engleski

Detection of structural regularities in traffic environments from laser range sensor point clouds

For mobile platform autonomy, it is opportune to use the regularity of structures that appear in human environments, for example the traffic. Examples of such regularities are traffic signs, traffic lanes and road curbs that separate the automobile from the pedestrian area. Laser range sensors are often used sensors on mobile platforms for autonomous driving due to high range measurement accuracy with respect to other sensors. In this thesis an algorithm is developed which can detect objects with structural regularities, like the road curb, from the point cloud measured with laser range sensor and its’ peformance is validated. The algorithm is based on calculating geometric features to detect curbs and a particle filter to filter the detection results.

autonomous driving ; curb detection ; traffic scenarios ; laser sensors

nije evidentirano