Title: Clustering based Image Segmentation and Tracking

Abstract: In machine learning and computer vision, image segmentation and tracking forms critical components in many applications. Fast and efficient algorithms are required for some applications such as robotics. Mean shift (MS) qualifies as one of the most popular mode-seeking algorithms used for clustering and image segmentation.However, its computational cost required to find the neighbors of each data point is quadratic to the number of data points. Consequently, the vanilla MS appears to be very slow for large-scale datasets. In this talk, we discuss a mode-seeking algorithm called GridShift, with significant speedup and principally based on MS.  The runtime of GridShift is linear in the number of active grid cells and exponential in the number of features. Therefore, it is ideal for large-scale low-dimensional applications such as object tracking and image segmentation. 

Speaker: Dr. Rammohan Mallipeddi, Associate Professor, Department of Artificial Intelligence,
School of Electronics Engineering, Kyungpook National University, Daegu, South Korea

Brief Bio of Speaker: Dr. Rammohan Mallipeddi (Senior Member, IEEE) received the master's and Ph.D. degrees in computer control and automation from the School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore, in 2007 and 2010, respectively. He is currently an Associate Professor with the Department of Artificial Intelligence, School of Electronics Engineering, Kyungpook National University, Daegu, South Korea.  His research interests include evolutionary computing, artificial intelligence, image processing, digital signal processing, robotics, and control engineering.   He is a highly-cited researcher with more than 7000 citations and h-index of 39 as per google scholar. He is also an  associate editor for IEEE Transactions on Cybernetics: Systems, and, Swarm and Evolutionary Computation.

Date: 28 July Tuesday, 3 PM. Venue: New seminar Room (EB208)