Systems and methods for assessing risk based on driver gesture behaviors
A system and method captures various gestures or movements made by a driver of a vehicle while driving. Based on the captured gestures or movements, the system and method determines driver gesture behaviors which relate to the driver's driving behaviors. The system and method then performs risk assessment by correlating the driver gesture behaviors with potential recognizable losses involving the driver and/or vehicle. Based on the risk assessment, the system and method assigns ratings for the driver which may be used for insurance rating purposes.
1. A computer-implemented method for assessing risk based on driver behavior, the method comprising:
implementing an image sensor at a vehicle, the image sensor oriented to capture images of a driver of the vehicle;
receiving, from the image sensor and at one or more electronic devices, one or more images of the driver of the vehicle captured via the image sensor;
analyzing the one or more images via the one or more electronic devices, including:
(i) detecting via the one or more electronic devices (a) a first detected hand or head position of the driver at a first time, and (b) a second non-binary value representing a second detected hand or head position of the driver at a second time; and
(ii) determining via the one or more electronic devices: (a) a first non-binary value representing a first risk of loss based on the first detected hand or head position and (b) a second non-binary value representing a second risk of loss based on the second detected hand or head position relative to the steering wheel;
calculating, via the one or more electronic devices, a driving score based, at least in part, on the first and second determined non-binary values representing the first and second risks of loss; and
displaying, via the one or more electronic devices, the driving score.
2. The computer-implemented method of claim 1 , further comprising activating the image sensor in response to detecting a mobile device at the vehicle.
3. The computer-implemented method of claim 2 , wherein detecting the mobile device includes detecting the mobile device via a short range wireless communication.
4. The computer-implemented method of claim 2 , wherein the one or more electronic devices include the mobile device, wherein the analyzing and the calculating are performed by the mobile device.
5. The computer-implemented method of claim 1 , further comprising time-stamping the one or more images to indicate a date and time of capture.
6. The computer-implemented method of claim 1 , wherein each of the one or more electronic devices are disposed at the vehicle.
7. The computer-implemented method of claim 1 , wherein the one or more electronic devices include an on-board computer for the vehicle and a computer device external to the vehicle.
8. The computer-implemented method of claim 1 , further comprising: classifying each of the one or more images into classes representing non-distracted behavior or distracted behavior, wherein the first and second non-binary values representing the first and second risks of loss are determined based, at least in part, on the classes for the one or more images.
9. The computer-implemented method of claim 1 , wherein the first and second detected hand or head positions represent detections that two hands are on the steering wheel.
10. The computer-implemented method of claim 1 , wherein the first detected hand or head position indicates how both a head and one or more hands of the driver are positioned; and wherein the second detected hand or head position indicates how both the head and the one or more hands of the driver are positioned.
11. A system for assessing risk based on driver behavior, the system comprising:
a communication interface operable to be communicatively coupled to an image sensor;
one or more processors coupled to the communication interface;
one or more memories coupled to the one or more processors, the one or more memories storing computer readable instructions that, when executed, cause the one or more processors to:
receive, from the image sensor, one or more images of a driver of the vehicle captured via the image sensor;
analyze the one or more images to:
(i) detect via the one or more electronic devices (a) a first detected hand or head position of the driver at a first time, and (b) a second non-binary value representing a second detected hand or head position of the driver; and
(ii) determine via the one or more electronic devices: (a) a first non-binary value representing a first risk of loss based on the first detected hand or head position and (b) a second non-binary value representing a second risk of loss based on the second detected hand or head position;
calculate a driving score based, at least in part, on the first and second determined non-binary values representing the first and second risks of loss; and
display the driving score.
12. The system of claim 11 , wherein the instructions further cause the one or more processors to activate the image sensor in response to a detection, by an on-board computer of the vehicle, of a mobile device at the vehicle.
13. The system of claim 12 , wherein the on-board computer detects the mobile device at the vehicle by detecting the mobile device via a short range wireless communication.
14. The system of claim 11 , wherein the instructions further cause the one or more processors to time-stamp the one or more images to indicate a date and time of capture.
15. The system of claim 11 , wherein the instructions further cause the one or more processors to activate the image sensor in response to a detection, by an on-board computer of the vehicle, of the system at the vehicle.
16. The system of claim 11 , wherein the one or more processors are disposed at the vehicle.
17. The system of claim 11 , wherein the one or more processors are disposed at a computer device external to the vehicle.
18. The system of claim 11 , wherein the instructions further cause the one or more processors to: classify each of the one or more images into classes representing non-distracted behavior or distracted behavior, wherein the first and second non-binary values representing the first and second risks of loss are determined based, at least in part, on the classes for the one or more images.
19. The system of claim 11 , wherein the first and second detected hand or head positions relative to the steering wheel represent detections that two hands are not on the steering wheel.
20. The system of claim 11 , wherein the first detected hand or head position indicates how both a head and one or more hands of the driver are positioned; and wherein the second detected hand or head position indicates how both the head and the one or more hands of the driver are positioned.