초록 ▼

An apparatus and a method are disclosed for tracking a plurality of targets (e.g. land-based vehicles) The method can include: for a first time-step, estimating a state of each target; at a second time-step, measuring values for a state of a target; for the second time-step, estimating a state of ea

An apparatus and a method are disclosed for tracking a plurality of targets (e.g. land-based vehicles) The method can include: for a first time-step, estimating a state of each target; at a second time-step, measuring values for a state of a target; for the second time-step, estimating a state of each target using the estimated target states for the first time-step; updating the estimated target states for the second time-step using the measured values; and performing an identity management process to estimate a probability that a particular state measurement corresponds to a particular target by providing a mixing matrix, wherein an element of the mixing matrix is based on an overlap between the updated estimated target states of targets in an underlying state space of the estimated target states.

대표청구항 ▼

1. A method of tracking a plurality of targets, the method comprising: for a first time-step, estimating a state of each target;at a second time-step: measuring values for a state of a target; andmeasuring and updating a value of an identity parameter for the target, wherein the identity parameter a

1. A method of tracking a plurality of targets, the method comprising: for a first time-step, estimating a state of each target;at a second time-step: measuring values for a state of a target; andmeasuring and updating a value of an identity parameter for the target, wherein the identity parameter at least partially distinguishes the target from one or more of the other targets;for the second time-step, estimating a state of each target using the estimated target states for the first time-step;updating the estimated target states for the second time-step using the measured values for the states of the targets; andperforming an identity management process to estimate a probability that a particular state measurement corresponds to a particular target, wherein the identity management process comprises: providing a mixing matrix, an element of the mixing matrix being based on an overlap between the updated estimated target states of targets in an underlying state space of the estimated target states; andwherein the providing of the mixing matrix comprises determining a value for an element of the missing matrix as a function of the state of the particular target at the second time-step, and a set of all state values and identity parameter values measured at time steps up to and including the second time-step. 2. A method according claim 1, wherein the providing of the mixing matrix comprises: determining values for elements {circumflex over (m)}qr, where: {circumflex over (m)}qr=∫√{square root over (pq(x)pr(x))}{square root over (pq(x)pr(x))}dx; pi(x)=p(xi=x|Y) for i=q, r; xi is a state of an ith target at the second time-step; andY is a set of all state values and identity parameter values measured at time steps up to and including the second time-step; andforming the elements into matrix {circumflex over (M)}=[{circumflex over (m)}qr]. 3. A method according to claim 2, wherein determining the mixing matrix comprises: normalising the matrix {circumflex over (M)}. 4. A method according to claim 1, wherein the updating of the estimated target states for the second time-step using the measured values is performed using one or more of: a multi-hypothesis tracking process, a maximum likelihood data association process, and a joint probabilistic data association process. 5. A method according to claim 1, wherein the updating of the estimated target states for the second time-step using the measured values is implemented using one of a particle filter and a Kalman filter. 6. A method according to claim 1, wherein motion of the targets to be tracked is constrained. 7. A method according to claim 6, wherein the targets are land-based vehicles. 8. A method according to claim 1, wherein a path of one of the targets is proximate to a path of at least one different target. 9. A method according to claim 8, wherein the path of one of the targets overlaps a path of at least one different target. 10. A method according to claim 1 wherein estimating a state of each target is performed with a particle filter. 11. A method according to claim 1, wherein a state of a target comprises a value for a position of the target and/or a value for a velocity of the target. 12. Apparatus for tracking a plurality of targets, the apparatus comprising: one or more processors arranged for a first time-step, to estimate a state of each target; andone or more sensors arranged, at a second time-step, to: measure values for a state of a target; andmeasure and update a value of an identity parameter for the target, wherein the identity parameter at least partially distinguishes the target from one or more of the other targets;wherein the one or more processors are configured: for the second time-step, to estimate a state of each target using the estimated target states for the first time-step;to update the estimated target states for the second time-step using the measured values for the states of the targets; andto perform an identity management process to estimate a probability that a particular state measurement corresponds to a particular target; wherein the identity management process includes providing a mixing matrix, an element of the mixing matrix being based on an overlap between the updated estimated target states of targets in an underlying state space of the estimated target states; andwherein the providing of the mixing matrix comprises determining a value for an element of the mixing matrix as a function of the state of the particular target at the second time-step, and a set of all state values and identity parameter values measured at time steps up to and including the second time-step. 13. Apparatus according to claim 12, wherein elements {circumflex over (m)}qr of the mixing matrix have the following values: {circumflex over (m)}qr=∫√{square root over (pq(x)pr(x))}{square root over (pq(x)pr(x))}dx; where: pi(x)=p(xi=x|Y) for i=q, r; xi is a state of an ith target at the second time-step; andY is a set of all state values and identity parameter values measured at time steps up to and including the second time-step; and wherein the elements are formed into matrix {circumflex over (M)}=[{circumflex over (m)}qr]. 14. A non-transitory computer program product encoded with instructions that, when executed by one or more processors, causes a process to be carried out, the process comprising: for a first time-step, estimating a state of each target;at a second time-step: measuring values for a state of a target; andmeasuring and updating a value of an identity parameter for the target, wherein the identity parameter at least partially distinguishes the target from one or more of the other targets;for the second time-step, estimating a state of each target using the estimated target states for the first time-step;updating the estimated target states for the second time-step using the measured values for the states of the targets; andperforming an identity management process to estimate a probability that a particular state measurement corresponds to a particular target, wherein the identity management process comprises: providing a mixing matrix, an element of the mixing matrix being based on an overlap between the updated estimated target states of targets in an underlying state space of the estimated target states; andwherein the providing of the mixing matrix comprises determining a value for an element of the mixing matrix as a function of the state of the particular target at the second time-step, and a set of all state values and identity parameter values measured at time steps up to and including the second time-step. 15. The computer non-transitory program product according to claim 14, wherein the updating of the estimated target states for the second time-step using the measured values is performed using one or more of: a multi-hypothesis tracking process, a maximum likelihood data association process, and a joint probabilistic data association process. 16. The computer non-transitory program product according to claim 14, wherein the updating of the estimated target states for the second time-step using the measured values is implemented using one of a particle filter and a Kalman filter. 17. The computer non-transitory program product according to claim 14, wherein motion of the targets to be tracked is constrained. 18. The computer non-transitory program product according to claim 14, wherein a path of one of the targets is proximate to a path of at least one different target. 19. The computer non-transitory program product according to claim 18, wherein the path of one of the targets overlaps a path of at least one different target. 20. The computer non-transitory program product according to claim 14, wherein estimating a state of each target is performed with a particle filter.