On-road target tracking using radar and image sensor based measurements

On-road target tracking using radar and image sensor based measurements is studied. A novel 2D road coordinate representation of an on-road moving target is introduced. A natural description of target longitudinal and lateral maneuvering behavior in 2D road coordinates is given using multiple models. An improved mean-adaptive acceleration model is utilized for describing longitudinal maneuver modes of motion. Three IMM-based estimators are developed that use different schemes for fusion of radar and image sensor based measurement data: centralized, distributed, and sequential. Simulation results are presented that illustrate the performance of the proposed estimators in general, and demonstrate their improved capabilities as compared with a known 1D road coordinate (mileage) estimator, in particular.