System and method for determining probability that a vehicle driver is associated with a driver identifier

• US 10,503,990 B2
• Filed: 10/15/2018
• Issued: 12/10/2019
• Est. Priority Date: 07/05/2016
• Status: Active Grant

• Current Assignee: Nauto, Inc.
• Original Assignee: Nauto, Inc.
• Inventors: Gleeson-May, Michael, Soo, Frederick, Heck, Stefan
• Primary Examiner(s): Prince, Jessica M
• Application Number:
  US16/160,809
• Publication Number:
  US 20190050657A1
• Time in Patent Office: 421 Days
• CPC Class Codes: B60R 25/25 using biometry
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures
• CPC Class Codes: G06V 20/597 Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

A method for driver identification including recording a first image of a vehicle driver; extracting a set of values for a set of facial features of the vehicle driver from the first image; determining a filtering parameter; selecting a cluster of driver identifiers from a set of clusters, based on the filtering parameter; computing a probability that the set of values is associated with each driver identifier of the cluster; determining, at the vehicle sensor system, driving characterization data for the driving session; and in response to the computed probability exceeding a first threshold probability: determining that the new set of values corresponds to one driver identifier within the selected cluster, and associating the driving characterization data with the one driver identifier.

Claims

1. A method for driver identification comprising:

recording an image sequence of a vehicle driver at an interior-facing camera of a vehicle system during a driving session, in response to detecting a sampling event;

determining a presence of a face in each image of the image sequence at a face detection module of the vehicle system to generate an image sequence subset;

transmitting the image sequence subset to a remote computing system;

extracting a feature vector from the image sequence subset at a feature extraction module of the remote computing system;

determining a set of auxiliary sensor signals;

computing a probability that the vehicle driver is associated with a driver identifier based on the feature vector in combination with the set of auxiliary sensor signals;

in response to the probability exceeding a first threshold value, automatically associating the driving session with the driver identifier;

in response to the first threshold value exceeding the probability and the probability exceeding a second threshold value, receiving a driver identification input from a user and associating the driving session with a user-selected driver identifier; and

in response to the second threshold value exceeding the probability, generating a new driver identifier corresponding to the feature vector in combination with the auxiliary sensor signal and associating the new driver identifier with the driving session.

2. The method of claim 1, further comprising transmitting the image sequence subset in response to a number of images in the subset exceeding a threshold number.

3. The method of claim 1, further comprising determining an image quality associated with each image of the image sequence, wherein recording of each image of the image sequence is performed based on the image quality of a preceding image of the sequence exceeding a threshold quality.

4. The method of claim 1, wherein the set of auxiliary sensor signals comprises a non-visual identification signal.

5. The method of claim 4, wherein the non-visual identification signal comprises driver login information received at a client application executing on a mobile device associated with the vehicle driver.

6. The method of claim 1, wherein detecting the sampling event comprises detecting a start time point of the driving session.

7. The method of claim 6, wherein detecting the start time point of the driving session comprises detecting a pattern of vehicle door opening and vehicle door closing at a sensor of the vehicle system.

8. The method of claim 1, wherein the set of auxiliary sensor signals comprises a set of historical data associated with past driving sessions.

9. The method of claim 8, wherein the set of historical data comprises a most recent previous driver identifier determined prior to the driving session.

10. The method of claim 8, wherein the set of historical data comprises a most frequent driver identifier determined in association with the past driving sessions.

11. A method for driver identification comprising:

recording a first image of a vehicle driver at an interior-facing camera of a vehicle system during a driving session;

computing a first probability that the vehicle driver is associated with a driver identifier based on the first image;

in response to the first probability falling below a first threshold value, recording a second image of the vehicle driver, and recomputing the first probability that the vehicle driver is associated with the driver identifier based on the first image and the second image;

in response to the first probability exceeding the first threshold value, transmitting the first and second images to a remote computing system;

extracting a feature vector from the first and second images at a feature extraction module of the remote computing system;

determining a set of auxiliary sensor signals;

computing a second probability that the vehicle driver is associated with the driver identifier based on the feature vector in combination with the set of auxiliary sensor signals;

associating the driver identifier with the driving session based on the second probability;

in response to the second probability exceeding a second threshold value, automatically associating the driving session with the driver identifier;

in response to the second threshold value exceeding the second probability and the second probability exceeding a third threshold value, receiving a driver identification input from a user and associating the driving session with a user-selected driver identifier; and

in response to the third threshold value exceeding the second probability, generating a new driver identifier corresponding to the feature vector in combination with the auxiliary sensor signal and associating the new driver identifier with the driving session.

12. The method of claim 11, wherein recording the first image is performed in response to detecting a sampling event.

13. The method of claim 12, wherein detecting the sampling event comprises detecting a start time point of the driving session.

14. The method of claim 13, wherein detecting the start time point of the driving session comprises detecting a user interaction between the vehicle driver and a mobile device associated with the vehicle driver and in communication with the vehicle system.

15. The method of claim 11, wherein the set of auxiliary sensor signals comprises a set of historical data associated with past driving sessions.

16. The method of claim 15, wherein the set of historical data comprises a most recent previous driver identifier determined prior to the driving session.

17. The method of claim 15, wherein the set of historical data comprises a most frequent driver identifier determined in association with the past driving sessions.

18. The method of claim 11, wherein the set of auxiliary sensor signals comprises a biometric signal received from the vehicle driver.

19. The method of claim 11, wherein the set of auxiliary sensor signals comprises a beacon signal received at the vehicle system from a mobile device associated with the vehicle driver.