Tracking objects using a laser scanner in driving situation based on modeling target shape

In this paper, we present a new approach to solve the problem of tracking partially hidden objects by a single layer laser scanner. Taking into consideration the shape of the detected object, we have optimized the clustering and the estimation of results. We propose to adapt the detection according to the predicted pose and the occlusions. We have developed an algorithm to detect the security barriers of the road in some conditions. Finally, we have projected our interpretation in the image of a vision system to provide the area of interest to be analyzed and fused with our results. This method is experimented using a single layer laser scanner of type SICK mounted on a vehicle and validated by the means of video data.