Safety score using video data but without video

• US 9,594,725 B1
• Filed: 08/28/2013
• Issued: 03/14/2017
• Est. Priority Date: 08/28/2013
• Status: Active Grant

• Current Assignee: Lytx, Inc.
• Original Assignee: Lytx, Inc.
• Inventors: Kypri, Niki, Cook, Bryon
• Primary Examiner(s): Raymond, Edward
• Application Number:
  US14/012,136
• Time in Patent Office: 1,294 Days
• Field of Search: 702/189, 702182-185
• US Class Current: 1/1
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/06 in graphical form
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/0866 the electronic data carrier being a digital video recorder in combination with video camera
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A safety score using video data but without video comprises an input interface and a processor. The input interface is configured to receive sensor data. The processor is configured to provide the sensor data to a safety score determiner, and determine a safety score using the safety score determiner without using inward facing video data, wherein the safety score determiner has been trained using a data set that includes sensor data with inward facing video data. The system for determining a safety score additionally comprises a memory coupled to the processor and configured to provide the processor with instructions.

Claims

1. A system for determining a safety score, comprising:

an input interface configured to receive maneuver data; and

a processor configured to;

determine a safety score from the maneuver data without inward facing video data using a safety score determiner; and

output the safety score, wherein the safety score is associated with the maneuver data and forms at least a partial basis to train the safety score determiner;

wherein inward facing video data is processable to identify anomalous events and train the safety score determiner and the safety score determiner has been trained using a data set that includes previously-collected maneuver data associated with inward facing video data.

2. A system as in claim 1, wherein the safety score determiner comprises a library of maneuver data and safety scores.

3. A system as in claim 1, wherein the safety score determiner determines the safety score by using a table.

4. A system as in claim 1, wherein the safety score determiner determines the safety score by interpolating between values in a table.

5. A system as in claim 1, wherein the safety score determiner determines the safety score by using a neural network.

6. A system as in claim 1, wherein the safety score determiner determines the safety score by using machine learning techniques.

7. A system as in claim 1, wherein the safety score determiner determines the safety score by using a support vector machine.

8. A system as in claim 1, wherein the system for determining the safety score additionally determines a driver safety score.

9. A system as in claim 8, wherein the driver safety score is recomputed periodically.

10. A system as in claim 1, wherein the system for determining the safety score additionally determines a fleet safety score.

11. A system as in claim 1, wherein the system for determining the safety score additionally determines an unsafe drivers list.

12. A system as in claim 11, wherein the unsafe drivers list is recomputed periodically.

13. A system as in claim 11, wherein the unsafe drivers list is a ranked list.

14. A system as in claim 11, wherein the unsafe drivers list comprises a list of drivers with safety scores worse than a threshold.

15. A system as in claim 11, wherein the unsafe drivers list comprises a list of drivers with top 10% worst safety scores.

16. A system as in claim 11, wherein the unsafe drivers list comprises a ranked list of drivers, the list including a pre-determined number of worst ranking drivers based on safety scores.

17. A system as in claim 1, wherein the system for determining the safety score additionally determines a list of drivers that require coaching.

18. A system as in claim 1, wherein the data set that includes maneuver data associated with inward facing video data comprises a third party data set.

19. A method for determining a safety score, comprising:

receiving maneuver data;

determining, using a processor, a safety score from the maneuver data without inward facing video data using a safety score determiner; and

outputting the safety score, wherein the safety score is associated with the maneuver data and forms at least a partial basis to train the safety score determiner;

wherein inward facing video data is processable to identify anomalous events and train the safety score determiner and the safety score determiner has been trained using a data set that includes previously-collected maneuver data associated with inward facing video data.

20. A computer program product for determining a safety score, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving maneuver data;

determining a safety score from the maneuver data without inward facing video data using a safety score determiner; and

outputting the safety score, wherein the safety score is associated with the maneuver data and forms at least a partial basis to train the safety score determiner;

wherein inward facing video data is processable to identify anomalous events and train the safety score determiner and the safety score determiner has been trained using a data set that includes previously-collected maneuver data associated with inward facing video data.

21. A method for determining a safety score, comprising:

receiving maneuver data, wherein the maneuver data does not include inward facing video data;

determining, using a processor, a safety score based on the maneuver data including;

determining whether the maneuver data matches at least one element of a set of previously-collected maneuver data, wherein the set of previously-collected maneuver data is trained by inward facing video data;

if the maneuver data matches at least one element of the set of previously-collected maneuver data, determining the safety score based on an average of scores associated with the at least one element of the set matching the received maneuver data; and

if the maneuver data does not match at least one element of the set of previously-collected maneuver data, determining the safety score based on a combination of scores associated with at least one element of the set meeting a threshold similarity compared with the received maneuver data; and

outputting the safety score.