Apparatus and method for tracking a target

• US 5,062,056 A
• Filed: 10/18/1989
• Issued: 10/29/1991
• Est. Priority Date: 10/18/1989
• Status: Expired due to Fees

• Current Assignee: Hughes Aircraft Company (Rtx Corporation)
• Original Assignee: Hughes Aircraft Company (Rtx Corporation)
• Inventors: Bohn, Timothy T., Lo, Thomas K., Banh, Nam D., Sacks, Jack M.
• Primary Examiner(s): Dixon, Joseph L.
• Application Number:
  US07/423,301
• Time in Patent Office: 741 Days
• Field of Search: 364/516, 364/423, 358/125, 358/126, 358/105, 235/411, 235/412, 382/1, 342/77, 342/159
• US Class Current: 235/411
• CPC Class Codes: G01S 3/7865 using correlation of the live video image with a stored image

Abstract

Target tracking capability is provided by a synergistic tracker system (5) which includes both a correlation tracker (30) and an object tracker (40) for processing sensor data input (10) and for generating tracking error signals (80). The operation of the synergistic tracker system is controlled by a central processing unit (70). The system operates by first correlating a reference region image with a portion of a current digitized image provided by an analog to digital converter (20). Secondly, the object tracker provides a precisely defined trackpoint for an object within the current image. The correlation tracker stabilizes and limits the portion of the digitized image that the object tracker must operate upon. Stabilizing and limiting this portion of the digitized image reduces the object tracker'"'"'s sensitivity to background clutter and sensitivity to a loss of lock induced by sensor motion. The object tracker provides a non-recursive update for the correlation'"'"'s reference region image. The correlation tracker and the object tracker are used simultaneously and cooperatively so that the strengths of one tracker are used to overcome the weaknesses of the other. A method of tracking a target immersed in background clutter is also disclosed.

Claims

1. A tracking system for tracking a target immersed in

background clutter using as an input a sequence of two dimensional digitized images taken from a scene, said system comprising:

correlation tracker means for matching a reference region image with a current digitized image and for generating a background reference point to be used for generating a first estimated track gate;

means coupled to said correlation tracker means for processing said background reference point to generate a first estimated track gate;

object tracker means for receiving said first estimated track gate from said means for processing, said object tracker means providing a second precisely defined target trackpoint and target size information; and

means for using said second target trackpoint and said target size information from said object tracker means to redefine said reference region image for use by said correlation tracker means during processing of a subsequent digitized image.

2. The system of claim 1, wherein said system includes means for using said background reference point to find a previous target trackpoint in said current digitized image, said system using said previous target trackpoint and a target velocity estimate to generate a first estimated target trackpoint to be used in generating said first estimated track gate.

3. The system of claim 2, wherein said system includes means for calculating said target velocity estimate from two previous target trackpoints, said target velocity estimate being calculated from a displacement of said target between said two previous target trackpoints divided by a time between calculating said two previous target trackpoints.

4. The system of claim 2, wherein said system includes central processing unit means for centering said first estimated track gate on said first estimated target trackpoint generated from the output of said correlation tracker means.

5. The system of claim 1, wherein said object tracker means includes means for generating said second precisely defined target trackpoint as a function of a portion of said current digitized image bounded by said first estimated track gate.

6. The system of claim 5, wherein said system includes means for generating a track gate size from said target size information, and means for centering a second precisely defined track gate on said second precisely defined target trackpoint generated by said object tracker means.

7. A tracking system for tracking a target in a series of

two dimensional digitized images taken from a scene, said system comprising:

correlation processor means for matching a reference region image with a current digitized image and for generating a background reference point to be used in generating a first estimated track gate;

storage means connected to the correlation processor means for storing the first estimated track gate generated from the output of the correlation processor means;

centroid processor means connected to the storage means for receiving the first estimated track gate, said centroid processor means generating a second precisely defined target trackpoint and target size information to be used in generating a second precisely defined track gate, said second track gate being stored in said storage means; and

means for using said second target trackpoint from the centroid processor means to redefine the reference region image for use by the correlation processor means during processing of a subsequent digitized image.

8. The system of claim 7, wherein said system includes means for generating a first estimated target trackpoint from said background reference point, said first estimated target trackpoint to be used in generating said first estimated track gate.

9. The system of claim 8, wherein said system includes means for using said background reference point to find a previous target trackpoint in said current digitized image, said system using said previous target trackpoint and, a target velocity estimate to generate said first estimated target trackpoint to be used in generating said first estimated track gate.

10. The system of claim 9, wherein said system includes means for calculating said target velocity estimate from two previous target trackpoints, said target velocity estimate being calculated from a displacement of said target between said two previous target trackpoints divided by a time between calculating said two previous target trackpoints.

11. The system of claim 9, wherein said system includes central processing unit means for centering said first estimated track gate on said first estimated target trackpoint generated from the output of said correlation processor means, and means for centering said second precisely defined track gate on said second precisely defined target trackpoint generated by said centroid processor means.

12. The system of claim 7, wherein said centroid

processor means generates said second precisely defined target trackpoint as a function of a portion of said current digitized image within said first estimated track gate previously generated from said output of the correlation processor means.

13. The system of claim 12 wherein said system includes means for generating a track gate size from said target size information.

14. A method of tracking a target immersed in background clutter using as an input a sequence of two dimensional digitized images, said method comprising the steps of:

(a) generating a background reference point for a current digitized image by using a correlation tracker to match a reference region image with said current digitized image, said background reference point to be used for generating a first estimated track gate;

(b) generating a second precisely defined target trackpoint and target size information by using an object tracker to receive said first estimated track gate as an input; and

(c) redefining said reference region image, for use by said correlation tracker during processing of a subsequent digitized image, by using said second precisely defined target trackpoint and said target size information from said object tracker.

15. The method of claim 14 wherein step (a) includes generating a first estimated target trackpoint by using said background reference point from said correlation tracker to find a previous target trackpoint in said current digitized image, said previous target trackpoint to be used with a target velocity estimate to interpolate said first estimated target trackpoint from said previous target trackpoint.

16. The method of claim 15, including the step of calculating said target velocity estimate from two previous target trackpoints, said target velocity estimate being calculated from a displacement of said target between said two previous target trackpoints divided by a time between calculating said two previous target trackpoints.

17. The method of claim 15, including the step of centering said first estimated track gate on said first estimated target trackpoint generated from the output of said correlation tracker.

18. The method of claim 14, wherein step (b) includes centering a second precisely defined track gate on said second precisely defined trackpoint generated by said object tracker.

19. The method of claim 18, including the step of generating said second precisely defined target trackpoint and said target size information by using said object tracker to receive and to operate upon a portion of said current digitized image bounded by said first estimated track gate.

20. The method of claim 18 including the step of generating a track gate size from said target size information.