BUILDING A MOVING OBJECT IDENTIFICATION SYSTEM BASED ON MACHINE LEARNING TECHNOLOGIES

The study is devoted to the construction of a system for identifying moving objects in a video stream based on machine learning technologies. Tracking and recognizing moving objects is an urgent task of our time. It is important to recognize objects in motion and identify them based on artificial intelligence. The system is divided into three main modules: face recognition, people tracking, and saving of recognition results. The use of modern technologies and YOLOv7 machine learning algorithms for tracking people and the Face Recognition library for face recognition is described. A contextual Data flow diagram is created, which shows the sequence of steps required to convert the input video stream into normalized face images that are ready for further recognition. The hierarchy of processes of the moving object identification system is built. The video processing process decomposition diagram shows the logical sequence of stages and data flows required to prepare face images. Behavior classification associates detected motion patterns with specific types of behavior. The system uses facial identification data and information about their previous behavior to classify movement patter