Computer Science Guest Speaker Series - Computer Vision and Machine Learning for the Real World

Event Date: 
Friday, November 4, 2022 - 11:30am to 1:00pm EDT
Event Location: 
online
Event Contact Name: 
Rachael Wang
Event Contact E-mail: 

THE DEPARTMENT OF COMPUTER SCIENCE GRADUATE SEMINAR 2022
Guest Speaker Series Presented By:

Dr. Nikos Papanikolopoulos
"Computer Vision and Machine Learning for the Real World"

Friday, November 4th, 2022
11:30 am

Abstract:
Recent advances in computational hardware, computer vision, and machine learning have created some unique opportunities for real-world data-centric systems. The talk will focus on some projects that use innovative imaging along with active learning and reinforcement learning to perform tasks in mental health assessment, intelligent transportation systems, human-robot interfaces, sports training, and precision agriculture. For example, we will describe a framework that performs the precise detection and characterization of plant deficiencies. This step is often followed by the proper deployment of fertilizers. In particular, the proposed methodology utilizes drone collected images to detect nitrogen (N) deficiencies in maize fields and assess their severity using low-cost RGB sensors. Our proposed methodology is twofold. A low complexity recommendation scheme identifies candidate plants exhibiting (N) deficiency and, with minimal interaction, assists the annotator in the creation of a training dataset which is then used to train an object detection deep neural network. Results on data from experimental fields support the merits of the proposed methodology with the mean average precision for the detection of N-deficient leaves reaching 82.3%.

This is joint work with a large number of colleagues including T. Morris, V. Morellas, L. Guzman, P. Stanitsas, H. Nelson, C. Conelea, K. Cullen, D. Zermas, C. Smith, and T. Bacharis.

Prof. Nikos Papanikolopoulos (IEEE Fellow) received his Diploma of Engineering in Electrical and Computer Engineering, from the National Technical University of Athens in 1987. He received his M.S. in 1988 and Ph.D. in 1992 in Electrical and Computer Engineering from Carnegie Mellon University. His research interests include computer vision, robotics, sensors for transportation and precision agriculture applications, and control systems. He is the Director of the Minnesota Robotics Institute and the McKnight Presidential Endowed Professor of CS at the University of Minnesota. He has received numerous awards including the 2022 UMN Award for Outstanding Contributions to Graduate and Professional Education and the 2016 IEEE RAS George Saridis Leadership Award in Robotics and Automation.

To register for this virtual event, please email grad.compsci@lakeheadu.ca and a Zoom link will be shared.

Everyone is welcome.