System for enhanced object tracking
A vehicle radar system ( 3 ) including a control unit arrangement ( 8 ) and at least one radar sensor arrangement ( 4 ) arranged to acquire a plurality of measured radar detections (z t , z t+1 ) at different times. The control unit arrangement ( 8 ) engages a tracking algorithm using the present measured radar detections (z t , z t+1 ) as input. For each track, for each one of a plurality of measured radar detections (z t , z t+1 ), the control unit arrangement ( 8 ) calculates a corresponding predicted detection (x t|t−1| , x t+1|t| ) and a corrected predicted detection (x t|t| , x t+1|t+1| ), and calculates an innovation vector ( 19, 19 ) constituted by a first vector type ( 18 a , Δφ) and a second vector type ( 18 b , Δr). The control unit arrangement ( 8 ) calculates a statistical distribution ( 24; σ inno,φ , σ inno,r ) for at least one of the vector types ( 18 a, Δφ; 18 b , Δr) and to determine how it is related to another statistical distribution ( 25; σ meas,φ , σ meas,r ); and/or to determine its symmetrical characteristics. The tracking algorithm is maintained or re-initialize in dependence of result.
1. A vehicle radar system comprising, a control unit arrangement and at least one radar sensor arrangement 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 control unit arrangement is arranged to engage a tracking algorithm using the measured radar detections as inputs such that at least one track is initialized, for the track and for each one of a plurality of measured radar detections, the control unit arrangement is arranged to calculate a corresponding predicted detection and a corresponding corrected predicted detection, and to calculate a corresponding distance vector and an innovation vector, that runs between a 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 control unit arrangement is 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; or
determine symmetrical characteristics of the calculated statistical distribution;
and to either maintain or re-initialize the tracking algorithm in dependence of the determined result that provides data for quality measures of the track.
2. The vehicle radar system according to claim 1 further comprising, the another statistical distribution is constituted by a predetermined statistical distribution, where the control unit arrangement 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.
3. The 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 control unit arrangement 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.
4. The vehicle radar system according to claim 1 further comprising, for a new track, the control unit arrangement is arranged to:
calculate a calculated previous radar detection that precedes the present measured radar detections; and to
re-initialize the tracking algorithm using the present measured radar detections in combination with the calculated previous radar detection.
5. The vehicle radar system according to claim 4 further comprising, the plurality of measured radar detections constitutes at least four measured radar detections.
6. The vehicle radar system according to claim 1 further comprising, the tracking algorithm includes a Kalman filter.
7. A method for a vehicle radar system, where the method comprises the steps of:
transmitting signals and receiving reflected signals;
acquiring a plurality of measured radar detections at different times;
engaging a tracking algorithm using the measured radar detections as input such that at least one track is initialized, for the track and for each one of a plurality of measured radar detections, the method includes:
calculating a corresponding predicted detection and a corresponding corrected predicted detection;
calculating a corresponding distance vector, an innovation vector, running between a 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;
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 or determine symmetrical characteristics of the calculated statistical distribution; and
determining if the tracking algorithm should be re-initialized in dependence of the determined result that provides data for quality measures of the track; and if the re-initialized tracking algorithm is determined not to be re-initialized, the method includes maintaining the tracking algorithm.
8. The method according to claim 7 further comprising, that another statistical distribution is constituted by a predetermined statistical distribution, where the method includes determining to which extent the calculated statistical distribution deviates from the predetermined statistical distribution, and if the deviation is determined to exceed a predefined threshold, the method includes re-initializing the tracking algorithm.
9. The method according to claim 7 further comprising, the another statistical distribution is constituted by a statistical distribution of components of the corresponding measured radar detections, where the method includes 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, the method includes re-initializing the tracking algorithm.
10. The method according to claim 7 further comprising, for a new track, the method includes:
calculating a calculated previous radar detection that precedes the present measured radar detections; and
re-initializing the tracking algorithm using the present measured radar detections in combination with the calculated previous radar detection.
11. The method according to claim 10 further comprising, the plurality of measured radar detections constitutes at least four measured radar detections.
12. The method according to claim 7 further comprising, the tracking algorithm uses a Kalman filter.