Presenters: Karthik Ravindran; Nigam Katta
Multi-Target tracking is the problem of estimating the kinematic parameters of moving targets using sensor measurements. The number of targets can vary from one or to many. Tracking multiple targets is more challenging than tracking a single target. The sensor can be static or moving. For autonomous navigation, target tracking is essential for environment perception.
This webinar focuses on the two main components:
Kalman filter is the most widely used estimator for tracking. Data association addresses the issue of mapping the sensor measurements to targets in the FOV, and for discriminating sensor measurements from clutter.