traffic Dynamics

Keyphrases

• Traffic Dynamics 100%
• Airborne LiDAR 100%
• Urban Traffic 100%
• Urban Objects 100%
• Object Dynamics 100%
• Classification Results 66%
• Per-pixel 66%
• Co-registration 66%
• Natural Ground 66%
• LiDAR Point Cloud 66%
• AdaBoost Classifier 66%
• Performance Analysis 33%
• Planarity 33%
• Training Data 33%
• Data-centric 33%
• System Performance 33%
• Spectral Features 33%
• Detection Accuracy 33%
• City Area 33%
• Statistical Features 33%
• Feature Space 33%
• Slow Moving 33%
• Traffic-related 33%
• False Positive Rate 33%
• Object-level 33%
• Cuboid 33%
• Vehicle Motion 33%
• Moving Vehicle 33%
• Spectral-spatial Feature 33%
• Point Density 33%
• Motion Artifact 33%
• Object Detection 33%
• Static Properties 33%
• Geometric Criterion 33%
• Selected Features 33%
• Airborne LiDAR Data 33%
• Downtown Area 33%
• LiDAR Intensity 33%
• Advanced Machine Learning 33%
• Dynamical Properties 33%
• Object Class 33%
• Spatial Statistical 33%
• ALS Data 33%
• Covariance-based 33%
• Observation Geometry 33%
• Velocity Estimation 33%
• Large-scale Urban Areas 33%
• Relevance Assessment 33%
• Feature Relevance 33%
• Raster Format 33%
• Machine Learning Strategies 33%
• ISPRS Benchmark 33%
• Urban Classification 33%
• Semantic Criteria 33%
• Velocity Accuracy 33%
• Artifact Model 33%
• Experimental Dataset 33%
• Fast-moving 33%
• Comparative Performance Analysis 33%
• Typical Cities 33%
• Complex Urban Areas 33%
• Spatial Context Information 33%

Engineering

• Point Cloud 100%
• Test Site 100%
• Adaboost 100%
• Performance Analysis 100%
• Experimental Result 50%
• Context Information 50%
• Spectral Feature 50%
• Motion Artifact 50%
• Data Point 50%
• Statistical Feature 50%
• Raster Format 50%
• Systems Performance 50%
• Feature Space 50%
• Learning System 50%

Earth and Planetary Sciences

• Machine Learning 100%
• Covariance 100%