Some recent news items:
Prof. Konrad has been invited to deliver lectures at technical universities in Wroclaw, Warsaw, Szczecin and Krakow, Poland, between May 21 and 30, 2019 as a Distinguished Lecturer of the IEEE Signal Processing Society.
Prof. Konrad has been invited to deliver a keynote address at the 2019 GTTI-SPS Thematic Meeting on Multimedia Signal Processing in Bormio, Italy on Jan. 21, 2019.
IEEE Signal Processing Society has named Prof. Konrad its Distinguished Lecturer for the period 2019-2020. Each year, five members of the Society are recognized with this honor. Prof. Konrad will travel to deliver lectures on topics ranging from privacy-preserving visual analytics to user authentication to autonomous video surveillance.
Research results from Amanda Gaudreau's (PhD'17) dissertation just appeared in the January 2018 issue of Brain, a Journal of Neurology by Oxford Academic, in an article entitled "Concussion, microvascular injury, and early tauopathy in young athletes after impact head injury and an impact concussion mouse model". Amanda contributed to image analysis of mouse brains that showed tau protein clumping in nerve cells after head impact. The article is causing quite a stir as it shows for the first time, based on a mouse model, that head impact, regardless of concussion, is a likely cause of chronic traumatic encephalopathy (CTE), commonly diagnosed in NFL players. Prof. Lee Goldstein is the lead author on the article, and was Amanda's co-advisor in the course of her research at Boston University.
Profs. Konrad jointly with Profs. Ishwar and Little from ECE and Prof. Gevelber from ME won a $1M grant from the Advanced Research Projects Agency – Energy (ARPA-E) entitled “Scalable, Dual-Mode Occupancy Sensing for Commercial Venues”. The team will develop an occupancy sensing system to estimate the number of people in commercial spaces and monitor how this number changes over time. The sensor combines the data from panoramic cameras and low-resolution thermal door sensors using innovative fusion algorithms to accurately count humans in rooms of different shapes and sizes. The data fusion system will take advantage of off-the shelf sensors to reduce cost, while the system’s scalable design will support venues of various sizes.
See more details in this College of Engineering article.
Paper acceptance for the 2017 Traffic Surveillance Workshop and Challenge (TSWC-2017) organized within CVPR Workshops (CVPRW) has been completed and workshop's program is available at http://tcd.miovision.com/challenge/tswc2017
I am one of the organizers of the 2017 Traffic Surveillance Workshop and Challenge to be held in conjunction with CVPR 2017 in Honolulu, HI, USA. See the web site for details: http://tcd.miovision.com/challenge/tswc2017
I was part of an international team of researchers from Canada, China and the United States who developed a a traffic surveillance dataset, MIO-TCD (http://tcd.miovision.com). The dataset consists of over half a million images acquired at different times of day and different periods of the year by 8,000 traffic cameras in Canada and the United States. The images cover a wide range of localization challenges and are representative of typical visual data captured today in urban traffic scenarios. Each moving object has been carefully outlined and identified to enable a quantitative comparison and ranking of various algorithms. This dataset aims to provide a rigorous benchmarking facility for training and testing existing and new algorithms for the localization of moving vehicles in traffic scenes.
Jointly with Prof. André Zaccarin of the Université de Laval in Canada, I chaired the tutorials at the 2015 IEEE International Conference on Image Processing, ICIP-2015 held in Québec City from Sep. 27 to Sep. 30, 2015. A very successful full-day event, the tutorial day included 9 sessions on topics of contemporary importance, with "Machine Learning" by Profs. Yoshua Bengio and Roland Memisevic of the Université de Montréal setting a record attendance for an ICIP tutorial ever.