Mapping of position measurements to objects using a movement model
A position tracking system may include a processor and a memory coupled to the processor. The memory may include instructions that, when loaded and executed by the processor, cause the processor to receive a plurality of measurements from a sensor and map a location of an object to a measurement using movement models. The mapping may be based upon a cost computed from movement models, the measurement, and the location.
1. A position tracking system, comprising:
at least one processor;
at least one computer-readable medium communicatively coupled to the processor, the medium including instructions, when loaded and executed by the processor, for causing the processor to:
receive a plurality of measurements from one or more sensors representing a single instance in time; and
map locations of objects to measurements using movement models, the movement models include stochastic models based on a Gaussian distribution function applied to a Newtonian movement, wherein the mapping is based upon costs computed from the movement models, the measurement data, and the locations, including:
for a given measurement, determine whether the given measurement is a location for a first object or a second object based upon costs computed from the movement models, the measurement data, and the locations.
2. The position tracking system according to claim 1 , wherein the measurements include position data.
3. The position tracking system according to claim 1 , wherein the movement models are based upon the past trajectory of the objects.
4. The position tracking system according to claim 1 , wherein the movement models include probability variances that are different between a direction of movement of the objects and a direction orthogonal to movement of the objects.
5. The position tracking system according to claim 1 , wherein the movement models include probabilities that are greater for a direction of movement of the objects than for a direction orthogonal to movement of the objects.
6. The position tracking system according to claim 1 , wherein variances of the movement models to determine probabilities with respect to a direction of movement of the objects and a direction orthogonal to movement of the objects are taken from a Kalman filter.
7. At least one non-transitory computer-readable medium comprising instructions, the instructions, when loaded and executed by a processor, cause the processor to:
receive a plurality of measurements from one or more sensors representing a single instance in time; and
map locations of objects to measurements using movement models, the movement models include stochastic models based on a Gaussian distribution function applied to a Newtonian movement, wherein the mapping is based upon costs computed from the movement models, the measurements, and the locations, including:
for a given measurement, determine whether the given measurement is a location for a first object or a second object based upon costs computed from the movement models, the measurement data, and the locations.
8. The medium according to claim 7 , wherein the measurement data includes position data.
9. The medium according to claim 7 , wherein the movement models are based upon the past trajectory of the objects.
10. The medium according to claim 7 , wherein the movement models include probability variances that are different between a direction of movement of the objects and a direction orthogonal to movement of the objects.
11. The medium according to claim 7 , wherein the movement models include probabilities that are greater for a direction of movement of the objects than for a direction orthogonal to movement of the objects.
12. The medium according to claim 7 , wherein variances of the movement models to determine probabilities with respect to a direction of movement of the objects and a direction orthogonal to movement of the objects are taken from a Kalman filter.
13. A method, comprising:
receiving a plurality of measurements from one or more sensors representing a single instance in time; and
mapping a location of objects to measurements using movement models, the movement models include stochastic models based on a Gaussian distribution function applied to a Newtonian movement, wherein the mapping is based upon a costs computed from movement models, the measurements, and the locations, including:
for a given measurement, determining whether the given measurement is a location for a first object or a second object based upon costs computed from the movement models, the measurement data, and the locations.
14. The method according to claim 13 , wherein the measurements include position data.
15. The method according to claim 13 , wherein the movement models are based upon a past trajectory of the objects.
16. The method according to claim 13 , wherein the movement models include probability variances that are different between a direction of movement of the objects and a direction orthogonal to movement of the objects.
17. The method according to claim 13 , wherein the movement models include probabilities that are greater for a direction of movement of the objects than for a direction orthogonal to movement of the objects.