Student Research Highlight: Simultaneous Tracking and Shape Estimation of Extended Targets

Target tracking algorithms are usually based on the assumption that the target extent is small compared to the measurement noise; hence, the target is modeled as a mathematical point. However, if the target extent is rather large, the target may cause multiple sensor measurements from different spatially distributed reflection centers. In this case, the modeling of the target extent is essential. In particular, the author looks at the random hypersurface model and its role in tracking; the tracking method is evaluated using a Microsoft® Kinect™ sensor as an example.