AI-based recognition & corresponding fallback system under irregular situations for AVs

► Object & Event Detection, Recognition, & Identification

Pedestrians, ATC, Traffic Signals, Obstacles, Passengers with Intent & Activity, etc.

► Privacy-preservation

Personal privacy preservation of individuals.

► Identification

Identification of person under IS.

► Human & Non-human Identification

Identification of real person to avoid IS.

► Adverse Weather Conditions

Object and event monitoring in adverse weather.

In-cabin Monitoring System (IMS) for Future Mobility

• Occupancy, No. of occupants, age group, gender, etc.;

• Occupant body part outside the vehicle, seat belt;

• Child age, car seat, an unattended child, etc.;

• Eating, smoking, drinking, spilling objects and belongings;

• Pets/Animals;

• Vandalism, teasing, abuse, argument, etc.;

• Dangerous objects, weapons, etc.;

• Personal privacy;

• Stealing, theft, etc.;

• Illegal activities;

• Misuse, mishandling, or malicious activities toward the vehicle.

• Irregular situations.

Privacy-preserved In-Cabin Monitoring System

There is a contrary demand for privacy in the IMS of AVs. Therefore, an intelligent IMS must simultaneously satisfy the requirements of personal privacy protection and person identification during abnormal situations. In this study, we proposed a privacy-preserved IMS which can reidentify anonymized virtual individual faces in an abnormal situation.