Observation of moving vehicles by the plural cameras established freely

Road traffic is increasing every year. Therefore, it is required that the ITS (intelligent transport system) provides the drivers with plural information for smooth and safe driving. As one of ITS techniques, the studies of the traffic flow measurement by image processing have been proposed widely. In the traditional methods, since they have almost observed the traffic flow from one viewpoint, one vehicle has been occluded by another one. Thus, it is impossible that the occluded part of the vehicle cannot be extracted by the image processing. In our proposed method, plural cameras are used to solve the occlusion in the image taken from one viewpoint. On the other hand, since the establishment of cameras are not always placed at the desirable position for the traffic flow observation system, we propose a method to extract the movement of vehicles from the multiple viewpoints. Even if the occluded part of the vehicle exists in the image taken from one viewpoint, our method solves the occlusion by using the image from another viewpoint. Moreover, our method is carried out on condition that the multiple viewpoints are placed freely