Motion classification for cross traffic in urban environments using laser and radar

In this paper, an approach for motion classification for laser sensors is presented concentrating on urban environments. In these complex environments the algorithm has to match both cross traffic and structures in parallel to the road, as well as objects starting and stopping moving. The requirements on sensors and algorithms for handling urban traffic are specified and some basic definitions in the context of motion classification are introduced in this paper. Our new approach extends the limits of a consistency-based motion classification with a laser sensor by a track-before-detect approach in a first step and, in a second step, by an additional source. This additional source is a radar sensor whose data is treated in a special way to be able to deal with cross traffic without any tracking. This approach runs online and has been validated in crowded urban environment.