Continuous identity monitoring for classifying driving data for driving performance analysis

Patent metadata

Field	Value
Publication number	US-10229461-B2
Application number	US-201514589903-A
Country	US
Kind code	B2
Filing date	Jan 5, 2015
Priority date	Jan 6, 2014
Publication date	Mar 12, 2019
Grant date	Mar 12, 2019

Abstract

Embodiments are provided for determining driving behavior. In an example method for determining driver behavior from a driving session, the method includes obtaining sensor data from a sensor during a driving session, obtaining image data from an imaging device during the driving session, and analyzing at least one of the sensor data and the image data from the driving session, to identify an event of interest. The method further includes assigning a classification to the event of interest according to a correlation between the sensor data for the event of interest and at least one image from the image data for the event of interest, the correlation based on time the sensor data and the image data is obtained during the driving session, and, wherein the at least one image for the event of interest provides the context for the event of interest.

First claim

The invention claimed is:

1. A method for determining driver behavior from at least one driving session, comprising:
sensing at least one physical attribute of biometric data of a driver of a vehicle, by at least one sensor to obtain sensor data during the at least one driving session;
capturing a plurality of images by at least one imaging device to obtain image data during the at least one driving session;
analyzing the sensor data and the image data from the at least one driving session, to identify at least one event of interest, and a reaction of the driver to the at least one event of interest;
creating a biometrical behavioral driver profile from the biometric data extracted from at least some of the at least one sensor;
obtaining predefined characteristics of a positive event, of a negative event, and of an exception event;
correlating between the sensor data for the at least one event of interest and at least one image from the image data for the at least one event of interest, based on a time the sensor data and the image data are obtained during the at least one driving session, wherein the at least one image for the at least one event of interest provides context for the at least one event of interest;
classifying the at least one event of interest to one of three classes defined as a positive event class, a negative event class, and an exception event class according to the correlation and based on the predefined characteristics;
determining when the driver reaction is an expected reaction to the at least one event of interest according to the classification;
assigning a driver profile score to the biometrical behavioral driver profile, based on the determination;
transmitting the sensor data and the image data, in real time, over a communication network, to a remote server to be presented to a user of the remote server; and
transmitting data to the driver of the at least one driving session to make the data available to the driver, based on the biometrical behavioral driver profile and according to the driver profile score.

2. The method of claim 1 , wherein the sensor data and the image data are transmitted to at least one storage medium over the communication network.

3. The method of claim 2 , wherein the sensor data and the image data are transmitted over the communication network to the remote server for the analyzing at least one of the sensor data or the image data from the at least one driving session, to identify the at least one event of interest.

4. The method of claim 1 , wherein the at least one driving session includes a single driving session and the driver profile score is determined for the single driving session.

5. The method of claim 1 , wherein the at least some of the at least one sensor used to extract the biometric data is contained in a wearable device.

6. The method of claim 5 , wherein the wearable device includes sensors for measuring at least one of heart rate, pulse rate, body temperature, skin moisture, and fat, and an imaging device for visually identifying the driver.

7. The method of claim 1 , wherein the at least one event of interest includes a plurality of events of interest.

8. The method of claim 7 , additionally comprising calculating an insurance premium for at least one of the driver and the vehicle, from at least one of the driver profile score and the at least one event of interest.

9. The method of claim 7 , wherein the obtaining image data from the at least one imaging device includes obtaining images of a path traversed by the vehicle during the at least one driving session.

10. The method of claim 7 , wherein the obtaining image data from the at least one imaging device includes obtaining images of the driver of the vehicle during the at least one driving session.

11. The method of claim 10 , wherein the context provided by the at least one image relates to at least one of identification of the driver and actions taken by the driver.

12. The method of claim 7 , additionally comprising obtaining additional data about the driver and using the additional data to recalculate the driver profile score.

13. A system for determining driver behavior from at least one driving session, comprising:
at least one sensor for sensing at least one physical attribute of biometric data of a driver of a vehicle to obtain sensor data during the at least one driving session;
an imaging device for capturing a plurality of images to obtain images during the at least one driving session; and
a processor in communication with the at least one sensor and the imaging device, the processor programmed to:
analyze at least one of the sensor data or image data from the at least one driving session, to identify at least one event of interest and a reaction of the driver to the at least one event of interest;
create a biometrical behavioral driver profile from the biometric data extracted from at least some of the at least one sensor;
obtain predefined characteristics of a positive event, of a negative event, and of an exception event;
correlate between the sensor data for the at least one event of interest and at least one image from the image data for the at least one event of interest, based on a time the sensor data and the image data are obtained during the at least one driving session, wherein the at least one image for the at least one event of interest provides context for the at least one event of interest;
classify the at least one event of interest to one of three classes defined as a positive event class, a negative event class, and an exception event class according to the correlation and based on the predefined characteristics;
determine when the driver reaction is an expected reaction to the at least one event of interest according to the classification;
assign a driver profile score to the biometrical behavioral driver profile, based on the determination;
transmit the sensor data and the image data, in real time, over a communication network, to a remote server, to be presented to a user of the remote server; and
transmit data to the driver of the at least one driving session to make the data available to the driver, based on the biometrical behavioral driver profile and according to the driver profile score.

14. The system of claim 13 , wherein the imaging device includes a camera.

15. The system of claim 14 , wherein the imaging device includes a plurality of cameras on both sides of the imaging device for obtaining front and rearward images with respect to the vehicle.

16. The system of claim 13 , additionally comprising a wearable device to be worn by the driver for obtaining the biometric data of the driver during the at least one driving session, the wearable device in communication with the processor.

17. The system of claim 16 , wherein the processor is additionally programmed to correlate a driver identification by associating the biometric data of the driver to the at least one event of interest, for the at least one driving session.

18. The system of claim 16 , wherein the wearable device includes sensors for measuring at least one of heart rate, pulse rate, body temperature, skin moisture, and fat, and an imaging device for visually identifying the driver.

19. The system of claim 13 , wherein the processor is additionally programmed to correlate a driver identification by associating an image of the driver to the at least one event of interest, for the at least one driving session.

Assignees

• Harman Int Ind

Inventors

• Akiva Ohad
• Atsmon Alon
• Atsmon Dan

Classifications

• G07C5/0841

  Registering performance data (recording measured values G01D; information storage G11B) · CPC title

• G07C5/0808

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G08G1/16

  Anti-collision systems (road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08) · CPC title

• G06Q40/08 Primary

  Insurance · CPC title