All 60-520 students must attend. Everyone else interested in the seminar is also cordially invited.
Video processing is no longer a prerogative of a few. With video-cameras now affordable, computers powerful enough to process video in real-time, and a large pool of Open Source video libraries available for everybody, it is now possible practically for anybody with basic engineering skill to create a video processing system. The variety of applications for video processing is just as impressive: from surveillance, to video coding and annotation, to computer-human interaction and collaborative environments, to multi-media, to video conferencing and computer games, to name a few.
However, while for humans it is very easy to give a meaning to observed visual stimuli, it remains to be a great challenge to build a computer system that can successfully do the same.
In this talk, we will overview the problems associated with the task of recognition in video, of which face recognition is of a particular interest because of its direct link to all human-oriented video technologies, and will present several successful video recognition applications developed within the IIT-NRC Perceptual Vision Project. These applications include Perceptual User Interfaces, within which computer users are identified by a webcamera, Video Annotation, which provides nametags for people in a movie or a video-conference, and Automated Surveillance Monitoring, where critical evidence snapshots are extracted and annotated automatically to facilitate the detection of criminals.
Dr. Dmitry O. Gorodnichy, PhD (CompSci) from U. of Alberta, PhD (Math) from Ukrainian AcSc, , MSc (cum laude) from Moscow Institute of Technology, is a project leader for Perceptual Vision Technology project at the Institute for Information Technology of the National Research Council of Canada. He is an author of over 50 publications dedicated to the problems of associative recognition, vision-based robotics, and more recently, video perception and face processing and recognition in video, including publications in Neural Processing Letters, Robotics Today, Image and Vision Computing, and an IEEE IJCNN Best Presentation Award paper. He is the editor of the Special Issue of the Image and Vision Computing journal on Face Processing in Video Sequences and an organizer and program chair of several international workshops on Face Processing in Video (IEEE FPiV’04, CRV FPiV’05) and Video Processing for Security (CRV VP4S-06). The work of Dr. Gorodnichy on designing Perceptual Vision Interfaces Nouse (Nose as Mouse) is featured in such national and international media, as New Scientist, BBC, CNN (UK), ABC (Australia), New York Times (USA), and CBC, Maclean’s Magazine, and Discovery Channel (Canada). He is a holder of NRC-CNRC Outstanding Scientific Achievement Award, Young Investigator Award from the Canadian Image Processing and Pattern Recognition Society and is listed as one of the Leaders of Tomorrow by the by Canadian Partnership Group for Science and Engineering (PAGSE).