Granted Patent B2

US 10,796,417 · App. 15/947,948 · Granted Oct 6, 2020

Inventors: Randall J. St. Romain, II (Clifton, VA); Ambrose J. Slone (Ashburn, VA); Péter L. Venetianer (McLean, VA)

Assignee: StereoVision Imaging, Inc.

G06T5/009G06T5/008G06T5/40G06T5/50G06T2207/10016G06T2207/20224

Abstract

Claims (27)

1. A method for improving contrast in a plurality of image frames captured by a video camera, the method comprising:

determining, by a computing processor, a changed region in a second frame of the plurality of image frames in relation to an first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames;

generating a transformation function corresponding to the changed region of the second frame, wherein the transformation function improves contrast of the changed region of the second frame, wherein generating the transformation function comprises generating a histogram for the changed region; and

applying the transformation function to the changed region of the second frame to improve the contrast of the changed region, but not to the unchanged region of the second frame.

2. A method for improving contrast of a plurality of image frames in a video stream captured by a video camera, the method comprising:

determining, by a computing processor, a changed region of a later-in-time image frame of the plurality of image frames relative to an earlier-in-time image frame and an unchanged region of the later-in-time image frame of the plurality of image frames relative to the earlier-in-time image frame;

determining, by the computing processor, a CLAHE transformation for the changed region of the later-in-time image frame of the plurality of image frames; and

applying, by the computing processor, the CLAHE transformation to the changed region of the later-in-time image frame of the plurality of image frames, but not to the unchanged region of the later-in-time image frame of the plurality of image frames.

3. A method for improving an image characteristic of a plurality of image frames in a video stream captured by a video camera, the method comprising:

determining, by a computing processor, a changed region of a second frame of the plurality of image frames in relation to a first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames;

determining, by a computing processor, an improvement to a image characteristic for the changed region of the second frame of the plurality of image frames by generating a histogram for the changed region of the second frame of the plurality of image frames; and

applying, by a computing processor, the improvement to the image characteristic of the changed region of the second frame of the plurality of image frames, but not to an image characteristic of the unchanged region of the second frame of the plurality of image frames.

4. The method of claim 3 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises:

determining a number of pixels in a region of the second frame that exceed a difference threshold relative to corresponding pixels in the first frame in order to determine the changed region.

5. The method of claim 3 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises:

determining a number of pixels in a region of the second frame that differ relative to corresponding pixels in the first frame in order to determine the changed region.

6. The method of claim 3 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises:

determining a motion of a region in the first frame; and

extrapolating the motion of the region to the second frame.

7. The method of claim 3 , wherein determining an improvement to the image characteristic for the changed region of the second frame of the plurality of image frames further comprises:

generating a transformation function from the histogram for the changed region of the second frame.

8. The method of claim 7 , wherein applying the second improvement to the image characteristic of the changed region of the second frame of the plurality of image frames comprises:

applying the second transformation function to the changed region of the second frame.

9. The method of claim 8 , wherein applying the second transformation function to the changed region of the second frame comprises:

applying the second transformation function to each of a plurality of pixels in the changed region of the second frame.

10. The method of claim 3 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises determining that the changed region is due to a change in illumination in the image frame, and

wherein determining an improvement to the image characteristic for the changed region of the second frame of the plurality of image frames comprises determining the improvement by scaling or shifting the first improvement.

Assignments (8)