System and method for detecting abnormal passenger behavior in autonomous vehicles

US11132585B2 · kind B2 · utility

Assignee

• Robert Bosch GmbH · DE

Inventors

• Yumi Kondo · Osaka, JP
• Ryan Burt · San Jose, US
• Krishnan Bharath Navalpakkam · San Jose, US
• Alexander Hirsch · Rolling Meadows, US
• Naveen Ramakrishnan · Wexford, US
• Filipe Goncalves · Braga, PT
• Stefan Weissert · Royal Oak, US
• Jayanta Kumar Dutta · Sunnyvale, US
• Ravi Kumar Satzoda · Palo Alto, US

Key dates

• Filing date: Dec 17, 2019
• Grant date: Sep 28, 2021
• Expiry date: Apr 12, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V40/20
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method and system are disclosed for monitoring passengers in within a cabin of a vehicle and determining whether the passengers are engaging in abnormal behavior. The method and system uses a novel vector to robustly and numerically represent the activity of the passengers in a respective frame, which is referred to herein as an “activity vector.” Additionally, a Gaussian Mixture Model is utilized by the method and system to distinguish between normal and abnormal passenger behavior. Cluster components of the Gaussian Mixture Model are advantageously learned using an unsupervised approach in which training data is not labeled or annotated to indicate normal and abnormal passenger behavior. In this way, the Gaussian Mixture Model can be trained at a very low cost.