Segmentation of road edges from a vehicle-mounted imaging radar

This work treats a problem arising in intelligent vehicles and highway systems (IVHS), specifically in automatic road following, collision avoidance, and maneuver control. A millimeter-wave radar is placed on the front of the vehicle and an image of the radar backscatter of the terrain is acquired in polar coordinates. This image contains both road and offroad scatter components which must be segmented from each other. The radar sensor acquires the scene in polar coordinates while constraints on the road edges are naturally formulated in the Cartesian cartographic domain. One novelty of our approach is to apply the road constraints in polar coordinates which allows us to estimate the road edge parameters directly from recorded data. Another novelty is to construct an estimator which minimizes a cost criterion which is largely insensitive to the off-road scatter components. Numerical results are given for real data (L-band radar images of a south-east Michigan roadway) which indicate the accuracy and robustness of our approach