Automatic Road Inventory Using LiDAR

Abstract Road inventory is very important for effective transportation management. This process is usually done by a technician in the field, manually from obtained aerial/satellite images or semi-automatically by a software application. The first two options are very time consuming, hence expensive. Many companies therefore try to process at least part of this task automatically. The road inventory process comprises an identification of objects that can be found either on the road or in the road proximity. Examples include road signs, road markings, guardrails and many more. We can register much information about these objects, such as their position, condition or type. Generally, there are two sources for the extraction of information needed for the inventory. The first source is a set of images captured by a camera. The second source is data captured by a LiDAR. Either of them can provide different information; therefore, the choice of the source must be made with regard to the required information. In our article, we compare information that can be obtained from camera images and LiDAR measurements. This comparison is presented on three example objects: traffic signs, road markings and general pole-shaped objects (e.g. city lights or trees). Further, we describe a process based on our algorithm that detects traffic signs in LiDAR measurement and transforms the results to a common format used in geographic information systems. We test our method on an approximately two-kilometer long road in an urban area.