ECE Seminar Series – Jan 10 (Fri) @ 2:00pm: "From Perception to Planning Through Robust Scene Understanding," Amit K. Roy-Chowdhury, Professor & UC Presidential Chair, ECE, UC Riverside

Location: Engineering Science Bldg (ESB), Room 1001
Come at 1:30p for Cookies, Coffee and Conversation!
DISTINGUISHED LECTURE at the ECE SEMINAR SERIES

Abstract

Recent advances in computer vision for scene understanding have raised hopes for solving complex planning and navigation problems with increased guarantees on safety and robustness. However, integrated perception and planning still remains a challenging task, largely due to the uncertainties associated with scene understanding. In this talk, we will consider a variety of scene understanding problems that need to be solved for integrated perception and planning to be successful. Scene understanding requires analysis of objects and their collections across various scales, from individual people and their actions to wide-area analysis that could span the interactions of these people with many other objects in the scene. At the level of individual people, we will show how to estimate the pose of each individual person under challenging real-life conditions like significant occlusions, leveraging upon the power of generative models. At the next higher scale when there are interactions among groups of individuals and objects, we will demonstrate the power of scene graphs to model the semantics of the scene. Robustness to a variety of operational domains will be considered through suitable uncertainty quantification metrics. In spite of this, it is likely that an autonomous agent will need to occasionally interact with human experts; we show how this can be achieved with natural language feedback leveraging upon the power of recently developed vision-language models.

Bio

Amit Roy-Chowdhury received his PhD from the University of Maryland, College Park (UMCP) in 2002 and joined the University of California, Riverside (UCR) in 2004 where he is a Professor and UC Presidential Chair of Electrical and Computer Engineering, Cooperating Faculty in Computer Science and Engineering, and Co-Director of the UC Riverside AI Research and Education Institute. He leads the Video Computing Group at UCR, working on foundational principles of computer vision, image processing, and machine learning, with applications in cyber-physical, autonomous and intelligent systems. He has published over 250 papers in peer-reviewed journals and conferences. He is on the editorial boards of major journals in computer vision and image processing, and on program/organizing committees of the main conferences in his area. He is a Fellow of the IEEE and IAPR, received the Doctoral Dissertation Advising/Mentoring Award from UCR, and the ECE Distinguished Alumni Award from UMCP.

Hosted By: Distinguished Lecture at the ECE Seminar Series

Submitted By: Professor B.S. Manjunath