Vehicle detection and tracking with 2D laser range finders

Dynamic environment perception is an important component for unmanned ground vehicle navigation. In this paper, we focus on the vehicle detection and tracking with two low cost 2D laser range finders. Firstly, a foreground segmentation method is proposed based on a combination of the time cue and motion cue. The modified laser beam model is proposed for the tilted 2D laser range finder in the foreground segmentation. Then, the vehicle detection and preliminary tracking is realized by the modified measurement model. Finally, a new precise tracking method is proposed to refine the preliminary tracking results. Qualitative and quantitative experiments are carried out in real dynamic environment, and the result shows that the proposed method can detect and track the vehicle accurately.