DEVELOPMENT OF OBJECT MOVEMENT ALGORITHM BY THE NEURAL NETWORK FOR THE CCTV SYSTEM

Abstract

This article addresses the problem of protecting the private property of a protected object, namely: it offers an algorithm for recognizing object movements using a neural network for the CCTV system. The ability of the perception of the outside world in the form of images allows to investigate with certain probability the properties of an infinite number of objects on the basis of acquaintance with their finite number, and the objective nature of the basic property of the images allows to model the process of their recognition. , namely "image", "feature", "vector implementation". The approaches, methods and technologies of object motion recognition are investigated, their qualitative characteristics and disadvantages are highlighted. Artificial neural networks have been found to be the most effective method for solving the object motion recognition task due to result accuracy, simplicity and speed. On the basis of the block diagram of the complex algorithm for image processing and analysis, the algorithm of object motion recognition using neural network for the video surveillance system was developed.