Precipitation removal for vision-based parking management systems

• US 9,165,352 B2
• Filed: 06/10/2013
• Issued: 10/20/2015
• Est. Priority Date: 06/10/2013
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Wu, Wencheng, Dalal, Edul N., Bulan, Orhan
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): CESE, KENNY A
• Application Number:
  US13/913,606
• Publication Number:
  US 20140363045A1
• Time in Patent Office: 862 Days
• Field of Search: 382/103, 382/107, 382/220, 382/221, 382/224
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20032 Median filtering
• CPC Class Codes: G06T 2207/20182 Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
• 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 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/70 Denoising; Smoothing

Abstract

Methods and systems receive a series of images and compare at least two of the images in the series of images to locate items that are in different positions to identify moving items. Such methods and systems further calculate a measure of the moving items within the series of images. Additionally, such methods and systems perform a continuously variable image correction to remove the moving items from the images to produce a series of corrected images. This “continuously variable image correction” increases the amount of image correction for a relatively higher measure of the moving items and decreases the amount of image correction for a relatively lower measure of the moving items, and does so continuously as the measure of the moving items changes within the series of images.

Claims

1. A system comprising:

a camera device acquiring a series of images; and

a computerized device operatively connected to said camera device,

said computerized device comparing at least two images in said series of images to locate items that are in different positions in said at least two images to identify moving items within said series of images,

said computerized device calculating a measure of said moving items,

said computerized device performing a continuously variable image correction to remove said moving items from said series of images to produce a series of corrected images,

said continuously variable image correction increasing an amount of image correction for a relatively higher measure of said moving items and decreasing said amount of image correction for a relatively lower measure of said moving items continuously as said measure of said moving items changes within said series of images,

said continuously variable image correction increasing and decreasing said amount of image correction in continuously variable amounts corresponding to changes in said measure of said moving items,

said continuously variable amounts being between predetermined maximum and minimum amounts of said image correction, and

said computerized device outputting said series of corrected images.

2. The system according to claim 1, said continuously variable image correction being applied to only portions of said images.

3. The system according to claim 1, said amount of image correction for a current frame further depending on said amount of image correction used for a previous frame.

4. The system according to claim 1, said continuously variable image correction being performed iteratively by repeating said calculating a measure of said moving items and performing said continuously variable image correction until said measure of said moving items in said corrected images is below a predetermined threshold.

5. The system according to claim 1, said continuously variable image correction comprising applying one of:

temporal median filtering, temporal order statistics filtering, temporal outlier rejection algorithms, temporal averaging, and temporal approximate median filtering.

6. The system according to claim 1, said system comprising an optical-based vehicle parking management system.

7. The system according to claim 1, said moving items comprising one of raindrops and snowflakes.

8. The system according to claim 1, said measure of said moving items comprising at least one of:

an average size of said moving items;

a maximum size of said moving items; and

an average rate of movement of said moving items.

9. A system comprising:

a camera device acquiring a series of images; and

a computerized device operatively connected to said camera device,

said computerized device comparing at least two images in said series of images to locate items that are in different positions in said at least two images to identify moving items within said series of images,

said computerized device calculating a measure of said moving items,

said computerized device performing a continuously variable image correction to remove said moving items from said series of images to produce a series of corrected images,

said continuously variable image correction increasing an amount of image correction for a relatively higher measure of said moving items and decreasing said amount of image correction for a relatively lower measure of said moving items continuously as said measure of said moving items changes within said series of images,

said continuously variable image correction increasing and decreasing said amount of image correction in continuously variable amounts corresponding to changes in said measure of said moving items,

said continuously variable amounts being between predetermined maximum and minimum amounts of said image correction,

said computerized device being located at a first location with said camera device,

said computerized device outputting said series of corrected images to a second computerized device over a computerized network, and

said second computerized device being at a second location different than said first location.

10. A method comprising:

receiving a series of images into a computerized device,

comparing at least two images in said series of images using said computerized device to locate items that are in different positions in said at least two images to identify moving items within said series of images;

calculating a measure of said moving items using said computerized device;

performing a continuously variable image correction to remove said moving items from said series of images to produce a series of corrected images using said computerized device, said continuously variable image correction increasing an amount of image correction for a relatively higher measure of said moving items and decreasing said amount of image correction for a relatively lower measure of said moving items continuously as said measure of said moving items changes within said series of images, said continuously variable image correction increasing and decreasing said amount of image correction in continuously variable amounts corresponding to changes in said measure of said moving items, and said continuously variable amounts being between predetermined maximum and minimum amounts of said image correction; and

outputting said series of corrected images from said computerized device.

11. The method according to claim 10, said continuously variable image correction being applied to only portions of said images.

12. The method according to claim 10, said amount of image correction for a current frame further depending on said amount of image correction used for a previous frame.

13. The method according to claim 10, said continuously variable image correction being performed iteratively by repeating said calculating a measure of said moving items and performing said continuously variable image correction until said measure of said moving items in said corrected images is below a predetermined threshold.

14. The method according to claim 10, said continuously variable image correction comprising applying one of:

temporal median filtering, temporal order statistics filtering, temporal outlier rejection algorithms, temporal averaging, and temporal approximate median filtering.

15. The method according to claim 10, said method comprising an optical-based vehicle parking management method.

16. The method according to claim 10, said moving items comprising one of raindrops and snowflakes.

17. The method according to claim 10, said measure of said moving items comprising at least one of:

an average size of said moving items;

a maximum size of said moving items; and

an average rate of movement of said moving items.

18. A method comprising:

receiving a series of images into a computerized device,

comparing at least two images in said series of images using said computerized device to locate items that are in different positions in said at least two images to identify moving items within said series of images;

calculating a measure of said moving items using said computerized device;

performing a continuously variable image correction to remove said moving items from said series of images to produce a series of corrected images using said computerized device, said continuously variable image correction increasing an amount of image correction for a relatively higher measure of said moving items and decreasing said amount of image correction for a relatively lower measure of said moving items continuously as said measure of said moving items changes within said series of images, said continuously variable image correction increasing and decreasing said amount of image correction in continuously variable amounts corresponding to changes in said measure of said moving items, and said continuously variable amounts being between predetermined maximum and minimum amounts of said image correction; and

outputting said series of corrected images from said computerized device,

said computerized device being located at a first location with a camera device,

said computerized device outputting said series of corrected images to a second computerized device over a computerized network, and

said second computerized device being at a second location different than said first location.