Due to Coronavirus issues, this meeting on March 17 has been cancelled. When appropriate, it will be rescheduled for a later date.

Speaker: Mohamed Marzban, Electrical and Computer Engineering Department, UT Dallas
Topic: “Deep learning for Precise Gaze Estimation in Naturalistic Driving Environments”

Abstract: Precise gaze estimation in naturalistic driving environments is considered a major research challenge. Our goal is to exploit data from different in-vehicle sensors to monitor and assess the visual attention of the driver and produce probabilistic estimations for the driver’s gaze angles. The proposed gaze estimation algorithms can help in evaluating and analyzing driver distractions, and producing valuable information to alarm the driver at the event of distraction. In addition, they can play a key role in deciding whether to hand control to a human operator in level 3 and 4 autonomous vehicles. We start by utilizing AprilTags to estimate the precise location of the driver’s gaze during driving. We then collect new continuous gaze dataset during parking that spans all possible in-vehicle azimuth and elevation gaze angles and augment it to driving gaze dataset. We detect the face and the eyes of the drivers to observe subtle gaze features and feed them to our developed deep learning architecture that outputs probabilistic estimation for the gaze angles. We produce high-accuracy and high-precision probabilistic elevation and azimuth angles estimations which demonstrates the robustness of our gaze estimation model.

BIO: Mohamed Marzban received the B.Sc. and M.Sc. degrees in electrical engineering from Cairo University, Egypt, in 2013 and 2016, respectively. He is currently pursuing the Ph.D. degree in the electrical and computer engineering department with the University of Texas at Dallas, Richardson, TX, USA. From 2013 to 2014, he was a systems research and development engineer with Intel labs. From 2015 to 2016, he was a Software Engineer with Avidbeam Inc. In 2018, he joined Qualcomm Technologies., Santa Clara, CA, USA, as a connected vehicles Intern. He is the recipient of Betty and Gifford Johnson Graduate Studies Award,  the Louis Beecherl Graduate award, Jan Van der Zeil Graduate award at the University of Texas at Dallas in 2017, 2018 and 2019, respectively. His research interests include advanced driver assistance systems, machine/deep learning applications, computer vision and wireless communications.

Date: March 17, 2020, Registration/Lunch: 11:30am; Presentation: 12-1pm
Cost: IEEE Members: $10; IEEE Student and Life Members: $5; Others: $15
Location: UT Dallas SPN.1 Building, 3000 Waterview, Richardson, TX 75080
Please Register/RSVP: here, then Please Pay at Door
UT Dallas Requires Parking Pass; Will be provided in final event emails.
Please Email us any dietary restriction on registration.

CVT Contact: jimgunn@ieee.org