News Shot Classification and Analysis

My aim is to classify and analyze different types of news shots which are encountered in the news broadcast videos that Red Hen processes everyday. The system will extract visual features (such as the presence of a particular object, scene type, etc.) in the form of class labels, and may help provide low level semantic information used for further processing. I also intend to develop a classifier which classifies on the basis of camera shot type (such as Newsperson(s), Background roll, Graphics, etc). The developed pipeline will finally be deployed onto the Case Western Reserve University distributed computing cluster.