Keynote Presentation

Our Keynote Speaker will give their presentation during dinner. 

This year, we are proud to have Dr. Robert Fiete, Chief Technologist and Sr. Fellow at L3Harris, as the Keynote Speaker.

Biography:

Dr. Bob Fiete is Chief Technologist and Senior Fellow at L3Harris with over 40 years of experience in imaging science.

He managed the Imaging Systems Analysis group in Kodak’s Government Systems organization where he developed the image chain modeling approach to create digital twins for designing and assessing imaging systems. Bob was Director of R&D for ITT (later Exelis) Space Systems Division, an adjunct professor at the Center for Imaging Science at RIT, chaired conferences and seminars on imaging and optics, briefed the National Security staff at the White House Situation Room, generated satellite image simulations for President Obama, briefed the House and Senate Intelligence Committees in Congressional hearings, and worked with the FBI and DOJ on many criminal cases involving image exploitation.

He has authored three books, five book chapters, and over forty technical papers. Bob was the inaugural editor of the SPIE Spotlights book series and has received twelve patents, including one for a method used to focus many of the current imaging satellites and another for an image enhancement method first used on the Harry Potter movies. He received his BS degree in Physics and Math from Iowa State University and his MS and PhD in Optical Sciences from the University of Arizona.

Bob was awarded the Rudolf Kingslake Medal by SPIE, is a Senior Member of OSA and SPIE, and is a Fellow of SPIE.

Address:Rochester, New York, United States

JCM Speakers

ABSTRACTS

Robustness and Reliability of Machine Learning and Its Importance in Imaging
Machine learning algorithms, particularly deep neural networks, have gained significant prominence due to their success, especially in the fields of imaging science and computer vision. However, the question of how reliable these models are in various applications remains a critical challenge. The robustness and reliability of machine learning algorithms refer to a model's ability to maintain performance across diverse and challenging conditions, including noisy data, adversarial attacks, and domain shifts. Imaging data is inherently complex, with variations in lighting, scale, viewpoint, and heterogeneity. Robust models are essential to delivering consistent and accurate results, particularly in fields like medical imaging, autonomous vehicles, and surveillance systems. This presentation explores the concept of robustness and reliability of machine learning, focusing on its pivotal role within the realm of imaging science. We will shed light on the paramount importance of uncertainty quantification in bolstering the robustness of machine learning models. Uncertainty quantification is the process of estimating the confidence or uncertainty associated with model predictions. We will present state-of-the-art models for quantifying uncertainty and empowering the robustness of modern machine learning models towards real-world deployment in various applications.

Stopping Industrial Static Ignitions
Electrostatic discharges can ignite liquids commonly used in industrial production operations. After a brief review of the conditions for ignition, three cases studies illustrate different root causes of ignitions; triboelectric charging, flow electrification, splash filling, and static charges stored on a human body. After viewing a video of a static ignition, the root cause of the ignition is discussed, and the charging mechanism identified. Understanding the charging mechanism enables us to choose an effective mitigation to prevent future ignitions.

Radar Signal Processing Education, Research, and Capabilities at Rochester Institute of Technology
This presentation will highlight the expanding radar remote sensing capabilities of the Digital Imaging and Remote Sensing Laboratory at Rochester Institute of Technology. This includes the recent purchase of a drone-based Ku-Band synthetic aperture radar, modeling and simulation capabilities to support ongoing radar signal processing research, and an overview of several funded research projects.

Agrivoltaics: Combining Photovoltaics with Agriculture
Photovoltaics (PV) implementation on farmland in harmony with agriculture and nature conservation, needs to be at the core of Agri-PV development and that is where scientists, engineers and farmers need to learn from each other.   Certain skills and knowledge are needed to further accelerate the deployment of Agri-PV. The talk will present the design of PV systems that involve panel configurations such as monofacial fixed-tilt modules suspended above agriculture, monofacial single-axis modules fitted with trackers which alter their angle throughout the day, and vertical bifacial modules set in fence-like rows.  The configurations are based on the type of crops grown for optimal land use with increase in land productivity.  Future trends on transparent PV and planning & monitoring system performance will also be introduced

Address:RIT, , Rochester, New York, United States, 14623