Computer Engineering Commons^™

A Self Organization-Based Optical Flow Estimator With Gpu Implementation, Manish Shiralkar

All Dissertations

This work describes a parallelizable optical flow estimator that uses a modified batch version of
the Self Organizing Map (SOM). This gradient-based estimator handles the ill-posedness in motion
estimation via a novel combination of regression and a self organization strategy.
The aperture problem is explicitly modeled using an algebraic framework
that partitions motion estimates obtained from regression into two sets, one (set H_c) with estimates
with high confidence and another (set H_p) with low confidence estimates. The self organization step
uses a uniquely designed pair of training set (Q=H_c) and the initial weights set …