Traffic-related data analysis plays an important role in urban andspatial planning. Infrared video cameras have capabilities to operate at day and night and to acquire the scene sampled with videoframe rate, but at the cost of geometric resolution. In this paper,an approach for the estimation of vehicle motion and the assessmentof traffic activity from airborne IR video data is presented. Thisstrategy is based on the separate handling of detection and trackingvehicle in the video, which differs from the common methoddeveloped to extract the object motion. The reason for it is thatstatic vehicles are also intended to be detected. A single vehicledetector is firstly applied to find the vehicles in the image framesof video successively. Sensor movement is compensated by coregisteringthe image sequence under the selected geometric constraint. Afterwards,a progressive grouping concept considering temporal coherence and geometric relation is designed to recover thevehicle trajectories and classify them into static, moving and uncertain type. Image matching and the topology of trajectory areintegrated into grouping process to aid the verification. Testingthe algorithm on an IR video of urban area show us a promising resultthat 83% of moving vehicles are successfully extracted which is able to serve as basis for traffic density analysis.     «

Traffic-related data analysis plays an important role in urban andspatial planning. Infrared video cameras have capabilities to operate at day and night and to acquire the scene sampled with videoframe rate, but at the cost of geometric resolution. In this paper,an approach for the estimation of vehicle motion and the assessmentof traffic activity from airborne IR video data is presented. Thisstrategy is based on the separate handling of detection and trackingvehicle in the video, which differs...     »