Image-based detection and tracking system and processing method employing clutter measurements and signal-to-clutter ratios

• US 5,602,760 A
• Filed: 02/02/1994
• Issued: 02/11/1997
• Est. Priority Date: 02/02/1994
• Status: Expired due to Term

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Hughes Electronics Corporation (AT&T, Inc.)
• Inventors: Prager, Kenneth E., Groves, Gillian K., Chacon, Kim M.
• Primary Examiner(s): Voeltz, Emanuel T.
• Assistant Examiner(s): PEESO, THOMAS R
• Application Number:
  US08/190,827
• Time in Patent Office: 1,105 Days
• Field of Search: 364/516, 342/159, 342/160, 342/176, 342/170, 382/103, 382/190
• US Class Current: 382/103
• 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 method for measuring and quantifying clutter, and target detection and tracking systems that employs wavelet-based clutter quantification to generate a clutter number and a signal-to-clutter ratio derived therefrom to achieve improved target detection performance. The method processes video signals representative of an image scene containing a target and background clutter to provide for more accurate tracking of the target by a tracker(s). The method comprises processing the video signals to compute a wavelet clutter number, processing the video signals to compute a signal-to clutter ratio using the wavelet clutter number, and generating a pointer to a lookup table that sets parameters and selects the tracker that is to be used to track the target based upon the computed signal-to clutter ratio.

Claims

1. A target detection and tracking system for tracking a target located in an image scene, said system comprising:

a sensor for generating video signals representative of the image scene;

a tracking computer that comprises

a wavelet-based signal-to-clutter processor for processing the video signals to compute a wavelet clutter number and a signal-to clutter ratio from the wavelet clutter number, and

tracker means for implementing at least one tracking algorithm to track the target in response to the computed signal-to clutter ratio; and

a display monitor coupled to an output of the tracking computer for viewing the tracked target and the image scene.

2. The system of claim 1 wherein the sensor is a forward looking infrared sensor.

3. The system of claim 1 wherein the sensor is a scanning forward looking infrared sensor.

4. The system of claim 1 wherein the sensor is a video sensor.

5. The system of claim 1 wherein the tracker means implements a plurality of different tracking algorithms, and wherein said processor generates a signal, based upon the computed signal-to clutter ratio, for selecting a particular algorithm to track the target.

6. The system of claim 1 wherein the tracker means implements a single tracking algorithm that is modified in response to the computed signal-to clutter ratio.

7. The system of claim 1 wherein the processor processes background video signals to compute the wavelet clutter number.

8. The system of claim 1 wherein the processor processes target area video signals to compute the signal-to clutter ratio from the wavelet clutter number.

9. The system of claim 1 wherein the computed signal-to clutter ratio corresponds to target contrast divided by the clutter number, and wherein the target contrast is defined as the difference between a peak gray level (P_t) of the target and mean background gray level (μ

_b).

10. The system of claim 1 wherein the wavelet clutter number (C_N) is computed in accordance with the equation ##EQU6## where E is the energy in decomposed high-pass subbands of the image for vertical and diagonal orientations, w(m,n) is the intensity of a wavelet image at location (m,n), and M,N are dimensions of the image.

11. The system of claim 1 wherein the computed signal-to clutter ratio (SCR) equals target contrast divided by the clutter number.

12. The system of claim 11, wherein ##EQU7## where the target contrast is defined as the difference between a peak gray level (P_t) of the target and a mean local background gray level (μ

_b).

13. A method of measuring clutter in an image from an MXN array, the method comprising the step of computing a clutter number according to the equation. ##EQU8## where E is the energy in decomposed high-pass subbands of the image for vertical and diagonal orientations, and w(m,n) is the intensity of a wavelet transformed image at location (m,n).

14. The method of claim 13 further comprising the step of computing a signal-to clutter ratio (SCR) according to the equation ##EQU9## where P_t is peak gray level of a target in the image and μ

_b is mean background gray level of a selected background area.

15. The method of claim 13 wherein horizontal orientation subbands of the wavelet transformed image are not used to compute the clutter number.

16. A method of measuring clutter in a video scene from an MXN array, the method comprising the steps of:

calculating the mean background gray level of a selected background area of the video scene;

calculating the peak gray level of a target area in the video scene;

performing a wavelet transform on the selected background area of the video scene;

calculating a clutter number from the wavelet transformed video scene; and

calculating a signal-to-clutter ratio from the clutter number, whereby the ratio provides a measure of the clutter in the video scene.

17. A method of tracking a target in an image scene comprising the steps of:

generating video signals representative of the image scene;

using wavelet based processing of the video signals to generate a wavelet clutter number and a signal to clutter ratio; and

tracking the target in response to the signal to clutter ratio.

18. A system for tracking a target in an image scene comprising;

means for generating video signals representative of the image scene;

means for processing the video signals using wavelet based processing to generate a wavelet clutter number and a signal to clutter ratio; and

tracking means for tracking said target in response to the signal to clutter ratio.

19. The system of claim 18 wherein said tracking means includes means for selecting a unique tracking algorithm from among a plurality of algorithms in response to the signal to clutter ratio.

20. The system of claim 18 wherein said tracking means uses a tracking algorithm, said tracking means further comprising means for modifying said tracking algorithm in response to the signal to clutter ratio.