Probability weighted centroid tracker

• US 20030026454A1
• Filed: 06/29/2001
• Published: 02/06/2003
• Est. Priority Date: 06/29/2001
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Lewins, Lloyd J., Albus, John E., Schacht, Julie R., Groves, Gillian K.
• Granted Patent: US 6,895,102 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

In accordance with one aspect of the present invention, a system for tracking a target is provided that includes an image sensor mounted to a gimbal for acquiring an image, wherein the image includes a plurality of pixels representing the target and a background. The system further includes a motor for rotating the gimbal and an autotracker electrically coupled to the image sensor and the motor. The autotracker includes a probability map generator for computing a probability that each of the plurality of pixels having a particular intensity is either a portion of the target or a portion of the background, a pixel processor in communicative relation with the probability map generator for calculating a centroid of the target based upon the probabilities computed by the probability map generator, and a controller in communicative relation with the pixel processor for generating commands to the motor based upon the centroid.

Claims

1. A system for tracking a target comprising:

(a) an image sensor mounted to a gimbal for acquiring an image, wherein the image includes a plurality of pixels representing the target and a background;

(b) a motor for rotating the gimbal; and

(c) an autotracker electrically coupled to the image sensor and the motor, the autotracker including

(i) a probability map generator for computing a probability that each of the plurality of pixels having a particular intensity is either a portion of the target or a portion of the background;

(ii) a pixel processor in communicative relation with the probability map generator for calculating a centroid of the target based upon the probabilities computed by the probability map generator; and

(iii) a controller in communicative relation with the pixel processor for generating commands to the motor based upon the centroid.

2. A system according to claim 1, wherein the probability map generator creates a map of the computed probabilities.

3. A system according to claim 2, wherein the probability map generator shapes the map in order to reduce the effect on the calculation of the centroid of those pixels that make up a portion of the background.

4. A system according to claim 1, wherein the pixel processor calculates a silhouette of the target based upon the probabilities computed by the probability map generator.

5. A system according to claim 4, wherein the autotracker system further includes a gate controller in communicative relation with the pixel processor, the gate controller using the silhouette to size an inner gate and the centroid to locate the gate around the target.

6. A system according to claim 5, wherein the gate controller positions a track gate and an outer gate in concentric relation with the inner gate, the track gate and the outer gate being a predetermined number of pixels larger than the inner gate.

7. A system according to claim 6, wherein the pixel processor calculates the number of pixels representing the target that are located in a first region between the outer gate and the track gate, the calculation being based on the probability computed by the probability map generator.

8. A system according to claim 7, wherein the pixel processor calculates the number of pixels representing the target that are located in a second region between the track gate and the inner gate, the calculation being based on the probability computed by the probability map generator.

9. A system according to claim 8, further comprising a status processor in communicative relation with the pixel processor, the status processor determining a quality of the system'"'"'s track of the target based upon the silhouette and the number of pixels representing the target that are determined to be located in the first region and the second region.

10. A system according to claim 1, wherein the autotracker is implemented on at least one microprocessor.

12. A method according to claim 1, wherein the step of generating includes assigning a value of either zero or one to the probability that a particular intensity within the selected consecutive range of intensities represents a portion of the target.

11. A method of transitioning an imaging target tracker from an initialization mode to a tracking mode comprising the steps of:

(a) maintaining an image sensor on the target through manual manipulation of the image sensor;

(b) centering a plurality of gates on an image detected by the image sensor, the image being made up of a plurality of pixels;

(c) selecting a range of consecutive intensities for the plurality of pixels that have a probability of representing the target;

(d) generating a probability map based upon the selected range of consecutive intensities; and

(e) generating at least two initial histograms based upon the selected range of consecutive intensities.

13. A method of tracking a target using an image captured by an image sensor comprising the steps of:

(a) computing a probability that a particular intensity of a pixel within the image is representative of the target;

(b) calculating a centroid of the target based upon the computed probability;

(c) manipulating the image sensor based upon the calculated centroid so as to maintain a line of sight of the image sensor on the target.

14. A method according to claim 13, wherein the step of calculating includes calculating first moments of the target centroid and weighting the first moments with the computed probability.

15. A method according to claim 13, wherein the step of manipulating includes generating commands based upon the calculated centroid and providing the commands to motors operatively connected to a rotatable mechanism on which the image sensor is mounted.

16. A method according to claim 13, further comprising the step of determining a silhouette of the target based upon the computed probability.

17. A method according to claim 16, further comprising the step of calculating a size of an inner gate based upon the silhouette and locating the inner gate based upon the calculated centroid.