Track associations at least partially based on low confidence detections

Abstract

This document describes techniques for performing track associations at least partially based on low confidence detections. For object trackers, which rely on measurement detections that are associated with a reported confidence, there is no direct tradeoff between a true positive track rate and a false positive track rate that applies to improving the accuracy of state estimates of tracks. To increase the true positive track rate while reducing the false positive track rate, a parameter is maintained for each track. Referred to as Probability of Existence (PoE), it is an estimate of likelihood that a real object exists with a true state that approximates an estimated state for that track. By considering PoE in combination with the reported confidence in the measurement detections being used, object tracking using radar and other sensors technologies is improved, so real-objects are reported more-quickly and accurately, and false objects are reported less often.