Analyzing video streams for identifying & eliminating advertisements
Loading...
Date
2017
Journal Title
Journal ISSN
Volume Title
Publisher
University of Management and Technology
Abstract
This project proposes a system which is semi-autonomous system and is based on software as a service architecture (SaaS). It analyzes video streams for acquisition of advertisements. On basis of this analysis it provides autonomous removal of advertisements from TV stream recordings, which are uploaded by user. It also generates reports based on statistics recorded from live TV streams. Video editing tools and software available in the markets perform time based trimming. This means that the user has to specify the points in time at which the scene begins and ends. These time points are used as reference markers. The content which lies in between theses markers is removed. These software are very easy to use and once reference markers and specified the cutting (trimming) process is very fast. In this proposed system we have automated the process of defining reference markers. This means that the user will not have to specify commercials in the video.
Description
Supervised by: Dr. Muhammad Masroor Ahmad
Keywords
Video editing tools, Software as a service architecture, BS thesis