AUTOMATIC GAIN CONTROL FILTER IN A VIDEO ANALYSIS SYSTEM

• US 20140003713A1
• Filed: 06/28/2013
• Published: 01/02/2014
• Est. Priority Date: 06/29/2012
• Status: Active Grant

• Current Assignee: Intellective Ai, Inc.
• Original Assignee: Behavioral Recognition Systems Incorporated
• Inventors: SEOW, Ming-Jung, YANG, Tao, COBB, Wesley Kenneth
• Granted Patent: US 9,317,908 B2
• Time in Patent Office: Days
• US Class Current: 382/164
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20208 High dynamic range [HDR] image processing
• CPC Class Codes: G06T 5/92 based on global image properties
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/10 Segmentation; Edge detection motion-based segmentation G06T7/215
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/251 involving models

Abstract

Techniques are disclosed for analyzing a scene depicted in an input stream of video frames captured by a video camera. Bounding boxes are determined for a set foreground patches identified in a video frame. For each bounding box, the techniques include determining textures for first areas, each including a foreground pixel and surrounding pixels, and determining textures for second areas including pixels of the background model image corresponding to the pixels of the foreground areas. Further, for each foreground pixel in the bounding box area, a correlation score is determined based on the texture of the corresponding first area and second area. Pixels whose correlation scores exceed a threshold are removed from the foreground patch. The size of the bounding box may also be reduced to fit the modified foreground patch.

Claims

1. A computer-implemented method for filtering out false-positive foreground pixels, the method comprising:

extracting foreground patches from a video frame using a background model image, the foreground patches each including respective foreground pixels;

for each foreground pixel;

determining a texture of a first area including the foreground pixel and pixels surrounding the foreground pixel and a texture of a second area including pixels of the background model image corresponding to the pixels of the foreground area, and

determining a correlation score based on the texture of the first area and the texture of the second area; and

for foreground pixels having a correlation score which exceeds a threshold, removing the foreground pixels from the corresponding foreground patch in which the foreground pixels lie.

2. The method of claim 1, wherein determining texture of the first area includes determining gradient values for the foreground pixel and the pixels surrounding the foreground pixel, and wherein determining texture of the second area includes determining gradient values for the pixels of the background model image corresponding to the pixels of the foreground area.

3. The method of claim 2, wherein the gradient values are determined using an edge detection technique which is resilient to noise and invariant to illumination and/or color/hue changes.

4. The method of claim 2, wherein the gradient values are determined by applying one of a Sobel Operator and a Haar wavelet transform.

5. The method of claim 1, further comprising:

determining a bounding box for each foreground patch,

wherein the steps of determining the textures, determining the correlation scores, and removing the foreground pixels are performed per bounding box.

6. The method of claim 5, wherein each bounding box is associated with a respective threshold value for comparing the correlation score against, the threshold value being proportional to a size of the bounding box.

7. The method of claim 5, wherein the number of surrounding pixels used in the first area is proportional to the size of the bounding box.

8. The method of claim 5, further comprising, reducing the bounding box sizes to fit the corresponding foreground patches after removing the foreground pixels.

9. The method of claim 1, further comprising, prior to determining the textures, converting the foreground and background pixels to grayscale.

10. A non-transitory computer-readable storage medium storing instructions, which when executed by a computer system, perform operations for filtering out false-positive foreground pixels, the operations comprising:

extracting foreground patches from a video frame using a background model image, the foreground patches each including respective foreground pixels;

for each foreground pixel;

determining a texture of a first area including the foreground pixel and pixels surrounding the foreground pixel and a texture of a second area including pixels of the background model image corresponding to the pixels of the foreground area, and

determining a correlation score based on the texture of the first area and the texture of the second area; and

for foreground pixels whose correlation scores exceed a threshold, removing the foreground pixels from the foreground patches in which the foreground pixels lie.

11. The computer-readable storage medium of claim 10, wherein determining texture of the first area includes determining gradient values for the foreground pixel and the pixels surrounding the foreground pixel, and wherein determining texture of the second area includes determining gradient values for the pixels of the background model image corresponding to the pixels of the foreground area.

12. The computer-readable storage medium of claim 11, wherein the gradient values are determined using an edge detection technique which is resilient to noise and invariant to illumination and/or color/hue changes.

13. The computer-readable storage medium of claim 11, wherein the gradient values are determined by applying one of a Sobel Operator and a Haar wavelet transform.

14. The computer-readable storage medium of claim 10, the operations further comprising:

determining a bounding box for each foreground patch,

wherein the steps of determining the textures, determining the correlation scores, and removing the foreground pixels are performed per bounding box.

15. The computer-readable storage medium of claim 14, wherein each bounding box is associated with a respective threshold value for comparing the correlation score against, the threshold value being proportional to a size of the bounding box.

16. The computer-readable storage medium of claim 14, wherein the number of surrounding pixels used in the first area is proportional to the size of the bounding box.

17. The computer-readable storage medium of claim 14, the operations further comprising, reducing the bounding box sizes to fit the corresponding foreground patches after removing the foreground pixels.

18. The computer-readable storage medium of claim 10, the operations further comprising, prior to determining the textures, converting the foreground and background pixels to grayscale.

19. A system, comprising:

a processor; and

a memory, wherein the memory includes an application program configured to perform operations for filtering out false-positive foreground pixels, the operations comprising;

extracting foreground patches from a video frame using a background model image, the foreground patches each including respective foreground pixels,

for each foreground pixel;

determining a texture of a first area including the foreground pixel and pixels surrounding the foreground pixel and a texture of a second area including pixels of the background model image corresponding to the pixels of the foreground area; and

determining a correlation score based on the texture of the first area and the texture of the second area, and for foreground pixels whose correlation scores exceed a threshold, removing the foreground pixels from the foreground patches in which the foreground pixels lie.

20. The system of claim 19, the operations further comprising:

determining a bounding box for each foreground patch,

wherein the steps of determining the textures, determining the correlation scores, and removing the foreground pixels are performed per bounding box,

wherein each bounding box is associated with a respective threshold value for comparing the correlation score against, the threshold value being proportional to a size of the bounding box, and wherein the number of surrounding pixels used in the first area is proportional to the size of the bounding box.