System for capturing a driver image

• US 10,445,603 B1
• Filed: 12/11/2015
• Issued: 10/15/2019
• Est. Priority Date: 12/11/2015
• Status: Active Grant

• Current Assignee: Lytx, Inc.
• Original Assignee: Lytx, Inc.
• Inventors: Quach, Quoc Chan, Podlevsky, Phillip
• Primary Examiner(s): Philippe, Gims S
• Assistant Examiner(s): Gadomski, Stefan
• Application Number:
  US14/966,503
• Time in Patent Office: 1,404 Days
• CPC Class Codes: B60R 11/04 Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
• CPC Class Codes: B60R 2011/0003 inside the vehicle
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 20/597 Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G07C 5/085 using electronic data carriers
• CPC Class Codes: G07C 5/0866 the electronic data carrier being a digital video recorder in combination with video camera
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

A system for capturing an image of a driver includes an input interface and a processor. The input interface is to receive sensor data associated with a vehicle. The processor is to determine whether to capture a driver image based at least in part on the sensor data and, in the event it is determined to capture the driver image, to indicate to capture the driver image.

Claims

1. A system for capturing an image of a driver, comprising:

an inward facing camera mounted to a rear view mirror of a vehicle;

an input interface to receive sensor data associated with the vehicle, and

a processor to;

determine whether to capture a driver image using the inward facing camera based at least in part on the sensor data, wherein it is determined to capture the driver image in response to the sensor data indicating the driver is likely to be looking in the direction of the camera; and

in response to determining to capture the driver image;

indicate to capture the driver image;

receive the driver image;

store the driver image;

determine whether to extract image recognition parameters from the driver image locally with the processor or with a vehicle data server;

in response to determining to extract the image recognition parameters from the driver image locally;

extract the image recognition parameters from the driver image;

determine whether to perform image recognition locally with the processor or with the vehicle data server;

in response to determining to perform image recognition locally;

perform driver identification, wherein the processor determines a driver identification based at least in part on the extracted image recognition parameters;

prompt a driver of the vehicle to confirm the driver identification;

receive a response to the prompt, wherein the response to the prompt comprises an indication that the driver identification is correct or an indication that the driver identification is not correct; and

in response to the indication being the driver identification is incorrect, increase a count of a number of attempts to confirm the driver identification by one.

2. The system of claim 1, wherein the sensor data comprises lane marker data.

3. The system of claim 2, wherein the lane marker data is determined from video data, vehicle lane detection data, or LIDAR data.

4. The system of claim 2, wherein it is determined to capture the driver image in the event that the lane marker data indicates the vehicle is turning right.

5. The system of claim 1, wherein the sensor data comprises accelerometer data.

6. The system of claim 5, wherein it is determined to capture the driver image in the event that the accelerometer data indicates that the vehicle is turning right.

7. The system of claim 1, wherein the sensor data comprises vehicle speed data.

8. The system of claim 7, wherein vehicle speed data comprises speedometer data.

9. The system of claim 1, wherein the sensor data comprises turn signal data.

10. The system of claim 9, wherein it is determined to capture the driver image in response to the turn signal data indicating a right turn and a vehicle speed data indicates the vehicle speed is below a speed threshold.

11. The system of claim 9, wherein it is determined to capture the driver image in response to the turn signal data indicating a left turn and a vehicle speed data indicates the vehicle speed is below a speed threshold.

12. The system of claim 1, wherein the driver identification is aided by audio information.

13. The system of claim 1, wherein the driver is prompted for a voice sample.

14. The system of claim 1, wherein the driver image is stored associated with a set of trip data.

15. The system of claim 1, wherein the image recognition parameters are stored associated with a set of trip data.

18. The system of claim 1, wherein in response to determining to extract the image recognition parameters from the driver image, the processor is further to store the image recognition parameters.

16. A method for capturing an image of a driver, comprising:

receiving sensor data associated with a vehicle;

determining, using a processor, whether to capture, using an inward facing camera mounted to a rear view mirror of a vehicle, a driver image based at least in part on the sensor data, wherein it is determined to capture the driver image in response to the sensor data indicating the driver is likely to be looking in the direction of the camera; and

in response to determining to capture the driver image;

indicating to capture the driver image;

receiving the driver image;

storing the driver image;

determining whether to extract image recognition parameters from the driver image locally with the processor or with a vehicle data server;

in response to determining to extract the image recognition parameters from the driver image locally;

extracting the image recognition parameters from the driver image;

determining whether to perform image recognition locally with the processor or with the vehicle data server;

in response to determining to perform image recognition locally;

perform driver identification, wherein the processor determines a driver identification based at least in part on the extracted image recognition parameters;

prompting a driver of the vehicle to confirm the driver identification;

receiving a response to the prompt, wherein the response to the prompt comprises an indication that the driver identification is correct or an indication that the driver identification is not correct; and

in response to the indication being the driver identification is incorrect, increasing a count of a number of attempts to confirm the driver identification by one.

17. A computer program product for capturing an image of a driver of a vehicle, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving sensor data associated with a vehicle;

determining whether to capture, using an inward facing camera mounted to a rear view mirror of a vehicle, a driver image based at least in part on the sensor data, wherein it is determined to capture the driver image in response to the sensor data indicating the driver is likely to be looking in the direction of the camera; and

in response to determining to capture the driver image;

indicating to capture the driver image;

receiving the driver image;

storing the driver image;

determining whether to extract image recognition parameters from the driver image locally with the processor or with a vehicle data server;

in response to determining to extract the image recognition parameters from the driver image locally;

extracting the image recognition parameters from the driver image

determining whether to perform image recognition locally with the processor or with the vehicle data server;

in response to determining to perform image recognition locally;

performing driver identification, wherein the processor determines a driver identification based at least in part on the extracted image recognition parameters;

prompting a driver of the vehicle to confirm the driver identification;

receiving a response to the prompt wherein the response to the prompt comprises an indication that the driver identification is correct or an indication that the driver identification is not correct; and

in response to the indication being the driver identification is incorrect increasing a count of a number of attempts to confirm the driver identification by one.