Development and research of software based on a motion detection algorithm for an intelligent video surveillance system

E.A. Bukhamer, I.N. Tomilov, E.E. Istratova

Abstract


The article presents the results of the development and testing of motion detection software. This module can be used as part of an intelligent video surveillance system in embedded systems with limited computing power. The software was developed based on the proposed motion detection algorithm. It was experimentally proved that the implementation in the Python programming language is several times slower than the implementation in the C / C ++ programming language, which makes the second implementation option more successful for solving the problem of developing a motion detection module. It was also proven that the motion detection module, developed on the basis of the modernized algorithm, compared to the basic one, has better detection accuracy and resistance to hardware noise and false alarms.


Full Text:

PDF (Russian)

References


Pareek P., Thakkar A. A survey on video-based human action recognition: recent updates, datasets, challenges and applications // Artif Intell Rev 54, 2259–2322 (2021). https://doi.org/10.1007/s10462-020-09904-8.

Abbas Q., Ibrahim M.E., Jaffar M.A. A comprehensive review of recent advances on deep vision systems // Artif Intell Rev 52, 39–76 (2019). https://doi.org/10.1007/s10462-018-9633-3.

Varkonyi-Kóczy A.R. New advances in digital image processing // Memetic Comp. 2, 283–304 (2020). https://doi.org/10.1007/s12293-010-0046-3.

Mahalingam T., Subramoniam M. Optimal object detection and tracking in occluded video using DNN and gravitational search algorithm // Soft Comput 24, 18301–18320 (2020). https://doi.org/10.1007/s00500-020-05407-4.

Molina-Cabello M.A., García-González J., Luque-Baena R.M. The effect of downsampling–upsampling strategy on foreground detection algorithms // Artif Intell Rev 53, 4935–4965 (2020). https://doi.org/10.1007/s10462-020-09811-y.

Kamranian Z., Naghsh Nilchi A.R., Sadeghian H. Joint motion boundary detection and CNN-based feature visualization for video object segmentation // Neural Comput & Applic 32, 4073–4091 (2020). https://doi.org/10.1007/s00521-019-04448-7.

López-Rubio F.J., López-Rubio E., Molina-Cabello M.A. The effect of noise on foreground detection algorithms // Artif Intell Rev 49, 407–438 (2018). https://doi.org/10.1007/s10462-016-9525-3.

Meng F., Yuan G., Lv S. An overview on trajectory outlier detection // Artif Intell Rev 52, 2437–2456 (2019). https://doi.org/10.1007/s10462-018-9619-1.

Yang S., Hao K., Ding Y. Improved visual background extractor with adaptive range change // Memetic Comp. 10, 53–61 (2018). https://doi.org/10.1007/s12293-017-0225-6.

Pal S.K., Bhoumik D., Bhunia Chakraborty D. Granulated deep learning and Z-numbers in motion detection and object recognition // Neural Comput & Applic 32, 16533–16548 (2020). https://doi.org/10.1007/s00521-019-04200-1.

Verdant A., Villard P., Dupret A. Three novell analog-domain algorithms for motion detection in video surveillance // Image Video Proc. 2011, 698914 (2011). https://doi.org/10.1155/2011/698914.

Istratova E.E., Dostovalov D.N., Bukhamer E.A. Development of an intelligent system for face recognition based on neural networks // International Journal of Open Information Technologies. 2021. V. 9. №. 4. - P. 41-45.

Bukhamer E.A., Tomilov I.N., Istratova E.E. Face recognition software for embedded platforms with limited computing power. Certificate of registration of the computer program 2021615215. 06.04.2021. Application № 2021614553 dated 06.04.2021


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162