Ford Global Technolgoies, LLC

Ford Motor Company Limited

Michigan State University

Mike Blommer

Kwaku O Prakah-Asante

Gary Steven Strumolo

Jian Wan

Radhakrishnan Swaminathan

Xiaoming Liu

Xi Yin

Reates Curry

Ziyuan Zhang

Yousef Atoum

Luan Tran

Gait, the walking pattern of individuals, is one of the most important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as the gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and view angle. To remedy this issue, a novel AutoEncoder framework is presented to explicitly disentangle pose and appearance features from RGB imagery and a long short-term memory integration of pose features over time produces the gait feature.

Systems and methods for gait recognition via disentangled representation learning

Methods and apparatus to monitor an activity level of a driver are disclosed. An example method includes receiving, at a processor, eye movement data from a sensor monitoring eye movements of a driver of a vehicle. The method includes calculating, via the processor, an eye movement activity index using a substantially real-time recursive analysis of the eye movement data. The method further includes calculating, via the processor, a low activity indicator for the driver based on the eye movement activity index. The method also includes executing a task based on the low activity indicator.

Methods and apparatus to monitor an activity level of a driver

Growing community of inventors

Ann Arbor, MI, United States of America

Mike Blommer