Development and research of software to improve the efficiency of motion detection in the intelligent video surveillance system

E.E. Istratova, A.O. Smirnova

Abstract


The article presents the results of the development and testing of software for motion detection, which has low requirements for computing resources and, at the same time, functional characteristics sufficient for the operation of an intelligent video surveillance system in real time. In the course of the work, the features of the application of software and hardware solutions and motion detection algorithms on devices with limited computing power were considered, and software requirements were determined. As a result of the software implementation, a motion detection solution was developed, a distinctive feature of which is the ability to work with multiple camera streams simultaneously in real time. The software can be installed on embedded systems and used to solve problems of monitoring and security of premises and territories. The finished software product allows you to set stream parameters when adding a camera, as well as subsequently change them, it also provides for editing the default values and global parameters of camera streams, which improves the efficiency of the motion detection process in intelligent video surveillance systems.

Full Text:

PDF (Russian)

References


Proskurin A.V., Kovtunenko I.I. Selection of informative images from a sequence based on object motion detection // Reshetnevskiye readings. - 2018. - no. 2. - S. 287-288.

Istratova E.E., Bukhamer E.A., Tomilov I.N. Development of a combined motion detection method for an intelligent video surveillance system // International Journal Of Open Information Technologies. - 2022. - No. 1. - S. 54-60.

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.

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.

Lee G., Wang M.J., Li H.T. A motion-adaptive deinterlacer via hybrid motion detection and edge-pattern recognition // Image Video Proc. — 741290 (2008). https://doi.org/10.1155/2008/741290.

Nokeeva R.M. Development of software for the optimal operation of the video recorder // Scientific research. - 2019. - No. 3 (29). - S. 15-19.

Mohtavipour, S.M., Saeidi, M. & Arabsorkhi, A. A multi-stream CNN for deep violence detection in video sequences using handcrafted features. Vis Comput 38, 2057–2072 (2022). https://doi.org/10.1007/s00371-021-02266-4.

Chillet, D., Hübner, M. Special issue on design and architectures of real-time image processing in embedded systems. J Real-Time Image Proc 9, 1–3 (2014). https://doi.org/10.1007/s11554-014-0401-6.

Pedre, S., Krajník, T., Todorovich, E. et al. Accelerating embedded image processing for real time: a case study. J Real-Time Image Proc 11, 349–374 (2016). https://doi.org/10.1007/s11554-013-0353-2.

Jeon, G., Chehri, A. Special issue on deep learning for emerging embedded real-time image and video processing systems. J Real-Time Image Proc 18, 1167–1171 (2021). https://doi.org/10.1007/s11554-021-01156-1.

Lacassagne, L., Manzanera, A., Denoulet, J. et al. High performance motion detection: some trends toward new embedded architectures for vision systems. J Real-Time Image Proc 4, 127–146 (2009). https://doi.org/10.1007/s11554-008-0096-7.

Seznec, M., Gac, N., Orieux, F. et al. Real-time optical flow processing on embedded GPU: an hardware-aware algorithm to implementation strategy. J Real-Time Image Proc 19, 317–329 (2022). https://doi.org/10.1007/s11554-021-01187-8.

Thevenin, M., Paindavoine, M., Schmit, R. et al. A templated programmable architecture for highly constrained embedded HD video processing. J Real-Time Image Proc 16, 143–160 (2019). https://doi.org/10.1007/s11554-018-0808-6.

Dias, T., López, S., Roma, N. et al. Scalable Unified Transform Architecture for Advanced Video Coding Embedded Systems. Int J Parallel Prog 41, 236–260 (2013). https://doi.org/10.1007/s10766-012-0221-x.

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.

Xiong, W., Lee, CM. & Ma, RH. Automatic video data structuring through shot partitioning and key-frame computing. Machine Vision and Applications 10, 51–65 (1997). https://doi.org/10.1007/s001380050059.

Kamranian, Z., Naghsh Nilchi, A.R., Sadeghian, H. et al. 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.

Yubing, T., Cheikh, F.A., Guraya, F.F.E. et al. A Spatiotemporal Saliency Model for Video Surveillance. Cogn Comput 3, 241–263 (2011). https://doi.org/10.1007/s12559-010-9094-8.

Lee, G., Wang, MJ., Li, HT. et al. A Motion-Adaptive Deinterlacer via Hybrid Motion Detection and Edge-Pattern Recognition. J Image Video Proc 2008, 741290 (2008). https://doi.org/10.1155/2008/741290.

Ali, I., Mille, J. & Tougne, L. Adding a rigid motion model to foreground detection: application to moving object detection in rivers. Pattern Anal Applic 17, 567–585 (2014). https://doi.org/10.1007/s10044-013-0346-6.

Szolgay, D., Benois-Pineau, J., Megret, R. et al. Detection of moving foreground objects in videos with strong camera motion. Pattern Anal Applic 14, 311–328 (2011). https://doi.org/10.1007/s10044-011-0221-2.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162