ON-STREET VEHICLE PARKING OCCUPANCY ESTIMATION VIA CURB DETECTION

• US 20150242695A1
• Filed: 02/27/2014
• Published: 08/27/2015
• Est. Priority Date: 02/27/2014
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Fan, Zhigang, Bulan, Orhan
• Granted Patent: US 9,298,993 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/2431 Multiple classes
• CPC Class Codes: G06F 18/285 Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30264 Parking
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/753 Transform-based matching, e.g. Hough transform
• CPC Class Codes: G06V 10/762 using clustering, e.g. of similar faces in social networks
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 20/586 of parking space
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/14 indicating individual free spaces in parking areas

Abstract

A method and system for on-street vehicle parking occupancy estimation via curb detection comprises training a computer system to identify a curb, evaluating image data of the region of interest to determine a region wherein a curb is visible in said region of interest, and estimating a parking occupancy of said region of interest according to said region where said curb is visible.

Claims

1. A method comprising:

training a computer system to identify a curb;

evaluating image data of a region of interest to determine a region wherein a curb is visible in said region of interest; and

estimating a parking occupancy of said region of interest according to said region where said curb is visible.

2. The method of claim 1 wherein training said computer system to identify a curb further comprises:

collecting data from said scene of interest;

clustering said collected data into groups representative of a selected condition; and

training at least one classifier for each of said groups.

3. The method of claim 2 wherein evaluating image data of said region of interest to determine a region wherein said curb is visible further comprises:

selecting a plurality of classifiers from said at least one classifier for each of said groups;

applying said plurality of classifiers to said region of interest to identify regions wherein said curb is visible; and

combining results from said plurality of classifiers.

4. The method of claim 3 wherein said image data comprise at least one of:

a still photo;

a frame of video data; and

a plurality of frames of video data.

5. The method of claim 3 wherein combining results from said plurality of classifiers comprises at least one of:

averaging all of said results from said plurality of classifiers and comparing said average to a predefined threshold;

comparing each of said results from said plurality of classifiers to a predefined threshold for each of said classifiers; and

performing majority voting on said results from said plurality of classifiers.

6. The method of claim 1 wherein estimating a parking occupancy of said region of interest according to said region where said curb is visible further comprises:

determining a length of said region where said curb is visible; and

dividing said length by a predefined length to determine a number of available parking spaces.

7. The method of claim 1 wherein said steps of evaluating image data of a region of interest to determine a region wherein a curb is visible in said region of interest and estimating a parking occupancy of said region of interest according to said region where said curb is visible is done in real-time.

8. A method comprising:

collecting data from a scene of interest;

clustering said collected data into groups representative of a selected condition;

training at least one classifier for each of said groups to identify a curb;

evaluating image data of a region of interest to determine a region wherein a curb is visible in said region of interest; and

estimating a parking occupancy of said region of interest according to said region where said curb is visible.

9. The method of claim 8 wherein evaluating image data of said region of interest to determine a region wherein said curb is visible further comprises:

selecting a plurality of classifiers from said at least one classifier for each of said groups;

applying said plurality of classifiers to said region of interest to identify regions wherein said curb is visible; and

combining results from said plurality of classifiers.

10. The method of claim 9 wherein said image data comprises at least one of:

a still photo;

a frame of video data; and

a plurality of frames of video data.

11. The method of claim 9 wherein combining results from said plurality of classifiers comprises at least one of:

averaging all of said results from said plurality of classifiers and comparing said average to a predefined threshold;

comparing each of said results from said plurality of classifiers to a predefined threshold for each of said plurality of classifiers; and

performing majority voting on said results from said plurality of classifiers.

12. The method of claim 8 wherein estimating a parking occupancy of said region of interest according to said region where said curb is visible further comprises:

determining a length of said region where said curb is visible; and

dividing said length by a predefined length to determine a number of available parking spaces.

13. The method of claim 8 wherein said steps of evaluating image data of a region of interest to determine a region wherein a curb is visible in said region of interest, and estimating a parking occupancy of said region of interest according to said region where said curb is visible is done in real-time.

14. A system comprising:

a camera configured to collect image data;

a processor; and

a computer-usable medium embodying computer code, said computer-usable medium being coupled to said processor, said computer code comprising non-transitory instruction media executable by said processor configured for;

training a computer system to identify a curb;

evaluating image data of a region of interest to determine a region wherein a curb is visible in said region of interest; and

estimating a parking occupancy of said region of interest according to said region where said curb is visible.

15. The system of claim 14 wherein said computer code comprising non-transitory instruction media executable by said processor configured for training said computer system to identify a curb further comprises:

collecting data from said scene of interest;

clustering said collected data into groups representative of a selected condition; and

training at least one classifier for each of said groups.

16. The system of claim 15 wherein said computer code comprising non-transitory instruction media executable by said processor configured for evaluating image data of said region of interest to determine a region wherein said curb is visible further comprises:

selecting a plurality of classifiers from said at least one classifier for each of said groups;

applying said plurality of classifiers to said region of interest to identify regions wherein said curb is visible; and

combining results from said plurality of classifiers.

17. The system of claim 16 wherein said image data comprises at least one of:

a still photo;

a frame of video data; and

a plurality of frames of video data.

18. The system of claim 16 wherein said computer code comprising non-transitory instruction media executable by said processor configured for combining results from said plurality of classifiers comprises at least one of:

averaging all of said results from said plurality of classifiers and comparing said average to a predefined threshold;

comparing each of said results from said plurality of classifiers to a predefined threshold for each of said classifiers; and

performing majority voting on said results from said plurality of classifiers.

19. The system of claim 14 wherein said computer code comprising non-transitory instruction media executable by said processor configured for estimating a parking occupancy of said region of interest according to said region where said curb is visible further comprises:

determining a length of said region where said curb is visible; and

dividing said length by a predefined length to determine a number of available parking spaces.

20. The system of claim 14 wherein said computer code comprising non-transitory instruction media executable by said processor configured for said steps of evaluating image data of a region of interest to determine a region wherein a curb is visible in said region of interest and estimating a parking occupancy of said region of interest according to said region where said curb is visible is done in real-time.