Tracking extended objects using extrusion Random Hypersurface Models

As sensor resolution increases, the accuracy and robustness of tracking algorithms can be improved by incorporating more information about the shape of the target object. This raises the need for simple and robust shape models capable of describing detailed objects. In this paper we propose an approach based on Random Hypersurface Models that interprets target shapes as scaled extrusions. This is achieved by combining projection-based models with probabilistic approaches, integrating the strengths of both mechanisms. As extruded shapes such as bottles, boxes, or containers can be extensively found in everyday situations, this approach can be applied for tracking in a large variety of environments.