초록 ▼

This invention provides a system and method for automatically inferring when a target that is being tracked by an aerial vehicle is doing something significant (e.g. stopping suddenly, changing direction quickly or getting out of track view), and consequently alerting an operator. The alerting syste

This invention provides a system and method for automatically inferring when a target that is being tracked by an aerial vehicle is doing something significant (e.g. stopping suddenly, changing direction quickly or getting out of track view), and consequently alerting an operator. The alerting system also provides a classification of what the target is doing. It frees the operator from continuously monitoring the imagery stream so the operator can perform other tasks.

대표청구항 ▼

1. A method comprising: determining, with a processing unit, global inertial coordinates of a center of a footprint of a sensor and at least two vertices of the footprint, wherein the sensor is equipped on an aerial vehicle;computing, with the processing unit, a track metric as a function of how clo

1. A method comprising: determining, with a processing unit, global inertial coordinates of a center of a footprint of a sensor and at least two vertices of the footprint, wherein the sensor is equipped on an aerial vehicle;computing, with the processing unit, a track metric as a function of how close a target is to the center of the footprint based on the global inertial coordinates of the center and the at least two vertices of the footprint;comparing, with the processing unit, the track metric to a threshold value; andgenerating, with the processing unit, an alert for a remote operator if the track metric falls outside the threshold value. 2. The method of claim 1, wherein the threshold value is based on a maximum airspeed of the aerial vehicle. 3. The method of claim 1, wherein the threshold value is based on a minimum turn radius of the aerial vehicle. 4. The method of claim 1, further comprising calculating a first time derivative and a second time derivative of the track metric and generating the alert if the track metric, the first time derivative or the second time derivative exceeds the threshold value. 5. A system comprising: a communication interface; anda processing unit configured to determine global inertial coordinates of a center of a footprint of a sensor equipped on an aerial vehicle and at least two vertices of the footprint, compute a track metric as a function of how close a target is to a center of the footprint based on the global inertial coordinates of the center and the at least two vertices of the footprint, compare the track metric to a threshold value, and control the communication interface to alert a remote operator if the track metric falls outside the threshold value. 6. The system of claim 5, wherein the processing unit is configured to compare the track metric to the threshold value that is based on a maximum airspeed of the aerial vehicle or a minimum turn radius of the aerial vehicle. 7. A method comprising: determining, with a processing unit, a position of a target relative to a center of a sensor footprint;determining, with the processing unit, a distance from the center of the sensor footprint to a side of the sensor footprint that is closest to the target;calculating, with the processing unit, one or more instantaneous track metrics based on (i) the position of the target relative to the center of the sensor footprint; and (ii) the distance from the center of the sensor footprint to the side of the sensor footprint that is closest to the target;calculating, with the processing unit, a track metric as a weighted moving average of the instantaneous track metric;comparing, with the processing unit, the track metric to a threshold value; andgenerating, with the processing unit, an alert for a remote operator if the track metric is outside of the threshold value. 8. The method of claim 1, wherein determining the global inertial coordinates of the center and the at least two vertices of the footprint comprises: determining local coordinates of the center and the at least two vertices of the footprint; andtransforming the local coordinates to the global inertial coordinates based on a first attitude angle of the sensor and a second attitude angle of the aerial vehicle. 9. The method of claim 8, wherein determining local coordinates of the center and the at least two vertices of the footprint comprises determining local coordinates of the center and the at least two vertices of the footprint based on an angle of a field of view of the sensor. 10. The method of claim 1, further comprising scaling the global inertial coordinates of the center and the at least two vertices of the footprint by a height the aerial vehicle is flying above the target, wherein computing the track metric comprises computing the track metric based on the scaled global inertial coordinates of the center and the at least two vertices of the footprint. 11. The method of claim 1, wherein computing the track metric as a function of how close a target is to the center of the footprint comprises: determining a first distance between the target and the center of the footprint of the sensor; anddetermining a second distance from the center of the footprint to a side of the footprint closest to the target, wherein the track metric comprises a value determined by dividing the first distance by the second distance. 12. The method of claim 11, wherein the threshold value is 0.9. 13. The method of claim 4, wherein generating the alert comprises: generating a first alert that indicates the aerial vehicle is about to lose track of the target if the track metric is 0.9; andgenerating a second alert that indicates the target stopped, changed direction or engaged in motion maneuvers if both the first and second time derivatives of the track metric exceed the threshold value. 14. The method of claim 1, wherein computing the track metric comprises: calculating, over time, a plurality of instantaneous track metrics as the function of how close the target is to the center of the footprint; anddetermining the track metric as a weighted moving average of the plurality of instantaneous track metrics. 15. The method of claim 14, wherein weight values are used to determine the weighted moving average. 16. The system of claim 5, wherein the processing unit is configured to determine the global inertial coordinates of the center and the at least two vertices of the footprint by at least determining local coordinates of the center and the at least two vertices of the footprint based on an angle of a field of view of the sensor, and transforming the local coordinates to the global inertial coordinates based on a first attitude angle of the sensor and a second attitude angle of the aerial vehicle. 17. The system of claim 5, wherein the processing unit is configured to scale the global inertial coordinates of the center and the at least two vertices of the footprint by a height the aerial vehicle is flying above the target, and compute the track metric based on the scaled global inertial coordinates of the center and the at least two vertices of the footprint. 18. The system of claim 5, wherein the processing unit is configured to calculate a first time derivative and a second time derivative of the track metric, wherein the processing unit is configured to generate the alert by at least: determining if the track metric exceeds the threshold value and generating a first alert that indicates the aerial vehicle is about to lose track of the target if the track metric is 0.9; anddetermining if both the first and second time derivatives of the track metric exceed the threshold value and generating a second alert that indicates the target stopped, changed direction or engaged in motion maneuvers if both the first and second time derivatives of the track metric exceed the threshold value. 19. The system of claim 5, wherein the processor is configured to compute the track metric by at least determining a first distance between the target and the center of the footprint of the sensor, and determining a second distance from the center of the footprint to a side of the footprint closest to the target, wherein the track metric comprises a value determined by dividing the first distance by the second distance. 20. The system of claim 5, wherein the processing unit is configured to compute the track metric by at least calculating, over time, a plurality of instantaneous track metrics as the function of how close the target is to the center of the footprint, and determining the track metric as a weighted moving average of the plurality of instantaneous track metrics.