DETERMINING OVERLAP OF A PARKING SPACE BY A VEHICLE

• US 20160307047A1
• Filed: 04/14/2016
• Published: 10/20/2016
• Est. Priority Date: 04/17/2015
• Status: Active Grant

• Current Assignee: Ubicquia IQ LLC
• Original Assignee: General Electric Company
• Inventors: Krishnamoorthy, Lokesh Babu, de Leon, Francisco, Vudumula, Madhavi, Hackett, Aileen Margaret
• Granted Patent: US 10,872,241 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04847 Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/30264 Parking
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• CPC Class Codes: G08G 1/148 Management of a network of parking areas
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04N 23/661 Transmitting camera control signals through networks, e.g. control via the Internet
• CPC Class Codes: H04N 23/6811 based on the image signal
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof

Abstract

A system comprising a computer-readable storage medium storing at least one program and a method for determining vehicle overlap with a parking space is presented. The method may include accessing a set of pixel coordinates defining a location of a vehicle within an image, and translating the set of pixel coordinates to a set of global coordinates defining a geospatial location of the vehicle. The method may further include accessing a set of known coordinates of the parking space. The method may further include determining an overlap amount by comparing the global coordinates of the vehicle with the known global coordinates of the parking space, and determining the vehicle overlaps the parking space based on the overlap amount transgressing a threshold overlap amount. The method may further include updating a data object associated with the vehicle to indicate the vehicle overlaps the parking space.

Claims

1. A system comprising:

one or more hardware processors;

a machine-readable medium storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising;

accessing, from a networked data store, a set of pixel coordinates of a vehicle, the set of pixel coordinates defining a location of the vehicle within an image of a parking space,

translating the set of pixel coordinates of the vehicle to a first set of global coordinates, the first set of global coordinates defining a first geospatial location corresponding to the vehicle;

accessing, from the networked data store, a second set of global coordinates defining a second geospatial location corresponding to the parking space;

determining an overlap amount by comparing the first set of global coordinates to the second set of global coordinates, the overlap amount including an amount of the parking space covered by the vehicle;

determining the vehicle overlaps the parking space based on the overlap amount transgressing a threshold overlap amount; and

updating a data object associated with the vehicle to indicate the vehicle overlaps the parking space.

2. The system of claim 1, wherein the comparing of the first set of global coordinates to the second set of global coordinates includes:

computing a first centroid using the first set of global coordinates, the first centroid corresponding an arithmetic mean position of all points of the vehicle defined by the set of global coordinates;

computing a second centroid using the second set of global coordinates, the second centroid corresponding to an arithmetic mean position of all points of the parking space defined by the second set of global coordinates; and

determining a distance between the first centroid and the second centroid, the distance corresponding to the overlap amount.

3. The system of claim 1, wherein translating the set of pixel coordinates to the set of global coordinates includes using a homography matrix algorithm to perform a direct linear transformation of the set of pixel coordinates to the set of global coordinates.

4. The system of claim 1, further comprising determining an occupancy status of the parking space based in part on determining the vehicle overlaps the parking space.

5. The system of claim 4, wherein:

the set of pixel coordinates are a first set of pixel coordinates defining a first location of the vehicle in a first image; and

the determining of the occupancy status of the parking space further includes determining the vehicle is stationary based on a comparison of the first set of pixel coordinates with a second set of pixel coordinates, the second set of pixel coordinates defining a second location of the vehicle in a second image.

6. The system of claim 2, computing the first centroid includes calculating an arithmetic mean position of all points in the vehicle define by the first set of global coordinates.

7. The system of claim 1, where the set of pixel coordinates include a coordinate pair defining a location of each corner of the vehicle in the image.

8. The system of claim 1, wherein the set of pixel coordinates are included in a data packet received from a camera node, the data packet including parking metadata, the camera node including a camera operable to record the image.

9. The system of claim 1, wherein:

the threshold overlap amount includes a minimum overlap amount; and

the determining the vehicle overlaps the parking space includes determining the overlap amount exceeds the minimum overlap amount.

10. The system of claim 1, wherein determining the overlap amount includes calculating a distance between the locations defined by the first set of global coordinates and the second set of global coordinates.

11. A method comprising:

accessing, from a networked data store, a set of pixel coordinates of a vehicle, the set of pixel coordinates defining a location of the vehicle within an image of a parking space;

translating the set of pixel coordinates of the vehicle to a first set of global coordinates, the first set of global coordinates defining a first geospatial location corresponding to the vehicle;

accessing, from a data object associated with the parking space, a second set of global coordinates defining a second geospatial location corresponding to the parking space;

determining an overlap amount by comparing the first set of global coordinates to the second set of global coordinates, the overlap amount including an amount of the parking space covered by the vehicle;

determining the vehicle overlaps the parking space based on the overlap amount transgressing a threshold overlap amount; and

updating a data object associated with the vehicle to indicate the vehicle overlaps the parking space.

12. The method of claim 11, wherein the comparing of the first set of global coordinates to the second set of global coordinates includes:

computing a first centroid using the first set of global coordinates, the first centroid corresponding an arithmetic mean position of all points of the vehicle defined by the set of global coordinates;

computing a second centroid using the second set of global coordinates, the second centroid corresponding to an arithmetic mean position of all points of the parking space defined by the second set of global coordinates; and

determining a distance between the first centroid and the second centroid, the distance corresponding to the overlap amount.

13. The method of claim 11, wherein the translating of the set of pixel coordinates to the set of global coordinates includes using a homography matrix algorithm to perform a direct linear transformation of the set of pixel coordinates to the set of global coordinates.

14. The method of claim 11, determining an occupancy status of the parking space based in part on determining the vehicle overlaps the parking space.

15. The method of claim 14, wherein:

the set of pixel coordinates are a first set of pixel coordinates defining a first location of the vehicle in a first image; and

the determining of the occupancy status of the parking space further includes determining the vehicle is stationary based on a comparison of the first set of pixel coordinates with a second set of pixel coordinates, the second set of pixel coordinates defining a second location of the vehicle in a second image.

16. The method of claim 11, where the set of pixel coordinates include a coordinate pair defining a location of each corner of the vehicle in the image.

17. The method of claim 11, wherein the set of pixel coordinates are included in a data packet of metadata received from a camera node, the camera node including a camera operable to record the image.

18. The method of claim 11, wherein:

the threshold overlap amount includes a minimum overlap amount; and

the determining the vehicle overlaps the parking space includes determining the overlap amount exceeds the minimum overlap amount.

19. The method of claim 11, wherein the second set of global coordinates are user-specified coordinates enter via user interface.

20. A non-transitory machine-readable storage medium, and embodying instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

accessing, from a networked data store, a set of pixel coordinates of a vehicle, the set of pixel coordinates defining a location of the vehicle within an image of a parking space;

translating the set of pixel coordinates of the vehicle to a first set of global coordinates, the first set of global coordinates defining a first geospatial location corresponding to the vehicle;

accessing, from a data object associated with the parking space, a second set of global coordinates defining a second geospatial location corresponding to the parking space;

determining an overlap amount by comparing the first set of global coordinates to the second set of global coordinates, the overlap amount including an amount of the parking space covered by the vehicle;

determining the vehicle overlaps the parking space based on the overlap amount transgressing a threshold overlap amount; and

updating a data object associated with the vehicle to indicate the vehicle overlaps the parking space.