UDC 004.896
DEVELOPMENT AND RESEARCH OF SOFTWARE FOR AN INTELLIGENT REAL-TIME VIDEO ANALYTICS SYSTEM
S. V. Skvortsov, Dr. in technical sciences, full professor, RSREU, Ryazan, Russia;
orcid.org/0000-0001-9495-4953, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
N. A. Sokolov, Master's student, RSREU, Ryazan, Russia;
orcid.org/0009-0008-3584-1033, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
This paper examines the architecture of intelligent video surveillance system, the development of which
is driven by growing security needs. The aim of the paper is to justify the choice of algorithmic framework
for the system, which enables the detection of people in surveillance zones, tracking their movements, and
reconstructing facial images in real time. A comparative analysis of computer vision neural networks, tracking
algorithms, and image reconstruction algorithms is performed for various lighting conditions and input
data quality. The impact of detection model specialization and reconstruction methods on recognition accuracy,
frame processing time, and occlusion tolerance for daytime and nighttime operation is demonstrated.
Key words: intelligent video surveillance, computer vision, object detection, motion tracking, image restoration, neural networks, keypoints, software, databases.