Various embodiments are described herein for a track quality based multi-target tracker and an associated method. The method includes associating a measurement with a track, generating measurement association statistics for the track, generating and updating a track quality value for a track based o
Various embodiments are described herein for a track quality based multi-target tracker and an associated method. The method includes associating a measurement with a track, generating measurement association statistics for the track, generating and updating a track quality value for a track based on a measurement-to-track association likelihood, and updating track lists based on the track quality value and the measurement association statistics of the tracks in these lists. The tracker includes structure for carrying out this method.
대표청구항▼
The invention claimed is: 1. A tracking module for tracking a detected target, the tracking module comprising: a track association module configured to associate a measurement with a track and generating measurement association statistics for the track; a track quality module configured to generate
The invention claimed is: 1. A tracking module for tracking a detected target, the tracking module comprising: a track association module configured to associate a measurement with a track and generating measurement association statistics for the track; a track quality module configured to generate and update a track quality value for a track based on a measurement-to-track association likelihood; and a track list update module configured to confirm and delete tracks in a track list comprising a list of confirmed tracks and a list of unobservable tracks based on the track quality value and the measurement association statistics of the tracks in this track list, wherein the track list update module is configured to move a confirmed track to the list of unobservable tracks if the measurement association statistics of the confirmed track indicates no measurement associations in the last nna time steps where nna is an integer, and to process the list of unobservable tracks by deleting the unobservable tracks with a track quality value less than a first track quality threshold value. 2. The tracking module of claim 1, wherein the track list further comprises a list of initial tracks. 3. The track module of claim 2,wherein the tracking module comprises a track initiator configured to generate a preliminary version of the track. 4. The tracking module of claim 3, wherein, for a current time step, the track association module is configured to associate measurements from a measurement list with the list of confirmed tracks, then the list of unobservable tracks, and then the list of initial tracks. 5. The tracking module of claim 3, wherein, for a current time step, the track association module is configured to associate measurements from a measurement list with the list of confirmed tracks and remove the associated measurements from the measurement list to generate a first updated measurement list, then associate measurements from the first updated measurement list with the list of unobservable tracks and remove the associated measurements from the first updated measurement list to generate a second updated measurement list, then associate measurements from the second updated measurement list and a third updated measurement list corresponding to a previous time step with the list of initial tracks and remove the associated measurements from the second updated measurement list to generate a third updated measurement list. 6. The tracking module of claim 3, wherein the track list update module is configured to process the list of initial tracks by deleting the initial tracks with a track quality value less than a second track quality threshold value. 7. The tracking module of claim 6, wherein the track list update module is configured to move a remaining initial track to the list of confirmed tracks if the remaining initial track has a track quality value at the current time step and a track quality value at a previous time step that are both greater than a third track quality threshold value, and measurement association statistics that indicate a number of associations greater than or equal to ni where ni is an integer. 8. The tracking module of claim 1, wherein the track list update module is further configured to process the list of unobservable tracks by moveing unobservable tracks to the list of confirmed tracks with a track quality value greater than a second track quality threshold value and measurement association statistics that indicate a number of new associations greater than or equal to na where na is an integer. 9. The tracking module of claim 3, wherein the track quality module is configured to predict the track quality value at a future time step P(k+1|k) given a track quality value at a current time step by multiplying a probability of a target existing for the track with the track quality value after an update at the current time step. 10. A tracking module for tracking a detected target, the tracking module comprising: a track association module configured to associate a measurement with a track and generating measurement association statistics for the track; a track quality module configured to generate and update a track quality value for a track based on a measurement-to-track association likelihood; a track list update module configured to update track lists comprising a list of initial tracks, a list of confirmed tracks, and a list of unobservable tracks based on the track quality value and the measurement association statistics of the tracks in these lists; and a track initiator configured to generate a preliminary version of the track, wherein the track quality module is configured to predict the track quality value at a future time step P(k+1|k) given a track quality value at a current time step by multiplying a probability of a target existing for the track with the track quality value after an update at the current time step and when the track is associated with a measurement at a future time step, the track quality module is configured to calculate a track quality value P(k+1|k) by calculating a first sum by adding a likelihood that the target corresponding to the track exists and the associated measurement is from the target with a likelihood that the target exists and the associated measurement is a false alarm, calculating a second sum by adding the first sum with a likelihood that the target does not exist and the associated measurement is a false alarm, and dividing the first sum by the second sum. 11. The tracking module of claim 10, wherein when the track is associated with a measurement at a future time step, the track quality module is further configured to calculate a track quality value P(k+1|k+1) according to where πd1 is a total detection probability inside a detection gate for the target, ƒ(z(k+1)|x(k+1|k)) is a likelihood of a measurement z(k+1) given a predicted position of the target x(k+1|k), ƒ(z(k+1)|Ø) is a density of false alarm at z(k+1) and k is the current time step. 12. A tracking module for tracking a detected target, the tracking module comprising: a track association module configured to associate a measurement with a track and generating measurement association statistics for the track; a track quality module configured to generate and update a track quality value for a track based on a measurement-to-track association likelihood; a track list update module configured to update track lists comprising a list of initial tracks, a list of confirmed tracks, and a list of unobservable tracks based on the track quality value and the measurement association statistics of the tracks in these lists; and a track initiator configured to generate a preliminary version of the track, wherein the track quality module is configured to predict the track quality value at a future time step P(k+1|k) given a track quality value at a current time step by multiplying a probability of a target existing for the track with the track quality value after an update at the current time step and when the track is not associated with a measurement at a future time step, the track quality module is configured to calculate a track quality value P(k+1|k+1) by calculating a first sum by adding a likelihood that the target corresponding to the track exists and it is not detected with a likelihood that the target does not exist, and dividing the likelihood that the target corresponding to the track exists by the first sum. 13. The tracking module of claim 12, wherein when the track is not associated with a measurement at a future time step, the track quality module is further configured to calculate a track quality value P(k+1|k+1) according to: where πd2 is a total detection probability inside the detection gate. 14. A method of detecting a target, the method comprising: associating a measurement with a track; generating measurement association statistics for the track; generating and updating a track quality value for a track based on a measurement-to-track association likelihood; and confirming and updating tracks in a track list comprising a list of confirmed tracks and a list of unobservable tracks based on the track quality value and the measurement association statistics of the tracks in this track list; moving a confirmed track to the list of unobservable tracks if the measurement association statistics of the confirmed track indicates no measurement associations in the last nna time steps where nna is an integer; and processing the list of unobservable tracks by deleting the unobservable tracks with a track quality value less than a first track quality threshold value. 15. The method of claim 14, wherein the track list further comprises a list of initial tracks. 16. The method of claim 15. wherein the method further comprises generating a preliminary version of the track. 17. The method of claim 16, wherein, for a current time step, the method comprises associating measurements from a measurement list with the list of confirmed tracks, then the list of unobservable tracks, and then the list of initial tracks. 18. The method of claim 16, wherein, for a current time step, the method comprises: associating measurements from a measurement list with the list of confirmed tracks; removing the associated measurements from the measurement list to generate a first updated measurement list; associating measurements from the first updated measurement list with the list of unobservable tracks; removing the associated measurements from the first updated measurement list to generate a second updated measurement list; associating measurements from the second updated measurement list and a third updated measurement list corresponding to a previous time step with the list of initial tracks; and removing the associated measurements from the second updated measurement list to generate a third updated measurement list. 19. The method of claim 16, wherein the method comprises processing the list of initial tracks by deleting the initial tracks with a track quality value less than a first second track quality threshold value. 20. The method of claim 19, wherein the method comprises moving a remaining initial track to the list of confirmed tracks if the remaining initial track has a track quality value at the current time step and a track quality value at a previous time step that are both greater than a third track quality threshold value, and measurement association statistics that indicate a number of associations greater than or equal to ni where ni is an integer. 21. The method of claim 14, wherein the method comprises processing the list of unobservable tracks by moving unobservable tracks to the list of confirmed tracks with a track quality value greater than a second track quality threshold value and measurement association statistics that indicate a number of new associations greater than or equal to na where na is an integer. 22. The method of claim 16, wherein the method comprises predicting the track quality value at a future time step P(k+1|k) given a track quality value at a current time step by multiplying a probability of a target existing for the track with the track quality value after an update at the current time step. 23. A method of detecting a target, the method comprising: associating a measurement with a track; generating measurement association statistics for the track; generating and updating a track quality value for a track based on a measurement-to-track association likelihood; updating track lists comprising a list of initial tracks, a list of confirmed tracks, and list of unobservable tracks based on the track quality value and the measurement association statistics of the tracks in these lists; generating a preliminary version of the track; and predicting the track quality value at a future time step P(k+1|k) given a track quality value at a current time step by multiplying a probability of a target existing for the track with the track quality value after an update at the current time step, wherein when the track is associated with a measurement at a future time step, the method comprises calculating a track quality value P(k+1|k+1) by calculating a first sum by adding a likelihood that the target corresponding to the track exists and the associated measurement is from the target with a likelihood that the target exists and the associated measurement is a false alarm, calculating a second sum by adding the first sum with a likelihood that the target does not exist and the associated measurement is a false alarm, and dividing the first sum by the second sum. 24. The method of claim 23, wherein when the track is associated with a measurement at a future time step, the method further comprises calculating a track quality value P(k+1|k+1) according to where πdis a total detection probability inside a detection gate for the target, ƒ(z(k+1)|x(k+1|k)) is a likelihood of a measurement z(k+1) given a predicted position of the target x(k+1|k), ƒ(z(k+1)|Ø) is a density of false alarm at z(k+1) and k is the current time step. 25. A method of detecting a target, the method comprising: associating a measurement with a track; generating measurement association statistics for the track; generating and updating a track quality value for a track based on a measurement-to-track association likelihood; updating track lists comprising a list of initial tracks, a list of confirmed tracks, and list of unobservable tracks based on the track quality value and the measurement association statistics of the tracks in these lists; generating a preliminary version of the track; and predicting the track quality value at a future time step P(k+1|k) given a track quality value at a current time step by multiplying a probability of a target existing for the track with the track quality value after an update at the current time step, wherein when the track is not associated with a measurement at a future time step, the method comprises calculating a track quality value P(k+1|k+1) by calculating a first sum by adding a likelihood that the target corresponding to the track exists and it is not detected with a likelihood that the target does not exist, and dividing the likelihood that the target corresponding to the track exists by the first sum. 26. The method of claim 25, wherein when the track is not associated with a measurement at a future time step, the method further comprises calculating a track quality value P(k+1|k+1) according to: where πd2 is a total detection probability inside the detection gate. 27. A radar system comprising: hardware configured to transmit radar pulses, receive reflected radar pulses, and process the reflected radar pulses to provide pre-processed radar data; circuitry configured to process the pre-processed radar data to detect targets and generate plots of the detected targets; and a tracking module configured to receive the plots and generate tracks belonging to several track lists, wherein for a given track the tracking module is configured to associate a measurement with the track and generate measurement association statistics, generate and update a track quality value for the track, determine which track list the track belongs to based upon the track quality value and the measurement association statistics of the track, and confirm and delete tracks in a list of confirmed tracks and a list of unobservable tracks based on the track quality value and the measurement association statistics for the tracks in the list of unobservable tracks, wherein the track list update module is configured to move a confirmed track to the list of unobservable tracks if the measurement association statistics of the confirmed track indicates no measurement associations in the last nna time steps where nna is an integer, and to process the list of unobservable tracks by deleting the unobservable tracks with a track quality value less than a first track quality threshold value.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (34)
Tamburino,Louis A., ATR trajectory tracking system (A-Track).
Wyschogrod Daniel (Brookline MA) Wood Loren (Lexington MA) Sturdy James L. (Leominster MA) Schultz Hayden B. (Maynard MA) Sasiela Richard J. (Sudbury MA) Marquis Douglas V. (Framingham MA) Harman ; I, Airport surface surveillance system.
Blackman Samuel S. (Los Angeles CA) Dempster Robert J. (Los Angeles CA), Method and apparatus for continuous time representation of multiple hypothesis tracking data.
Beadle,Edward R.; Dishman,John F.; Anderson,Richard H.; Anderson,Paul D., Method and system for tracking eigenvalues of matrix pencils for signal enumeration.
Driessen, Hans; Meijer, Wietze; Zwaga, Jitse, Multi-targets detection method applied in particular to surveillance radars with multi-beamforming in elevation.
Joshua Michael Wurman ; Mitchell Alfred Randall, Radar system having multiple simultaneously transmitted beams operating in a scanning mode to identify scatterers.
Krikorian,Kapriel V.; Rosen,Robert A., Technique for cancellation of elevated clutter for the detection of fixed and ground moving targets under trees.
Testa, Loretta A.; Blackman, Samuel S.; Huffaker, Ray B.; Durand, Catherine; Hacobian, Kristine, Apparatus and method for processing electronic intelligence (ELINT) and radar tracking data.
Hiemenz, Robert E.; Thomas, Jr., Daniel D., Constant pulse repetition frequency techniques for eliminating second time around returns in pulsed doppler radar.
Wang, Jian; Brookner, Eli; Drake, Peter R.; Fournier, Bradley; Ponsford, Anthony M.; Chang, Yueh-Chi, Methods and apparatus for 3D radar data from 2D primary surveillance radar and passive adjunct radar.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.