Algorithm for tracking the movements of a person in the video stream from surveillance cameras

Keywords: surveillance cameras, pattern recognition, delta E, tracing, YOLO neural network, active area, object detection, tracking, mathematical statistics, predicted area, RGB pixels

Abstract

The task of tracking the movement of objects in the video stream (tracing) is one of the most difficult tasks of modern video surveillance and video analytics systems. The tracing task is understood as the task of automated recognition and further tracking of objects throughout the sequence of frames of the video stream. The purpose of this article is not only a brief analysis of some of the existing methods and algorithms necessary for visualizing the movement of objects, but also the development of a new algorithm for tracing human movements in a video stream with the ability to display motion trajectories. The proposed approach makes it possible to eliminate some of the shortcomings of currently existing methods (presence of special equipment, the need for preliminary training, overlapping of the object with other objects, going beyond the camera’s field of view). The paper describes the main advantages of this algorithm, its most important functions and capabilities. The main stages of the algorithm operation include: selecting a person in the video stream, implementing the digital processing procedure, which is based on dividing the human body into its constituent parts and obtaining a color histogram of these parts, predicting the location and recognizing the person under study on all subsequent frames of the video stream, where the RGB pixel color analysis is performed using the method of comparing the obtained data with the color histogram of the constituent parts of the main object. The output data of the proposed algorithm is used in the procedure of forming and displaying a general picture of the movement of a particular object within the entire video stream. This article may be of interest to specialists and experts who use computer vision methods in their work to automatically obtain the necessary data when analyzing video fragments.

Downloads

Download data is not yet available.

Author Biographies

Mikhail M. Gumenyuk, Yuri Gagarin State Technical University of Saratov

PhD student, Department of Applied Information Technologies, Yuri Gagarin State Technical University of Saratov

Alexander V. Brovko, Yuri Gagarin State Technical University of Saratov

Doctor of Sciences in Physics and Mathematics, Professor of the Department of Applied Information Technologies, Yuri Gagarin State Technical University of Saratov

References

1. Anstedt T., Keller I. and Lutz H. (2022) Video analytics: Myths and reality. Ed. «Security Focus». (In Russian)
2. Viola P. and Jones M. (2001) Rapid Object Detection using a Boosted Cascade of Simple Features. Accepted Conference on Computer Vision and Pattern Recognition (CVPR 2001). P. 511–518. DOI
3. Minaev E. Yu., Kutikova V. V. and Nikonorov A. V. (2018) Tracking of objects in a video stream based on convolutional neural networks and fractal analysis. New technique. P. 2792–2898. (In Russian)
4. Artemov A. A., Kavalerov M. V. and Kuznetsov G. S. (2011) The problem of finding objects in images using computer vision based on color information. Bulletin of Perm State Technical University. Electrical engineering, information technology, control systems. P. 70–79. (In Russian)
5. Shelabin D. A. and Sergeev S. L. (2013) The process of tracing moving objects in a video stream. Actual problems of humanities and Natural Sciences. P. 71–77. (In Russian)
6. Zhivrin Ya. E. and Alkzir Nafeh Bashar (2018) Methods for determining objects in images. Young Scientist Magazine. 7 (193). P. 8–19. (In Russian)
7. Pchelkin A. V. and Nikiforov M. B. (2020) An algorithm for measuring the coordinates of an object in a video stream for an object tracking system with a prediction of the trajectory of movement. Izvestia of Tula State University. Technical Sciences. (12). P. 29–35. (In Russian)
8. Grabner H., Grabner M. and Bischof M. (2006) Real-time Tracking via On-line Boosting. In Proceedings British Machine Vision Conference (BMVC). P. 47–56. DOI
9. Babenko B. (2009) Visual Tracking with Online Multiple Instance Learning. Computer Vision and Pattern Recognition, CVPR 2009. IEEE Conference. P. 101–108. DOI
10. Henriques J. F. (2015) High-Speed Tracking with Kernelized Correlation Filters. IEEE transactions on pattern analysis and machine intelligence. P. 301–314. DOI
11. Lyashov M. V., Bereza A. N. Babaev A. M. and Kotsyubinskaya S. A. (2018) Neural network system for tracking and recognizing objects in a video stream. Modern high-tech technologies. (12-1), P. 102–107. (In Russian)
12. Pastushkov A. V. (2018) Method and algorithms for searching for an object in a video stream. Tomsk State University of Control Systems and Radio electronics (TUSUR) RAS. Tomsk, Russia. (In Russian)
13. Gumenyuk M. M. (2022) Analysis of solutions for detecting and recognizing objects in images. Management problems in socio-economic and technical systems: sat. sci. articles XVIII International Scientific and Practical Conference. 14–15 April 2022, Saratov, Russia, P. 126–132. (In Russian)
14. Erokhin D. Yu. and Ershov M. D. (2018) Modern convolutional neural networks for object detection and recognition. Digital signal processing. 3. P. 64–69. (In Russian)
15. Kukharev G. A. and Shchegolova N. L. (2018) Methods of two-dimensional projection of digital and images into their own subspaces: features of implementation and application. Computer optics. 42(4). P. 637–656. (In Russian)
16. Oliva D., Abd Elaziz M. and Hinojosa S. (2019) Metaheuristic Algorithms for Image Segmentation: Theory and Applications. New York, Springer Publishing Company. DOI
17. RussianBlogs. (2019) OpenCV Grabcut algorithm: segmentation and foreground extraction. URL
18. Fukunaga K. and Hostetler L. D. (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions of Information Theory. 21. P. 32–40. DOI
19. Shaposhnikov A. I. (2021) Feature vector selection for the MeanShift procedure. Reports of Tomsk State University of Control Systems and Radio electronics. 24 (2). P. 34–38. (In Russian)
20. Wikipedia (2020) Color difference. URL
Published
2023-10-26
How to Cite
Gumenyuk, M. M., & Brovko, A. V. (2023). Algorithm for tracking the movements of a person in the video stream from surveillance cameras. Proceedings of Voronezh State University. Series: Systems Analysis and Information Technologies, (3), 107-120. https://doi.org/10.17308/sait/1995-5499/2023/3/107-120
Section
Intelligent Information Systems, Data Analysis and Machine Learning