Dr. Ko Nishino, Louis Kratz's research published in IEEE journal

Crowd motion tracking image
Nishino and Kratz track pedestrians in crowded scenes by predicting their movements using a space-time model of the crowd's motion.

March 21, 2012 — "Tracking with Local Spatio-Temporal Motion Patterns in Extremely Crowded Scenes," a research paper written by Dr. Ko Nishino, associate professor of computer science, and Louis Kratz, CS Ph.D. candidate, was chosen as the Spotlight Paper for the May 2012 issue of IEEE Transactions on Pattern Analysis and Machine Intelligence.

Videos of crowded scenes represent significant challenges to tracking due to the large number of pedestrians and the frequent partial occlusions that they produce. In the paper, Nishino and Kratz present a novel Bayesian framework for tracking pedestrians in videos of crowded scenes using a space-time model of the crowd motion.

The paper is currently highlighted on the journal's website here and will be available to the public for free for 30 days. Read the PDF here.