Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Electronics and Communication

In this thesis, we propose a complete framework that enables big-data frameworks to run sequential computer vision algorithms in a scalable and parallel way. Our idea is to divide the input video files into small chunks that can be processed in parallel without affecting the quality of the resulting output. We developed an intelligent data grouping that enables chunk-based framework to distribute these data chunks among the available resources and gather the results out of each chunk faster than the standalone sequential approach

Issued also as CD