Thomas S Lo, 56Irvine, CA

4959714, Sep 25, 1990

Aug 8, 1988

7/229198

Thomas K. Lo - Temple City CA
Jack M. Sacks - Thousand Oaks CA
Wayne P. Simoni - Canoga Park CA

Hughes Aircraft Company - DE

H04N 718
H04N 700

358125

A conventional tracker 14 is used to continually aim a sensor 12 at a flying object so that it is located in substantially the same spatial location in a plurality of image frames taken at different times. Thus, the object remains in about the same spatial position in each image frame while the background clutter generally changes. By processing two or more of the image frames it is possible to calculate a more precise aimpoint for the object than is generally provided by the track point.

4937878, Jun 26, 1990

Aug 8, 1988

7/229390

Thomas K. Lo - Temple City CA
Jack M. Sacks - Thousand Oaks CA
Nam D. Banh - Canoga Park CA

Hughes Aircraft Company - Los Angeles CA

G06K 920

382 1

A method and apparatus are disclosed for detecting moving objects silhouetted against background clutter. A correlation subsystem 12 is used to register the background of a current image frame (framestore 1) with an image frame taken two time periods earlier (framestore 3). A first difference image is generated by subtracting the registered images, with the first difference image being filtered by low pass filter 34 and thresholded by a three level segmenter 36. A second difference image is likewise generated between the current image frame and another image frame taken at a different subsequent time period. This second difference image is likewise filtered and thresholded. The two difference images are logically ANDed together by gate 39 whose output is connected to a formatter, sorter and feature extractor 40. Track files are generated in CPU 16 for comparing subsequently extracted image features with previously stored extracted features.

5109435, Apr 28, 1992

Mar 4, 1991

7/663786

Thomas K. Lo - Temple City CA
Jack M. Sacks - Thousand Oaks CA
Nam D. Banh - Canoga Park CA

Hughes Aircraft Company - Los Angeles CA

G06K 938
G06K 920
H04N 718
H04N 5225

382 48

Three image frames containing an object of interest and background clutter are taken at successive time intervals and stored in memory. The background of images A, B and C are registered preferably using an area correlator 12. A median filter 16 is used to select a median value from the registered image frames. Then, subtractor 18 serves to subtract the median pixel values from one of the image frames. This difference output is then thresholded to provide a binary signal whose pixel values exceeding the threshold levels are generally associated with the position of the moving object.

5386480, Jan 31, 1995

Mar 9, 1992

7/848604

Thomas K. Lo - Temple City CA
Deborah C. Roty - West Hills CA

Hughes Aircraft Company - Los Angeles CA

G06K 900

382 1

A system for detecting an object in a scene. The invention (10) includes memory (12) for storing a first frame of image data represented by a plurality of input signals I. sub. o. A spatial filter (16) is included for spatially filtering a second frame of image data represented by a plurality of input signals I. sub. o to provide first spatial filter output signals of the form. eta. sub. s I. sub. o. These signals are subtracted from the first frame of image data to provide difference signals of the form. eta. sub. D I. sub. o, where. eta. sub. D represents a measure of object registration. A second spatial filter (18) is included for spatially filtering the difference signals to provide spatially filtered difference signals of the form. eta. sub. s. eta. sub. D I. sub. o. Finally, the signals are processed (30) to extract the measure of object registration. eta. sub. D.

5020113, May 28, 1991

Aug 8, 1988

7/229407

Thomas K. Lo - Temple City CA
Jack M. Sacks - Thousand Oaks CA
Wayne P. Simoni - Canoga Park CA
Leonard A. Lee - Canoga Park CA
Harrison Nguyen - Ontario CA
Lynne M. Karlin - Northridge CA
Andy L. Quan - Canogo Park CA
Kazuo R. Hosokawa - Canogo Park CA

Hughes Aircraft Company - Los Angeles CA

G06K 964

382 42

A method and apparatus for correlating two signals representing a live image and a reference image are disclosed. The reference signal is processed to provide a polarity bit and mask bit for each pixel position in the reference image. The processed video signal is stored in a memory 20 and used in a convolver and summer section 18 in which the polarity bits between the reference and live images are gated by gate 17 and are used in generating a correlation output from summer 23. However, the polarity bits do not affect the correlation output if the logical output from gate 19 is of a given state which occurs if the associated mask bits indicate that the gradient value at the particular pixel position does not exceed certain minimum threshold values.

5062056, Oct 29, 1991

Oct 18, 1989

7/423301

Thomas K. Lo - Temple City CA
Nam D. Banh - Canoga Park CA
Timothy T. Bohn - Simi Valley CA
Jack M. Sacks - Thousand Oaks CA

Hughes Aircraft Company - Los Angeles CA

G01S 1300
H04N 5225
G06F 780

364516

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.

5261010, Nov 9, 1993

Sep 27, 1991

7/766318

Thomas K. Lo - Temple City CA
Teresa A. Hinkle - Madison AL
Lop G. Ng - Encino CA

Hughes Aircraft Comany - Los Angeles CA

G06K 962
G06K 964
G06K 968

382 42

An improved method for finding the mask threshold for a maskable bilevel correlator operates on a series of frames of information. Beginning with an initial threshold, two rates are computed. The rate of change of the correlation peak magnitude P. sub. (T), a function of threshold T, with respect to the change in the value of the mask threshold T, or (dP. sub. (T) /dT), and the corresponding rate of change of correlation reference pixels with magnitude exceeding the mask threshold, U. sub. (T), a function of threshold T, with respect to the change in the value of the mask threshold T, or (dU. sub. (T) /dT), are measured. The correct, or best, value of the threshold occurs when. vertline. dP. sub. (T) /dT. vertline. gtoreq. 5*. vertline. dU. sub. (T) /dT. vertline.