Crowd-sourced driver grading

• US 10,504,304 B1
• Filed: 05/31/2019
• Issued: 12/10/2019
• Est. Priority Date: 04/15/2016
• Status: Active Grant

• Current Assignee: Allstate Insurance Company (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Ferguson, Dana
• Primary Examiner(s): Shafi, Muhammad
• Application Number:
  US16/427,607
• Time in Patent Office: 193 Days
• Field of Search: 701 323
• CPC Class Codes: B60R 2300/302 combining image information with GPS information or vehicle data, e.g. vehicle speed, gyro, steering angle data
• CPC Class Codes: B60R 2300/50 characterised by the display information being shared, e.g. external display, data transfer to other traffic participants or centralised traffic controller
• CPC Class Codes: B60R 2300/70 characterised by an event-triggered choice to display a specific image among a selection of captured images
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 50/265 Personal security, identity or safety
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/0825 using optical means
• CPC Class Codes: G07C 5/0891 Video recorder in combination with video camera

Abstract

An video analysis computing system driving analysis may include a camera associated with a first vehicle and having a viewing angle capable of capturing a video of one or more other vehicles in proximity to the first vehicle, a first memory location communicatively coupled to the camera, wherein the first memory location stores video data captured by the camera, and an evaluation module including a processor executing instructions that cause the processor to: evaluate the captured video stored in the first memory location to determine whether a driving event performed by a second vehicle has occurred, assign, in response to an identified driving event performed by the second vehicle, a driving event rating to a video showing the identified driving event, wherein the driving event rating may be calculated, at least in part, using a crowd-sourced driving event rating obtained after posting the video to a social network.

Claims

1. A system comprising:

a video capture device associated with a first vehicle and having a viewing angle capable of capturing a video of one or more other vehicles;

a first memory location communicatively coupled to the video capture device, wherein the first memory location stores a video captured by the video capture device;

a processor executing instructions that cause the processor to;

analyze, without user input and using a video analysis algorithm, the captured video stored in the first memory location to determine a driving event performed by a second vehicle in the captured video;

determine, by an event analyzer, a first event rating indicating a level of danger of the driving event with respect to at least one of;

a driver of the second vehicle, a driver of the first vehicle, the second vehicle and the first vehicle, wherein determining the first event rating includes;

aggregating other event ratings of the same driving event from a plurality of sources other than the driver of the second vehicle;

removing ratings outliers from the other event ratings; and

combining remaining ratings of the other event ratings to determine the first event rating;

receive a second event rating of the driving event from the driver of the second vehicle;

determine an accuracy of the second event rating relative to the first event rating;

determine an incentive to provide the driver of the second vehicle based on the determined accuracy of the second event rating.

2. The system of claim 1, wherein the instructions further cause the processor to:

evaluate the driving event captured in the video to determine a first trajectory of the second vehicle during the driving event;

generate, for display in a graphical user interface, a computer visualization of at least one second trajectory for the second vehicle, including digitally modelling one or more actions of a driver of the second vehicle, wherein the at least one second trajectory comprises a path for the second vehicle to travel to avoid causing the driving event; and

generate an educational video, including visually overlaying the computer visualization of the at least one second trajectory to avoid performing the driving event on the captured video showing the second vehicle performing the driving event, by modifying underlying digital video data of the captured video.

3. The system of claim 2 comprising:

the first vehicle, wherein the video capture device is physically attached to the first vehicle, and

wherein generating the educational video includes generating a computer rendering of a driving event corresponding to the video.

4. The system of claim 1, wherein the video capture device is physically incorporated into a mobile device.

5. The system of claim 1, wherein aggregating the other event ratings of the same driving event from the plurality of sources other than the driver of the second vehicle includes:

transmitting at least a portion of the captured video to a social network platform; and

receiving the other event ratings from a plurality of users on the social network platform.

6. The system of claim 1, wherein determining the incentive is performed further based on a number of videos taken of the driver of the second vehicle within a specified time frame.

7. The system of claim 1, wherein the video capture device captures the video for a predetermined time period before a trigger, the trigger causing the captured device to be stored into storage.

8. A method comprising:

analyzing, without user input and using a video analysis algorithm, captured video stored in memory to determine a driving event performed by a first vehicle in the captured video, the video captured by a video capture device associated with a second vehicle;

determining, by an event analyzer, a first event rating indicating a level of danger of the driving event with respect to at least one of;

a driver of the first vehicle, a driver of the second vehicle, the first vehicle and the second vehicle, wherein determining the first event rating includes;

aggregating other event ratings of the same driving event from a plurality of sources other than the driver of the first vehicle;

removing ratings outliers from the other event ratings; and

combining remaining ratings of the other event ratings to determine the first event rating;

receiving a second event rating of the driving event from the driver of the first vehicle;

determining an accuracy of the second event rating relative to the first event rating; and

determining an incentive to provide the driver of the first vehicle based on the determined accuracy of the second event rating.

9. The method of claim 8, further comprising:

evaluating the driving event captured in the video to determine a first trajectory of the first vehicle during the driving event;

generating, for display in a graphical user interface, a computer visualization of at least one second trajectory for the first vehicle, including digitally modelling one or more actions of a driver of the first vehicle, wherein the at least one second trajectory comprises a path for the first vehicle to travel to avoid causing the driving event; and

generating an educational video, including visually overlaying the computer visualization of the at least one second trajectory to avoid performing the driving event on the captured video showing the first vehicle performing the driving event, by modifying underlying digital video data of the captured video.

10. The method of claim 9, wherein the video capture device is physically attached to the first vehicle, and

wherein generating the educational video includes generating a computer rendering of a driving event corresponding to the video.

11. The method of claim 8, wherein the video capture device is physically incorporated into a mobile device.

12. The method of claim 8, wherein aggregating the other event ratings of the same driving event from the plurality of sources other than the driver of the second vehicle includes:

transmitting at least a portion of the captured video to a social network platform; and

receiving the other event ratings from a plurality of users on the social network platform.

13. The method of claim 8, wherein determining the incentive is performed further based on a number of videos taken of the driver of the second vehicle within a specified time frame.

14. The method of claim 8, wherein the video capture device captures the video for a predetermined time period before a trigger, the trigger causing the captured device to be stored into storage.

15. A non-transitory computer readable medium storing computer-readable instructions that, when executed, cause an apparatus to:

analyze, without user input and using a video analysis algorithm, captured video stored in memory to determine a driving event performed by a first vehicle in the captured video, the video captured by a video capture device associated with a second vehicle;

determine, by an event analyzer, a first event rating indicating a level of danger of the driving event with respect to at least one of;

a driver of the first vehicle, a driver of the second vehicle, the first vehicle and the second vehicle, wherein determining the first event rating includes;

aggregating other event ratings of the same driving event from a plurality of sources other than the driver of the first vehicle;

removing ratings outliers from the other event ratings; and

combining remaining ratings of the other event ratings to determine the first event rating;

receive a second event rating of the driving event from the driver of the first vehicle;

determine an accuracy of the second event rating relative to the first event rating; and

determine an incentive to provide the driver of the first vehicle based on the determined accuracy of the second event rating.

16. The non-transitory computer readable medium of claim 15, wherein the apparatus is further caused to:

evaluate the driving event captured in the video to determine a first trajectory of the first vehicle during the driving event;

generate, for display in a graphical user interface, a computer visualization of at least one second trajectory for the first vehicle, including digitally modelling one or more actions of a driver of the first vehicle, wherein the at least one second trajectory comprises a path for the first vehicle to travel to avoid causing the driving event; and

generate an educational video, including visually overlaying the computer visualization of the at least one second trajectory to avoid performing the driving event on the captured video showing the first vehicle performing the driving event, by modifying underlying digital video data of the captured video.

17. The non-transitory computer readable medium of claim 16, wherein the video capture device is physically attached to the first vehicle, and

wherein generating the educational video includes generating a computer rendering of a driving event corresponding to the video.

18. The non-transitory computer readable medium of claim 15, wherein the video capture device is physically incorporated into a mobile device.

19. The non-transitory computer readable medium of claim 15, wherein aggregating the other event ratings of the same driving event from the plurality of sources other than the driver of the second vehicle includes:

transmitting at least a portion of the captured video to a social network platform; and

receiving the other event ratings from a plurality of users on the social network platform.

20. The non-transitory computer readable medium of claim 15, wherein determining the incentive is performed further based on a number of videos taken of the driver of the second vehicle within a specified time frame.