Modified smoothing data association for target tracking in clutter

Abstract

Tracking an unknown target in noisy environment is difficult especially when the target is maneuvering and has unknown trajectory. Smoother uses measurements from future scans to estimate the target state in past scan. This requires the fusion of forward and backward prediction. However, due to uncertain target motions and low detection probabilities, backward prediction could not associate with forward prediction which results in inequitable fusion pair and thus, smoothing performance could not be improved. To cope with these difficulties, the proposed algorithm modifies the fixed-lag smoothing data association based on the integrated probabilistic data association (IPDA) algorithm and a new algorithm called modified smoothing IPDA (MSIPDA) is developed. MSIPDA utilizes two IPDA filters to obtain forward IPDA (fIPDA) track and backward (bIPDA) track estimation in each scan. Each fIPDA prediction generates multiple fusion pairs in association with bIPDA multi-track prediction. These fusion pairs are created in the form of components. As a result, multiple smoothing components are formed with their smoothing component data association probabilities for computing MSIPDA track components state estimate. In addition, the smoothing data association probabilities upgrade the forward track which makes the forward track more powerful for target tracking in clutter. The numerical assessment of MSIPDA is verified using simulations. The result shows significant false track discrimination performance in comparison to existing algorithms.