9th IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS)
Call for Paper
Keynote Speakers
Best Paper
 Latest News

:: Prof. Ko Nishino will give an invited talk!

:: The workshop program is announced!

:: Prof. Robert T. Collins will give an invited talk!

:: Submission deadline is extended!

:: PBVS '13 website is open!


Email Guoliang Fan

Keynote Speakers

Invited Talk 1: Multi-frame Data Association with Higher-Order Cost Functions


Robert T. Collins
Associate Professor of Computer Science & Engineering Department
The Pennsylvania State University

Abstract: Within the paradigm of detect-then-track, an object detector is run on each video frame to hypothesize objects of interest, followed by a data association stage to link detections into multi-frame trajectories. This second stage of multi-frame data association is of particular interest, as it is a combinatorial optimization problem of significant complexity. We argue that recent vision-based approaches rely too heavily on object appearance cues to solve this problem, to the point of ignoring motion characteristics. One example is the recent network flow formulation where the number and best set of trajectories can be solved optimally using min-cost flow in polynomial time. Although an exciting result, the approach relies on being able to factor trajectory cost functions into the product/sum of pairwise costs on each frame-to-frame link. This limits evaluation of geometric track quality to terms based only on distance traveled between frames, e.g. shortest paths, and does not allow for higher-order smoothness constraints that are functions over three or more frames, such as piecewise constant velocity. The lack of regularizing motion models has a detrimental effect on quality of the trajectories found when appearance information is weak (e.g. thermal) or nonexistent (e.g. radar blips), and/or when the detection frame-rate is low. This talk will present recent work that combines elements from network flow into the more traditional, but NP-hard, multidimensional assignment formulation, resulting in efficient algorithms capable of finding high quality approximate solutions to the multi-frame data association problem under higher-order cost functions.

Bio: Robert T. Collins received the Ph.D. degree in Computer Science from the University of Massachusetts at Amherst in 1993. He is an associate professor in the Computer Science and Engineering Department at The Pennsylvania State University, where he co-directs the Lab for Perception, Action and Cognition (LPAC). Prior to joining Penn State in 2005, he was a member of the research faculty in the Robotics Institute at Carnegie Mellon University, where he worked for over a decade on DARPA projects such as VSAM, HID and VIVID, and helped to develop the CBS EyeVision System, for which he hold three joint patents with co-inventors at CMU. His current research interests include video scene understanding, automated surveillance, human activity modeling, and multi-target tracking. He is a senior member of the IEEE, a member of the IEEE Computer Society, a member of the Computer Vision Foundation, and an associate editor for the International Journal of Computer Vision.

Invited Talk 2: Visual Material Recognition


Ko Nishino
Associate Professor
Department of Computer Science, Drexel University

Abstract: Information regarding what an object is made of--its material--can provide crucial clues for image understanding.If a robot, for instance, detects soft dirt or a smooth metal surface ahead, it can adjust its movement in advance. Recognizing materials solely from images, however, has proven to be a difficult problem. In this talk, I will present our research geared towards visual material recognition. I will first discuss about a generative approach, in which we aim to decompose the image into its building blocks--geometry, illumination, and reflectance--so that we can later use the reflectance estimate to deduce the material. I will show how the space of real-world reflectance can be faithfully encoded with a novel reflectance model and be exploited to estimate reflectance in complex real-world environments. I will then discuss a discriminative approach in which we directly try to classify each pixel of an image into different materials. For this, we introduce a novel intermediate representation, called visual material traits, that represent the appearance of material properties like "smooth" and "shiny," and use them to recognize materials locally without any knowledge of the object. Finally, I will show some preliminary results on using material as visual context for image understanding.

Bio: Ko Nishino is an associate professor in the Department of Computer Science at Drexel University. He received a B.E. and an M.E. in Information and Communication Engineering in 1997 and 1999, respectively, and a PhD in Computer Science in 2002, all from The University of Tokyo. Before joining Drexel University in 2005, he was a Postdoctoral Research Scientist in the Computer Science Department at Columbia University. His primary research interests lie in computer vision and include appearance modeling and synthesis, geometry processing, and video analysis. His work on exploiting eye reflections received considerable media attention including articles in New York Times, Newsweek, and NewScientist. He received the NSF CAREER award in 2008.

Copyright © OTCBVS, Contact the Webmaster.