System for enhanced object tracking

1. A vehicle radar system comprising a controller and a radar sensor that is arranged to transmit signals and receive reflected signals, where the vehicle radar system is arranged to acquire a plurality of measured radar detections of the reflected signals at different times; where the controller is arranged to engage a tracking algorithm using the measured radar detections as inputs such that at least one track is initialized, the controller is arranged to:

calculate, using the tracking algorithm, a calculated previous radar detection corresponding to the radar sensor and a corresponding previous time that precedes said different times; and to

re-initialize the tracking algorithm using the present measured radar detections in combination with the calculated previous radar detection; and

for the at least one track, for each one of the plurality of measured radar detections, the controller is arranged to calculate a corresponding predicted detection and a corresponding corrected predicted detection, and to furthermore calculate a corresponding distance vector and, an innovation vector-that runs between the present measured radar detection and the corresponding predicted detection, where the innovation vector is constituted by a vector component of a first vector type and of a vector component of a second vector type, where the controller is further arranged to:

calculate a statistical distribution of a plurality of at least one of the first and second vector types;

determine how the calculated statistical distribution is related to another statistical distribution; and/or

determine symmetrical characteristics of the calculated statistical distribution;

and to either maintain or re-initialize the tracking algorithm in dependence of the symmetrical characteristics of the calculated statistical distribution that provides data for a quality measure of the track.

2. A vehicle radar system according to claim 1 further comprising, the plurality of measured radar detections constitutes at least four measured radar detections.

3. A vehicle radar system according to claim 1 further comprising, the tracking algorithm includes a Kalman filter.

4. A vehicle radar system according to claim 1 further comprising, the another statistical distribution is constituted by a predetermined statistical distribution, where the controller is arranged to determine to which extent the calculated statistical distribution deviates from the predetermined statistical distribution, and if the deviation is determined to exceed a predefined threshold, to re-initialize the tracking algorithm.

5. A vehicle radar system according to claim 1 further comprising, the another statistical distribution is constituted by a statistical distribution of components of the corresponding measured radar detections, where the controller is arranged to determine a ratio between the calculated statistical distribution and the another statistical distribution, and if the ratio is determined to deviate beyond a predefined threshold, to re-initialize the tracking algorithm.

6. A method for a vehicle radar system comprising the steps of:

transmitting, by a radar sensor, signals and receiving, by the radar sensor, reflected signals;

acquiring, by the radar sensor, a plurality of measured radar detections at different times;

engaging a tracking algorithm using the measured radar detections as inputs such that at least one track is initialized, for each track,

calculating, using the tracking algorithm, a calculated previous radar detection corresponding to the radar sensor and a corresponding previous time that precedes said different times;

re-initializing the tracking algorithm using the present measured radar detections in combination with the calculated previous radar detection; and

for each one of the plurality of the measured radar detections, the method includes calculating a corresponding predicted detection and a corresponding corrected predicted detection, and calculating a corresponding distance vector and an innovation vector that runs between the present measured radar detection and a corresponding present predicted detection, where the innovation vector is constituted by a vector component of a first vector type and of a vector component of a second vector type, where the method further comprises:

calculating a statistical distribution of a plurality of at least one of the first and second vector types;

determining how the calculated statistical distribution is related to another statistical distribution; and/or

determining symmetrical characteristics of the calculated statistical distribution; and either maintaining or re-initializing the tracking algorithm in dependence of the symmetrical characteristics of the calculated statistical distribution that provides data for quality measures of the track.

7. The method according to claim 6 further comprising, the plurality of measured radar detections constitutes at least four of the measured radar detections.

8. The method according to claim 6 further comprising, the tracking algorithm uses a Kalman filter.

9. The method according to claim 6 , wherein the another statistical distribution is constituted by a predetermined statistical distribution, and wherein the method further comprises determining an extent to which the calculated statistical distribution deviates from the predetermined statistical distribution, and if the deviation is determined to exceed a predefined threshold, to re-initialize the tracking algorithm.

10. The method according to claim 6 , wherein the another statistical distribution is constituted by a statistical distribution of components of the corresponding measured radar detections, and wherein the method further comprises determining a ratio between the calculated statistical distribution and the another statistical distribution, and if the ratio is determined to deviate beyond a predefined threshold, to re-initialize the tracking algorithm.