Abstract
One of the most important tacks for tracking and trajectory planning is how to represent suitably objects, evolving in complex environments (for example urban environments), in which different objects (pedestrians, bikes, vehicles) move unpredictably and close to each other. In the framework of the development of a multiple objects tracking system using multisensor fusion, this paper presents an oriented bounding box (OBB) representation. Two variants of the OBB creation algorithm, depending on how objects contours are determined, are proposed. This two variants are evaluated and compared in terms of complexity and accuracy using measurements coming from a laser range finder.