Vehicle activity indication from airborne LiDAR data of urban areas by binary shape classification of point sets

This paper presents a generic scheme to analyze urban traffic viavehicle motion indication from airborne laser scanning (ALS) data.The scheme comprises two main steps performed progressively ? vehicleextraction and motion status classification. The step for vehicle extraction is intended to detect and delineate single vehicleinstances as accurate and complete as possible, while the step formotion status classification takes advantage of shape artefacts definedfor moving vehicle model, to classify the extracted vehicle point sets based on parameterized boundary features, which are sufficientlygood to describe the vehicle shape. To accomplish the tasks, a hybrid strategy integrating context-guided method with 3-dsegmentation based approach is applied for vehicle extraction. Then, a binary classification method using Lie group based distanceis adopted to determine the vehicle motion status. However, the vehicle velocity cannot be derived at this stage due to unknown truesize of vehicle. We illustrate the vehicle motion indication scheme by two examples of real data and summarize the performanceby accessing the results with respect to reference data manually acquired, through which the feasibility and high potentialof airborne LiDAR for urban traffic analysis are verified.     «

This paper presents a generic scheme to analyze urban traffic viavehicle motion indication from airborne laser scanning (ALS) data.The scheme comprises two main steps performed progressively ? vehicleextraction and motion status classification. The step for vehicle extraction is intended to detect and delineate single vehicleinstances as accurate and complete as possible, while the step formotion status classification takes advantage of shape artefacts definedfor moving vehicle model, to classif...     »