Non-invasive Techniques for Human Fatigue Monitoring

25
Non-invasive Techniques for Human Fatigue Monitoring Qiang Ji Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute [email protected] http://www.ecse.rpi.edu/homepages/qji

description

Non-invasive Techniques for Human Fatigue Monitoring. Qiang Ji Dept. of Electrical, Computer, and Systems Engineering Rensselaer Polytechnic Institute [email protected] http://www.ecse.rpi.edu/homepages/qji. Visual Behaviors. Visual behaviors that typically reflect a - PowerPoint PPT Presentation

Transcript of Non-invasive Techniques for Human Fatigue Monitoring

Page 1: Non-invasive Techniques for Human Fatigue Monitoring

Non-invasive Techniques for Human Fatigue

MonitoringQiang Ji

Dept. of Electrical, Computer, and Systems Engineering

Rensselaer Polytechnic [email protected]

http://www.ecse.rpi.edu/homepages/qji

Page 2: Non-invasive Techniques for Human Fatigue Monitoring
Page 3: Non-invasive Techniques for Human Fatigue Monitoring

Visual BehaviorsVisual behaviors that typically reflect

a person's level of fatigue include

– Eyelid movement – Head movement – Gaze – Facial expressions

Page 4: Non-invasive Techniques for Human Fatigue Monitoring

Eyelid Movements Tracking Eyes

Develop techniques that can robustly track eyes under different face orientations, illuminations, and large head movements.

Compute Eye movement parameters PERCLOS Average Eye Closure/Open Speed

(AECS)

Page 5: Non-invasive Techniques for Human Fatigue Monitoring

Eyes tracking demo

Page 6: Non-invasive Techniques for Human Fatigue Monitoring

PERCLOS measurement over time

Page 7: Non-invasive Techniques for Human Fatigue Monitoring

Average Eye Closure Speed Over time

Page 8: Non-invasive Techniques for Human Fatigue Monitoring
Page 9: Non-invasive Techniques for Human Fatigue Monitoring
Page 10: Non-invasive Techniques for Human Fatigue Monitoring

Gaze (Pupil Movements)

Real time gaze tracking No calibration is needed and

allows natural head movements !.

Gaze parameters Spatial gaze distribution overtime Ratio of fixation time to saccade time.

Page 11: Non-invasive Techniques for Human Fatigue Monitoring

Gaze distribution over time while alert

Page 12: Non-invasive Techniques for Human Fatigue Monitoring

Gaze distribution over time under fatigue

Page 13: Non-invasive Techniques for Human Fatigue Monitoring
Page 14: Non-invasive Techniques for Human Fatigue Monitoring

Head Movement Real time head pose tracking

Perform 3D face pose estimation from a single uncalibrated camera.

Head movement parameters Head tilt frequency over time Percentage of side views (PerSideV)

Page 15: Non-invasive Techniques for Human Fatigue Monitoring
Page 16: Non-invasive Techniques for Human Fatigue Monitoring
Page 17: Non-invasive Techniques for Human Fatigue Monitoring

Facial Expressions Tracking facial features

Recognize certain facial expressions related to fatigue like yawning.

Building a database of fatigue expressions.

Page 18: Non-invasive Techniques for Human Fatigue Monitoring

Facial expression demo

Page 19: Non-invasive Techniques for Human Fatigue Monitoring

Fatigue Modeling• Knowledge of fatigue is uncertain and

from different levels of abstraction.

• Fatigue represents the affective state of an individual, is not observable, and can only be inferred.

Page 20: Non-invasive Techniques for Human Fatigue Monitoring

Overview of Our Approach

Propose a probabilistic framework based on Bayesian Networks (BN) to

model fatigue.systematically integrate various

sources of information related to fatigue.

infer and predict fatigue from the available observations and the relevant contextual information.

Page 21: Non-invasive Techniques for Human Fatigue Monitoring

Bayesian Networks Construction

• A BN model consists of target hypothesis variables (hidden nodes) and information variables (information nodes).

• Fatigue is the target hypothesis variable that we intend to infer.

• Other contextual factors and visual cues are the information nodes.

Page 22: Non-invasive Techniques for Human Fatigue Monitoring

Causes for Fatigue

Major factors to cause fatigue include: Sleep quality. Circadian rhythm (time of day). Physical conditions. Working environment.

Page 23: Non-invasive Techniques for Human Fatigue Monitoring

Bayesian Network Model for Monitoring Human Fatigue

Page 24: Non-invasive Techniques for Human Fatigue Monitoring

Interface with Vision Interface with Vision ModuleModule

An interface has been developed to connect the output of the computer vision system with the information fusion engine.

The interface instantiates the evidences of the fatigue network, which then performs fatigue inference and displays the fatigue index in real time.

Page 25: Non-invasive Techniques for Human Fatigue Monitoring

Conclusions

• Developed non-intrusive real-time computer vision techniques to extract multiple fatigue parameters related to eyelid movements, gaze, head movement, and facial expressions.

• Develop a probabilistic framework based on Bayesian networks to model and integrate contextual and visual cues information for fatigue monitoring.