Methods and apparatus for vehicle operation analysis

• US 10,189,479 B2
• Filed: 04/06/2016
• Issued: 01/29/2019
• Est. Priority Date: 04/06/2016
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Innes, Timothy, Mitchell, Stephen, Naing, Soe, O'Donnell, Matthew, Silva, Andrew
• Primary Examiner(s): Paige, Tyler D
• Application Number:
  US15/091,859
• Publication Number:
  US 20170291611A1
• Time in Patent Office: 1,028 Days
• Field of Search: 701 32
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2555/60 Traffic rules, e.g. speed limits or right of way
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/44 for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]

Abstract

Methods and apparatus are disclosed to monitor and evaluate vehicle operator behavior. An example method includes processing, using a particularly programmed processor, image data obtained with respect to a vehicle to identify an object in the image data. The example method includes measuring, using the mobile device, a geographic location of the vehicle. The example method includes determining, using the mobile device, an operating state of the vehicle. The example method includes analyzing the object in the image data, the geographic location, and the operating state of the vehicle to determine a behavior of the vehicle. The example method includes generating a score for a driver associated with the vehicle by comparing the behavior of the vehicle with a reference behavior, the reference behavior quantified by one or more driving metrics. The example method includes outputting the score.

Claims

1. A method to monitor, evaluate and quantify vehicle behavior, the method comprising:

processing, using a mobile device including a processor, image data obtained by a camera showing an environment including a) at least a portion of a vehicle and b) objects external to and in proximity to the vehicle, wherein the objects comprise a traffic sign, and wherein processing the image data comprises using a component analysis of the image data to isolate features in the image data to identify the objects in relation to the vehicle and to identify the traffic sign among the objects based on at least one of a shape, color, or content of the traffic sign;

identifying, using the mobile device, a driver event using a pattern of objects including the traffic sign and the vehicle in the image data, the driver event involving the traffic sign and associated with a driver event rule specifying a reference vehicle operating behavior for the driver event, the driver event rule including observance of the traffic sign;

measuring, using the mobile device, a geographic location of the vehicle using a received signal indicating the geographic location of the vehicle;

determining, using the mobile device, an operating state of the vehicle using a received indication of vehicle motion;

evaluating, using the mobile device, compliance with the driver event rule for the driver event by at least;

a) calculating a proximity of the traffic sign to the vehicle based on a distance between the vehicle and the traffic sign and ii) the operating state of the vehicle, the distance determined using the geographic location of the vehicle and a geometry between the vehicle and the traffic sign extracted from the image data; and

b) comparing the proximity of the traffic sign and the operating state of the vehicle to determine an actual vehicle operating behavior; and

c) generating a score associated with operation of the vehicle by comparing the actual vehicle operating behavior with the reference vehicle operating behavior; and

outputting, using the mobile device, a profile of the actual vehicle operating behavior including the score to quantify an evaluation of the actual vehicle operating behavior.

2. The method of claim 1, wherein the processing further comprises processing the image data using an artificial neural network with independent component analysis to identify the traffic sign in the image data.

3. The method of claim 1, wherein the processing further comprises processing the image data using an artificial neural network with cascade learning to identify the traffic sign in the image data.

4. The method of claim 1, wherein the traffic sign comprises a stop sign.

5. The method of claim 1, wherein the operating state comprises a speed of the vehicle.

6. The method of claim 1, wherein compliance with the driver event rule is evaluated using one or more driving metrics comprising at least one of:

a) compliance with stop signs, b) compliance with traffic lights, c) compliance with speed limits, d) turn signal usage, e) cornering g-force, f) lane centering, or g) lead car proximity.

7. The method of claim 6, wherein the profile comprises an overall score and scores for each of the one or more driving metrics.

8. The method of claim 1, wherein the evaluating compliance with the driver event rule is facilitated via an application server.

9. The method of claim 8, wherein the application server is a cloud-based application server.

10. The method of claim 9, further including aggregating, using the cloud-based application server, scores from a plurality of vehicles to form an aggregate profile of actual vehicle operating behavior to be shared with the mobile device.

11. A device comprising:

a memory including machine readable instructions; and

a processor to execute the instructions to perform operations comprising;

processing image data obtained by a camera showing an environment including a) at least a portion of a vehicle and b) objects external to and in proximity to the vehicle, wherein the objects comprise a traffic sign, and wherein processing the image data comprises using a component analysis of the image data to isolate features in the image data to identify the objects in relation to the vehicle and to identify the traffic sign among the objects based on at least one of a shape, color, or content of the traffic sign;

identifying a driver event using a pattern of objects including the traffic sign and the vehicle in the image data, the driver event involving the traffic sign and associated with a driver event rule specifying a reference vehicle operating behavior for the driver event, the driver event rule including observance of the traffic sign;

measuring a geographic location of the vehicle using a received signal indicating the geographic location of the vehicle;

determining an operating state of the vehicle using a received indication of vehicle motion;

evaluating compliance with the driver event rule for the driver event by at least;

a) calculating a proximity of the traffic sign to the vehicle based on a distance between the vehicle and the traffic sign and ii) the operating state of the vehicle, the distance determined using the geographic location of the vehicle and a geometry between the vehicle and the traffic sign extracted from the image data; and

b) comparing the proximity of the traffic sign and the operating state of the vehicle to determine an actual vehicle operating behavior; and

c) generating a score associated with operation of the vehicle by comparing the actual vehicle operating behavior with the reference vehicle operating behavior; and

outputting a profile of the actual vehicle operating behavior including the score to quantify an evaluation of the actual vehicle operating behavior.

12. The device of claim 11, wherein the operations further comprise processing the image data using an artificial neural network with independent component analysis to identify the traffic sign in the image data.

13. The device of claim 11, wherein the operations further comprise processing the image data using an artificial neural network with cascade learning to identify the traffic sign in the image data.

14. The device of claim 11, wherein the traffic sign comprises a stop sign.

15. The device of claim 11, wherein the operating state comprises a speed of the vehicle.

16. The device of claim 11, wherein compliance with the driver event rule is evaluated using one or more driving metrics comprising at least one of:

a) compliance with stop signs, b) compliance with traffic lights, c) compliance with speed limits, d) turn signal usage, e) cornering g-force, f) lane centering, or g) lead car proximity.

17. The device of claim 16, wherein the profile comprises an overall score and scores for each of the one or more driving metrics.

18. A non-transitory computer readable media including instructions that, when executed, cause a machine to perform operations comprising:

processing image data obtained by a camera showing an environment including a) at least a portion of a vehicle and b) objects external to and in proximity to the vehicle, wherein the objects comprise a traffic sign, and wherein processing the image data comprises using a component analysis of the image data to isolate features in the image data to identify the objects in relation to the vehicle and to identify the traffic sign among the objects based on at least one of a shape, color, or content of the traffic sign;

identifying a driver event using a pattern of objects including the traffic sign and the vehicle in the image data, the driver event involving the traffic sign and associated with a driver event rule specifying a reference vehicle operating behavior for the driver event, the driver event rule including observance of the traffic sign;

measuring a geographic location of the vehicle using a received signal indicating the geographic location of the vehicle;

determining an operating state of the vehicle using a received indication of vehicle motion;

evaluating compliance with the driver event rule for the driver event by at least;

a) calculating a proximity of the traffic sign to the vehicle based on a distance between the vehicle and the traffic sign and ii) the operating state of the vehicle, the distance determined using the geographic location of the vehicle and a geometry between the vehicle and the traffic sign extracted from the image data; and

b) comparing the proximity of the traffic sign and the operating state of the vehicle to determine an actual vehicle operating behavior; and

c) generating a score associated with operation of the vehicle by comparing the actual vehicle operating behavior with the reference vehicle operating behavior; and

outputting a profile of the actual vehicle operating behavior including the score to quantify an evaluation of the actual vehicle operating behavior.