Method and system for imaging target detection

• US 6,072,889 A
• Filed: 12/03/1997
• Issued: 06/06/2000
• Est. Priority Date: 12/03/1997
• Status: Expired due to Fees

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Johnson, Stephen G., Deaett, Michael A., Pawlak, Anthony J., DeGraaf, Erik J., Norcross, Melinda L.
• Primary Examiner(s): Johns, Andrew W.
• Application Number:
  US08/984,592
• Time in Patent Office: 916 Days
• Field of Search: 382/103, 382/173, 382/180, 382/190, 342/62, 244/3.16, 244/3.17, 250/203.1, 250/203.3, 250/203.6, 250/202
• US Class Current: 382/103
• CPC Class Codes: F41G 7/2226 comparing the observed data with stored target data, e.g. target configuration data
• CPC Class Codes: F41G 7/2253 Passive homing systems, i.e. comprising a receiver and do not requiring an active illumination of the target
• CPC Class Codes: F41G 7/2293 using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 3/781 Details
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

A system and method for imaging target detection includes scanning a target area to produce an image of the target area and discriminating a target by identifying image pixels of similar intensity levels, grouping contiguous pixels with similar intensity levels into regions, calculating a set of features for each region and qualifying regions as possible targets in response to the features; discriminating the background by identifying image pixels of similar intensity levels, grouping contiguous pixels of similar intensity levels into regions, calculating a set of features for each background region and qualifying background regions as terrain characteristics in response to the features and analyzing the qualified terrain characteristics and qualified target candidates to determine and prioritize targets.

Claims

1. An imaging target detection system comprising:

scanner means for producing an image of a target area;

target discriminator means including target segmentation means for identifying image pixels of similar intensity levels;

target regionalization means for grouping into regions contiguous pixels of similar intensity levels;

means for calculating a set of features for each target region; and

means, responsive to said features, for qualifying regions as target candidates;

background discriminator means including background segmentation means for identifying image pixels of similar intensity levels;

background regionalization means for grouping into regions contiguous pixels of similar intensity levels;

means for calculating a set of features for each background region; and

means, responsive to said features, for qualifying background regions as terrain characteristics; and

image analysis logic means responsive to said qualified terrain characteristics and qualified target candidates for determining and prioritizing targets.

2. The imaging target detection system of claim 1 in which said target discriminator means includes cumulative distribution function segmentation means.

3. The imaging target detection system of claim 1 in which said background discriminator means includes vector quantization segmentation means.

4. The imaging target detection system of claim 1 in which said means for calculating a set of features for each target region includes means for eliminating regions containing above and below a predetermined number of pixels.

5. The imaging target detection system of claim 1 in which said means for calculating a set of features for each background region includes means for eliminating regions containing above and below a preselected number of pixels.

6. The imaging target detection system of claim 1 in which said background discrimination means includes Viterbi tracker means for detecting a track in the pixels of the images, and said means for qualifying background regions is responsive to said Viterbi tracker means and said means for calculating a set of features for each background region, for qualifying background regions as terrain characteristics.

7. The imaging target detection system of claim 1 in which said scanner means includes a scanning device for providing a signal representative of the target area and geometric transform means for converting said signal into an image of the target area.

8. The imaging target detection system of claim 1 in which said image includes at least two images of different colors.

9. The imaging target detection system of claim 8 in which said different colors are in the mid and far infrared wavelength.

10. The imaging target detection system of claim 8 which includes a target discriminator means and a background discriminator means for each color image.

11. The imaging target detection system of claim 1 in which said image analysis logic means provides a confidence level for prioritizing targets.

12. A missile imaging target detection system comprising:

scanner means for producing an areal image of a target area;

target discriminator means including target segmentation means for identifying image pixels of similar intensity levels;

target regionalization means for grouping into regions contiguous pixels of similar intensity levels;

means for calculating a set of features for each target region; and

means, responsive to said features, for qualifying regions as possible targets;

background discrimination means including background segmentation means for identifying image pixels of similar intensity levels;

background regionalization means for grouping into regions pixels of similar intensity levels;

means for calculating a set of features for each background region; and

means, responsive to said features, for qualifying background regions as terrain characteristics; and

image analysis logic means responsive to said qualified terrain characteristics and qualified possible targets for determining and prioritizing targets.

13. A method for imaging target detection, comprising:

scanning a target area to produce an image of the target area;

discriminating a target by identifying image pixels of similar intensity levels;

grouping contiguous pixels of similar intensity levels into regions;

calculating a set of features for each region; and

qualifying regions as possible targets, in response to said features;

discriminating the background by identifying image pixels of similar intensity levels;

grouping contiguous pixels of similar intensity levels into regions;

calculating a set of features for each background region; and

qualifying background regions as terrain characteristics in response to said features; and

analyzing said qualified terrain characteristics and target candidates to determine and prioritize targets.

14. The method for imaging target detection of claim 13 in which discriminating a target includes segmenting according to a cumulative distribution function.

15. The method for imaging target detection of claim 13 in which discriminating a background includes segmenting with vector quantization.

16. The method for imaging target detection of claim 13 in which calculating a set of features for each target region includes eliminating regions which contain above a first predetermined number of pixels and below a second predetermined number of pixels.

17. The method for imaging target detection of claim 13 in which calculating a set of features for each background region includes eliminating regions which contain above a first preselected number of pixels and below a second preselected number of pixels.

18. The method of imaging target detection of claim 13 in which said discriminating the background includes Viterbi tracking for detecting a track in the pixels of the images, and qualifying background regions includes correlating the Viterbi tracking and the set of features calculated for each background region, for qualifying regions as terrain characteristics.

19. The method of imaging target detection of claim 13 in which said scanning includes producing a signal representative of the target area and geometrically transforming said signal into an image of the target area.

20. The method of imaging target detection of claim 13 in which said image includes at least two images of different colors.

21. The method of imaging target detection of claim 20 in which said different colors are in the mid and far infrared wavelength.

22. The method of imaging target detection of claim 20 in which discriminating a target and discriminating the background are performed for each color image.

23. The method of imaging target detection of claim 13 in which said image logic analyzing provides a confidence level for prioritizing targets.

24. A method for missile imaging target detection, comprising:

scanning a target area to produce an image thereof;

discriminating a target by identifying image pixels of similar intensity levels;

grouping contiguous pixels of similar intensity levels into regions;

calculating a set of features for each region; and

qualifying regions as possible targets, in response to said features;

discriminating the background by identifying image pixels of similar intensity levels;

grouping contiguous pixels of similar intensity levels into regions;

calculating a set of features for each background region; and

qualifying background regions as terrain characteristics in response to said features; and

analyzing said qualified terrain characteristics and target candidates for determining and prioritizing targets.