Detection of near-field camera obstruction
View Patent ↗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.
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.