Multimedia Knowledge and Social Media Analytics Laboratory

Kaltsa Vagia

vagiakal@iti.gr

Short Bio

Vagia Kaltsa received the Diploma degree in Electrical and Computer engineering from the Aristotle University of Thessaloniki in 2009. Since October 2010, she is a Ph.D. candidate at the Aristotle University of Thessaloniki and she is also working as a Postgraduate Research Fellow at the Information Technologies Institute (ITI) in Centre for Research and Technology Hellas (CERTH).

Her current research interests include computer vision, video and image processing, analysis of crowds and anomaly detection from surveillance videos.

 

Research

"Swarm Intelligence for detecting Interesting Events"

In the following playlist, some sample videos of anomaly detection from Ucsd dataset are provided. Rectangles depict regions of interest (ROIs) in which our algorithm is applied. Blue color contour is the default color of ROIs, while green contour reveals "anomalies" according to ground truth. Detected "anomalies" from our algorithm appear with red colored ROIs.

 

 

 

 

Key Publications: 

V. Kaltsa, A. Briassouli, I. Kompatsiaris, L. Hadjileontiadis, M. G. Strintzis, "Swarm Intelligence for Detecting Interesting Events in Crowded Environments", IEEE Trans. on Image Processing, vol 24, issue 7, pp 2153-2166, July 2015. DOI: 10.1109/TIP.2015.2409559

V. Kaltsa, A. Briassouli, I. Kompatsiaris and M. G. Strintzis,  "Swarm - based Motion Features for Anomaly Detection in Crowds", 2014 IEEE International Conference on Image Processing, Paris, France, Oct 27-30, 2014.

V. Kaltsa, A. Briassouli, I. Kompatsiaris and M. G. Strintzis, "Timely, Robust Crowd Event Characterization", 2012 IEEE International Conference on Image Processing, Orlando, Fla, USA, Sept 30 - Oct 3 2012.