Back to results
US 11,144,754 B2Granted
Gaze detection using one or more neural networks
AssigneeNVIDIA Corporation
InventorsFeng Hu, Niranjan Avadhanam, Yuzhuo Ren, Sujay Yadawadkar, Sakthivel Sivaraman, Hairong Jiang, Siyue Wu
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques are described to determine locations of objects using images including digital representations of those objects. In at least one embodiment, a gaze of one or more occupants of a vehicle is determined independently of a location of one or more sensors used to detect those occupants.
Claims20
A processor, comprising:
- one or more circuits to help determine a gaze of an occupant of a vehicle independently of an angle from which the occupant is detected by one or more sensors in the vehicle,
- wherein the gaze is determined based, at least in part, on one or more neural networks, and
- wherein the one or more neural networks are trained using position data known for a vehicle coordinate system and mapped to at least one virtual coordinate system corresponding to the one or more sensors.
A vehicle comprising:
- one or more sensors;
- and
- one or more processors to help determine a gaze of an occupant of the vehicle independently of an angle from which the occupant is detected by the one or more sensors,
- wherein the gaze is determined based, at least in part, on one or more neural networks, and
- wherein the one or more neural networks are trained using position data known for a vehicle coordinate system and mapped to at least one virtual coordinate system corresponding to the one or more sensors.
2 more elements
A method comprising:
- detecting one or more occupants of a vehicle by one or more sensors;
- and
- determining a gaze of the one or more occupants independently of a location of the one or more sensors,
- wherein the gaze is determined based, at least in part, on one or more neural networks, and
- wherein the one or more neural networks are trained using position data known for a vehicle coordinate system and mapped to at least one virtual coordinate system corresponding to the one or more sensors.
2 more elements
A processor comprising:
- one or more circuits to help train one or more neural networks to determine a gaze of one or more people independently of an angle from which the gaze is detected,
- wherein the one or more neural networks are trained using position data known for a reference coordinate system and mapped to at least one virtual coordinate system corresponding to one or more sensors used to detect the one or more people.
A system comprising:
- one or more processors to help train one or more neural networks to determine a gaze of one or more people independently of an angle from which the gaze is detected,
- wherein the one or more neural networks are trained using position data known for a reference coordinate system and mapped to at least one virtual coordinate system corresponding to one or more sensors used to detect the one or more people.
Dependencies are inferred from the claim text.