Visual target tracking for autonomous vehicles with the optimal OOSM solution

In this paper, an algorithm is proposed for the vision-based object identification and tracking by autonomous vehicles. In order to estimate the velocity of the tracked object, this algorithm fuses information captured by the vehicle's onboard sensors such as cameras and inertial motion sensors to determine the velocity and position of the object of interest in the world coordinate. However in this multiple sensor fusion based tracking system, the measurements from the same target can arrive out of sequence. This is called the "out-of-sequence" measurement (OOSM) problem. In this paper the 1-step-lag OOSM solution from Bar-Shalom is implemented to solve the problem. The target tracking performance with the OOSM solution is demonstrated through experimental results.