Home > Seminars > Amy Reibman - Video Quality in an Age of Universal Cameras

Amy Reibman - Video Quality in an Age of Universal Cameras


11/1/2018 at 3:30PM


11/1/2018 at 4:45PM


138 DeBartolo


College of Engineering close button

Patrick Flynn

Patrick Flynn

VIEW FULL PROFILE Email: flynn@nd.edu
Phone: 574-631-8803
Website: http://www.nd.edu/~flynn
Office: 384A Fitzpatrick Hall
Curriculum Vitae


College of Engineering Duda Family Professor of Engineering
Computer Vision Biometrics Pattern Recognition Computer Graphics and Scientific Visualization Mobile Application Development
Click for more information about Patrick
Add to calendar:
iCal vCal

Digital cameras are everywhere, constantly recording our environment. Cameras 
are distributed in hallways, classrooms, and on roadways. Wearable (body-mounted) cameras and vehicle-mounted “dash-cams” all record video without active intentional guidance by a human. Wherever the person goes or looks, video is captured. Unfortunately, the images captured from these cameras are not always high quality, even if they have a high spatio-temporal resolution. This reduces their effectiveness when they are subsequently watched by viewers or used by automated analytics algorithms to extract information.

In this talk, I’ll present two topics motivated by these new scenarios. On the first topic, I’ll consider perceptual quality of video recorded from First-Person (FP) (wearable) cameras, including a “mutual reference” quality estimation of images extracted from the video, and measurements of both the stability and First-Person Motion Information from the FP videos. 

I’ll also demonstrate a stabilization algorithm that balances both stability and first-person motion. On the second topic, I’ll present a quality assessment tool for predicting the accuracy of a several commonly-used pedestrian detectors 
in a practical system that includes video compression.

If time permits, I’ll discuss some ongoing research in video analytics for
real-world applications, where quality degradation is pervasive and labels
are difficult to obtain.

Seminar Speaker:

Amy Reibman

Amy Reibman

Purdue University

Amy R. Reibman is a Professor of Electrical and Computer Engineering 
at Purdue University. She pursued 23 years of industrial research at AT&T Labs -- Research, where she was a Distinguished Member of Technical Staff and a Lead Inventive Scientist. Her research interests are in video analytics, video stabilization, and image and video quality assessment. She has also done pioneering work on video transmission over packet networks. She has published over 35 journal papers, 100 conference papers, and holds more than 40 US patents.

Dr. Reibman was elected IEEE Fellow in 2005, for her contributions to 
video transport over networks. She was chair of the IEEE Fellow Committee 
in 2016-2017, a Judge on the IEEE Fellow Committee from 2012-2015,
and a member of the IEEE Fellow Strategic Planning Committee from 2013-2018.
In 1998, she won the IEEE Communications Society Leonard G.  Abraham Prize 
Paper Award.  She was the Technical co-chair of the IEEE International 
Conference on Image Processing in 2002, and she is currently Technical co-chair
of the IEEE Global Conference on Signal and Information Processing in 2018. 
She was a Distinguished Lecturer for the IEEE Signal Processing Society 
from 2008-2009, was a member of the IEEE Awards Committee from 2010-2012.