Abstract
In recent years, video surveillance systems have become an essential component of modern security and safety systems. These systems rely on the ability to accurately classify and track moving objects in video streams, which can be challenging due to the complex nature of video data. Therefore, the need for effective methods for object classification in video has become increasingly important.
In this thesis, we will discuss adaptive methods for the classification of objects in videos. We will provide an overview of the classical steps involved in video classification and highlight the importance of classification in video surveillance systems. We will focus on the classification of moving objects in video streams and explore various adaptive methods that can be used to improve the accuracy of object classification.