Detection of near-field camera obstruction

• US 9,064,317 B2
• Filed: 05/15/2012
• Issued: 06/23/2015
• Est. Priority Date: 05/15/2012
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Liu, Juan, Raghavan, Ajay, Price, Robert R.
• Primary Examiner(s): Ho, Tuan
• Assistant Examiner(s): CAMARGO, MARLY S.B.
• Application Number:
  US13/472,126
• Publication Number:
  US 20130308004A1
• Time in Patent Office: 1,134 Days
• Field of Search: 348/222.1, 348/252, 348/200.1, 348/205, 348/239, 382/199, 382/266, 382/254, 382/103
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling

Abstract

A method (100) is provided for detecting an obstruction within a field of view of a camera (12) from an image (200) captured by the camera (12). The method (100) includes: analyzing the image (200) by applying edge detection (104) to the image (200), identifying (108) regions of the image (200) lacking edge content and comparing (112) a size of the identified regions to a threshold; and determining if there is an obstruction based upon a result of said comparison.

Claims

1. A method for detecting an obstruction within a field of view of a camera from an image captured by the camera, said method comprising:

analyzing the image, said analyzing of the image comprising;

applying edge detection to the image;

identifying regions of the image lacking edge content; and

,

comparing a size of the identified regions to a threshold; and

determining if there is an obstruction based upon a result of said comparison.

2. The method of claim 1, wherein applying said edge detection generates an edge map including a plurality of pixels, where each pixel may be either an edge pixel or not an edge pixel, and said analyzing further comprises:

local smoothing of said map.

3. The method of claim 2, wherein said local smoothing comprises:

placing a window around a given pixel of the map;

assigning a value associated with the given pixel based upon whether or not any pixel within the window is an edge pixel; and

repeating said placing and said assigning for successive pixels of the map.

4. The method of claim 3, wherein said identifying comprises:

performing connected component analysis on the smoothed map.

5. The method of claim 1, wherein said analyzing further comprising:

generating a scalar value which represents the size of the identified regions.

6. The method of claim 5, wherein the scalar value is a percentage relative to an entire area of the image.

7. The method of claim 1, wherein said threshold is selected based on a statistical analysis of a set of training images including at least one image obtained by a camera with an obstruction in its field of view and at least one image obtained by a camera without an obstruction in its field of view.

8. The method of claim 1, said method further comprising:

providing notification of a detected obstruction.

9. An apparatus that executes the method of claim 1.

10. A non-transitory machine-readable medium including a computer program which when executed performs the method of claim 1.

11. A method for detecting an obstruction within a field of view of a camera from an image captured by the camera, said method comprising:

analyzing the image with a computer processor to identify regions of the image which are out of focus;

comparing a size of the identified regions to a threshold; and

determining if there is an obstruction based upon a result of said comparison.

12. A camera system comprising:

a camera that obtains an image; and

an image processor that analyzes said image to determine if there is an obstruction in the camera'"'"'s field of view, wherein said analyzing includes;

applying edge detection to the image;

identifying regions of the image lacking edge content;

comparing a size of the identified regions to a threshold; and

determining if there is an obstruction based upon a result of said comparison.

13. The camera system of claim 12, wherein applying said edge detection generates an edge map including a plurality of pixels, where each pixel may be either an edge pixel or not an edge pixel, and said analyzing further comprises:

local smoothing of said map.

14. The camera system of claim 13, wherein said local smoothing comprises:

placing a window around a given pixel of the map;

assigning a value associated with the given pixel based upon whether or not any pixel within the window is an edge pixel; and

repeating said placing and said assigning for successive pixels of the map.

15. The camera system of claim 14, wherein said identifying comprises:

performing connected component analysis on the smoothed map.

16. The camera system of claim 12, wherein said analyzing further comprising:

generating a scalar value which represents the size of the identified regions.

17. The camera system of claim 16, wherein the scalar value is a percentage relative to an entire area of the image.

18. The camera system of claim 12, wherein said threshold is selected based on a statistical analysis of a set of training images including at least one image obtained by a camera with an obstruction in its field of view and at least one image obtained by a camera without an obstruction in its field of view.