Machine-learned model training for pedestrian attribute and gesture detection

This invention describes a vehicle that can understand what people around it are doing. It uses its sensors, like cameras, to gather information about pedestrians. A special computer program, called a machine-learned model, analyzes this information to figure out if a person is making a specific gesture or has a certain characteristic. Based on what the model detects, the vehicle then takes an appropriate action, such as slowing down or stopping.

Why it matters: Since 2023, the rapid evolution of machine learning models, particularly in real-time computer vision, has significantly improved the accuracy and efficiency of pedestrian gesture and attribute detection. This progress makes training and deploying such safety-critical systems in vehicles more feasible and effective.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedMachine learning, sensor integration, vehicle control software

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10