SENSOR-BASED IN-VEHICLE DYNAMIC DRIVER GAZE TRACKING
Systems and methods are disclosed for sensor-based in-vehicle dynamic driver gaze tracking. In one implementation, one or more first inputs can be received. The first input(s) can be processed to compute one or more directional adjustments. Second input(s) originating from an image sensor positioned within a vehicle can be received. The second input(s) can be processed to determine a gaze direction of at least one eye of a driver of the vehicle. Based on the determined gaze direction of the at least one eye of the driver and the computed first directional adjustment, aspect(s) of distractedness of the driver can be determined. Operation(s) can be initiated based on the determined aspect(s) of distractedness.
1 . A system comprising:
a processing device; and
a memory coupled to the processing device and storing instructions that, when executed by the processing device, cause the system to perform operations comprising:
receiving one or more first inputs;
processing the one or more first inputs to compute one or more directional adjustments;
receiving one or more second inputs originating from an image sensor positioned within a vehicle;
processing the one or more second inputs to determine a gaze direction of at least one eye of a driver of the vehicle;
based on (a) the determined gaze direction of the at least one eye of the driver and (b) the computed directional adjustment, determining one or more aspects of distractedness of the driver; and
initiating one or more operations based on the determined one or more aspects of distractedness.
2 . The system of claim 1 , wherein the one or more first inputs comprise information corresponding to one or more dimensions of the vehicle.
3 . The system of claim 1 , wherein the one or more first inputs comprise information corresponding to one or more parameters associated with one or more components of the vehicle.
4 . The system of claim 1 , wherein the one or more first inputs comprise information corresponding to one or more events associated with the vehicle.
5 . The system of claim 1 , wherein the one or more second inputs comprise a sequence of gaze instances.
6 . The system of claim 1 , wherein initiating one or more operations comprises filtering one or more events.
7 . The system of claim 1 , wherein determining one or more aspects of distractedness of the driver comprises determining one or more aspects of distractedness of the driver via a neural network.
8 . The system of claim 1 , wherein the one or more directional adjustments comprise a region corresponding to an area of an image that relates to a road on which the vehicle is traveling.
9 . A method comprising:
receiving one or more first inputs;
processing the one or more first inputs to compute one or more directional adjustments;
receiving one or more second inputs originating from an image sensor positioned within a vehicle;
processing the one or more second inputs to determine a gaze direction of at least one eye of a driver of the vehicle;
based on (a) the determined gaze direction of the at least one eye of the driver and (b) the computed directional adjustment, determining one or more aspects of distractedness of the driver; and
initiating one or more operations based on the determined one or more aspects of distractedness.
10 . The method of claim 9 , wherein the one or more first inputs comprise information corresponding to one or more dimensions of the vehicle.
11 . The method of claim 9 , wherein the one or more first inputs comprise information corresponding to one or more parameters associated with one or more components of the vehicle.
12 . The method of claim 9 , wherein the one or more first inputs comprise information corresponding to one or more events associated with the vehicle.
13 . The method of claim 9 , wherein the one or more second inputs comprise a sequence of gaze instances.
14 . The method of claim 9 , wherein initiating one or more operations comprises filtering one or more events.
15 . The method of claim 9 , wherein determining one or more aspects of distractedness of the driver comprises determining one or more aspects of distractedness of the driver via a neural network.
16 . The method of claim 9 , wherein the one or more directional adjustments comprise a region corresponding to an area of an image that relates to a road on which the vehicle is traveling.
17 . A non-transitory computer readable medium having instructions stored thereon that, when executed by a processing device, cause the processing device to perform operations comprising:
receiving one or more first inputs;
processing the one or more first inputs to compute one or more directional adjustments, the one or more directional adjustments comprise a region corresponding to an area of an image that relates to a road on which a vehicle is traveling;
receiving one or more second inputs originating from an image sensor positioned within the vehicle;
processing the one or more second inputs to determine a gaze direction of at least one eye of a driver of the vehicle;
based on (a) the determined gaze direction of the at least one eye of the driver and (b) the computed directional adjustment, determining, via a neural network, one or more aspects of distractedness of the driver; and
initiating one or more operations based on the determined one or more aspects of distractedness.
18 . The non-transitory computer readable medium of claim 17 , wherein the one or more first inputs comprise information corresponding to one or more dimensions of the vehicle.
19 . The non-transitory computer readable medium of claim 17 , wherein the one or more first inputs comprise information corresponding to one or more parameters associated with one or more components of the vehicle.
20 . The non-transitory computer readable medium of claim 17 , wherein the one or more first inputs comprise information corresponding to one or more events associated with the vehicle.