Spatio-temporal motion features for laser-based moving objects detection and tracking

This paper proposes a spatio-temporal motion feature detection and tracking method using range sensors working on a moving platform. The proposed spatio-temporal motion features are similar to optical flow but are extended on a moving platform with fusion of odometry and show much better classification accuracy with consideration of different uncertainties. In the proposal, the ego motion is compensated by odometry sensors and the laser scan points are accumulated and represented as space-time point clouds, from which the velocities and moving directions can be extracted. Based on these spatio-temporal features, a supervised learning technique is applied to classify the points as static or moving and Kalman filters are implemented to track the moving objects. A real experiment is performed during day and night on an autonomous vehicle platform and shows promising results in a crowded and dynamic environment.

Authors

• Xiaotong Shen
• Seong-Woo Kim
• Marcelo H. Ang

Keywords

• Sensors
• Three-dimensional displays
• Feature extraction
• Uncertainty
• Laser radar
• Motion detection
• Tracking
• Motion Features
• Spatiotemporal Characteristics
• Object Tracking
• Moving Object Detection
• Laser Scanning
• Supervised Learning
• Dynamic Environment
• Point Cloud
• Kalman Filter
• Range Of Sensors
• Supervised Learning Techniques
• Ego-motion
• Pedestrian
• Inertial Measurement Unit
• Model-based Approach
• Motion Estimation
• Supervised Learning Methods
• Static Objects
• Cross-validation Technique
• Surface Normals
• Current Scan
• Crowded Environment
• Velocity Information
• Radial Basis Function Network
• Spatial Shape
• Dead Reckoning
• Occupied Space
• LiDAR Sensor
• Priority Map