Detection of unsafe cabin conditions in autonomous vehicles
AssigneeReveal Innovations, LLC
InventorsRocky Chau-Hsiung Lin, Thomas Yamasaki, Koichiro Kanda
Life of this patent
Estimating the term…
Abstract
Devices, systems and processes for the detection of unsafe cabin conditions that provides a safer passenger experience in autonomous vehicles are described. One example method for enhancing passenger safety includes capturing at least a set of images of one or more passengers in the vehicle, determining, based on the set of images, the occurrence of an unsafe activity in an interior of the vehicle, performing, using a neural network, a classification of the unsafe activity, and performing, based on the classification, one or more responsive actions.
Claims14
A system for enhancing passenger safety in a vehicle, comprising:
- a processor;
- and
- an internal sensor system, coupled to the processor, configured to capture at least a set of images of one or more passengers in the vehicle,
- wherein the processor is configured to:
- determine, based on the set of images, an occurrence of an unsafe activity,
- perform, using a neural network, a classification of the unsafe activity, and
- perform, based on the classification, one or more responsive actions,
- wherein the unsafe activity comprises an object being thrown out of a window or a door of the vehicle, and
- wherein the neural network is trained based on a plurality of images of one or more second passengers inside a second vehicle, each of the plurality of images being labeled with a safe label or an unsafe label.
A method for enhancing passenger safety in a vehicle, comprising:
- capturing at least a set of images of one or more passengers in the vehicle;
- determining, based on the set of images, an occurrence of an unsafe activity in a cabin of the vehicle, wherein the unsafe activity comprises an object being thrown out of a window or a door of the vehicle;
- performing, using a neural network, a classification of the unsafe activity, wherein the unsafe activity is one of a predetermined number of unsafe activities, and wherein the neural network is trained based on a first plurality of images of one or more second passengers inside a second vehicle, each of the first plurality of images being labeled with a safe label or an unsafe label;
- and
- performing, based on the classification, one or more responsive actions.
Dependencies are inferred from the claim text.