A Study of the Possibility of Usage Motion Vectors of Compressed Videos to Create Video Identification

Abstract

The use of motion vectors for identifying video sequences has been well studied (in the framework of research on the topic CBCD – Content-Based Copy Detection ‒ detecting copies of videos based on content analysis). This makes it possible to check the similarity of two video fragments or search for a fragment in a larger video sequence. Existing and well-known methods for forming identification datasets typically use complete video stream decoding. The authors suggested using the motion vectors of a compressed video stream, which reduces the computational costs for identifying video sequences and uses simplified algorithms to generate identification data. Unlike the previously proposed methods, which implement either modified video codecs or obsolete ones, the authors propose using data formed by compression codecs that are used in the most common video hosting platforms (Youtube, Vimeo, etc.) The possibility of forming an automated system of comparing video sequences, along with its possibilities and limitations, will be studied in the following works.