Method and system for improved unresolved target detection using multiple frame association

• US 20050185824A1
• Filed: 09/13/2004
• Published: 08/25/2005
• Est. Priority Date: 02/24/2004
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Missiles and Firecontrol - Orlando
• Inventors: Chen, Hai-Wen
• Granted Patent: US 7,483,551 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

A method and apparatus for detecting and tracking objects using infrared sensors are disclosed. The system is preferably an IRST (infrared, search and tracking) system, and it includes at least one or more infrared sensors, a receiver and a processor. The receiver receives image data from the infrared sensors having a predetermined field of view. The image data includes a reference image, which is preferably a current frame, and a search image, which is preferably a previous frame. The image data is classified to determine whether the image data includes relatively low clutter or relatively high clutter. When the image data includes relatively high clutter of the type typically found in an urban area, the processor performs spot time-difference processing on multiple frames of the image data. The processor detects a moving object from the multiple frames of image data, and it is also capable of detecting stationary objects and random objects.

Claims

1. A method for detecting and tracking objects, comprising:

receiving image data from a sensor field of view, said image data including a current frame having a reference image and a previous frame having a search image;

spot time-difference processing multiple frames of the image data to determine a potential moving object, when the image data includes relatively high clutter; and

detecting a moving object from the multiple frames of image data that have been spot time-difference processed.

2. A method according to claim 1 wherein the spot time-difference processing of multiple frames of image data, having spots which correspond to potential moving targets, includes:

registering the spots from at least a first current frame of a reference image and the spots from at least a first previous frame of a search image;

registering the spots from at least a second current frame of a reference image and the spots from at least a second previous frame of a search image;

determining the velocities and directions of the registered spots from the multiple frames of data.

3. A method according to claim 2, wherein the determining step further includes establishing tracking gates in each current frame and corresponding previous frame.

4. A method according to claim 3 wherein the object is determined to be a stationary object if its location does not change between the current frame and the previous frame.

5. A method according to claim 3 wherein the object is determined to be a random object if its velocity and direction is random over multiple frames.

6. A method according to claim 3 wherein the object is determined to be moving object if its velocity and direction is constant over multiple frames.

7. A method according to claim 3 wherein the registering steps include aligning the pixels in the corresponding current frames and previous frames.

8. A method according to claim 3 wherein the determining means includes establishing a threshold to minimize false detections.

9. A method according to claim 2 wherein the spots are spatially filtered prior to being registered.

10. A method according to claim 1 which further includes the steps of:

classifying the clutter in the image data to determine whether the image data includes relatively low clutter or relatively high clutter; and

spatially filtering the image data when the image data includes relatively low clutter.

11. A method according to claim 3 wherein the determining step results in the detection of stationary objects and randomly moving objects.

12. A method according to claim 1 which further includes the step of spatially filtering the image data in order to detect a spot and registering each detected spot prior to spot time difference processing the image data.

13. A system for detecting and tracking objects, comprising:

at least one sensor;

a receiver for receiving image data from the sensor, said image data including a reference image and a search image; and

a processor for classifying the clutter in the image data to determine whether the image data includes relatively low clutter or relatively high clutter, for spot time-difference processing multiple frames of the image data when the image data includes relatively high clutter, and for detecting a moving object from the multiple frames of image data that have been spot time-difference processed.

14. A system according to claim 13 wherein the reference image is a current frame and the search image is a previous frame.

15. A system according to claim 13 which further includes a spatial filter for spatially filtering the image data.

16. A system according to claim 15 wherein objects are detected using both spot time-difference processed images and spatially filtered images.

17. A system according to claim 13 wherein the processor detects stationary objects and randomly moving objects.

18. A system according to claim 13 which further includes the step of spatially filtering the image data in order to detect a spot and registering each detected spot prior to spot time difference processing the image data.

19. A system according to claim 13 wherein the sensor is an infrared sensor.