Development of a file system for storing data of an intelligent video surveillance system

The article considers the problem of creating a file system with characteristics different from universal ones for storing data of intelligent video surveillance systems. Access to the file system is a determining factor on which the performance of the entire system depends. A fast data bus and a modern processor do not always determine the speed of data operations, but also the hard disk access driver which, accordingly, can limit the system ability to perform basic functions: surveillance, image analysis, detection of images and events. It is necessary to select a more productive server which is expensive, or use a specialized driver to increase the speed of writing and reading on the hard disk. The use of a specialized file system focused on solving one or a limited number of problems can significantly increase the speed of systems in cases where the server is used with the same technical characteristics. In intelligent video surveillance systems, the use of a specialized file system can provide an increase in the speed of image processing and the accuracy of object detection in the video stream, due to the increased speed of reading and writing from the disk. An analysis of existing file systems has shown that the existing solutions do not provide the required speed of working with data in intelligent video surveillance systems when using technical means with the same computing characteristics. In this article, the authors propose a specialized file system for storing data in intelligent video surveillance systems. A file system has been developed that is focused on solving one problem: storing data in intelligent surveillance systems. The developed driver increases the speed of accessing the data on the hard drive. The new file system for storing data in an intelligent video surveillance system works together with a database for one, separate task. A comparison of the speed of writing and reading data using the developed driver and using existing universal drivers made. As a result of the comparison, it has been established that the use of the new driver has increased the speed of writing and reading by 43.4 % relative to NTFS file system. As part of the study, a file system for intelligent video surveillance systems was developed, but similar specialized file systems can be developed for use in other areas where it is necessary to increase the speed (reduce the time) of writing and reading data from the file system.

1. Avhad A.R., Gangad P.S., Kharote S.M., Muntode S.S., Sanap M.D. Blockchain based secure file transfer system with password protection. International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), 2024, vol. 4, no. 2, pp. 299–303. https://doi.org/10.48175/ijarsct-19651

2. Panjuta D., Jabbarzadeh J. C# File System. Learning C# Through Small Projects. Springer, 2024, pp. 167–198. https://doi.org/10.1007/978-3031-51914-7_6

3. Needhi J., Prasath R., Vikram K.K., Vishnu G. Performance optimization of voice-assisted file management systems. International Journal of Engineering and Computer Science, 2024, vol. 13, no. 7, pp. 26250–26256. https://doi.org/10.18535/ijecs/v13i07.4854

4. Cho K., Bahn H. A lightweight file system design for unikernel. Applied Sciences, 2024, vol. 14, no. 8, pp. 3342. https://doi.org/10.3390/app14083342

5. Gui J., Wang Y., Shuai W. Improving reading performance by file prefetching mechanism in distributed cache systems. Concurrency and Computation: Practice and Experience, 2024, vol. 36, no. 22, pp. e8215 https://doi.org/10.1002/cpe.8215

6. Yuliana M., Hidayah N., Sudarsono A. Implementation of Web-Based file sharing security system. MOTIVECTION: Journal of Mechanical, Electrical and Industrial Engineering, 2024, vol. 6, no. 1, pp. 41–52. https://doi.org/10.46574/motivection.v6i1.314

7. Man T., Osipov V., Zhukova N., Subbotin A., Ignatov D. Neural networks for intelligent multilevel control of artificial and natural objects based on data fusion: A survey. Information Fusion, 2024, vol. 110, pp. 102427. https://doi.org/10.1016/j.inffus.2024.102427

8. Man T., Vodyaho A., Zhukova N., Subbotin A., Shichkina Y. Urban intelligent assistant on the example of the escalator passenger safety management at the subway stations. Scientific Reports. 2023. vol. 13, no. 1, pp. 15914. https://doi.org/10.1038/s41598-023-42535-x

9. Osipov V., Zhukova N., Subbotin A., Glebovskiy P., Evnevich E. Intelligent escalator passenger safety management. Scientific Reports, 2022, vol. 12, no. 1, pp. 5506. https://doi.org/10.1038/s41598-02209498-x

10. Cowan D.D., Stepien T.M., Ierusalimschy R., Lucena C.J.P. Application integration: Constructing composite applications from interactive components. Software: Practice and Experience, 1993, vol. 23, no. 3, pp. 255–275. https://doi.org/10.1002/spe.4380230304

11. Sudharsan S., Sakthi Anand A., Shanmugaraj K., Palani Samy K.C. Deep learning-based intelligent video surveillance system for realtime motion detection. International Scientific Journal of Engineering and Management, 2024, vol. 3, no. 4, pp. 1–10. https://doi.org/10.55041/ISJEM01492

12. Li J., Zheng Z., Li Y., Ma R., Xia S. Multitask deep learning for Edge Intelligence Video Surveillance system. Proc. of the IEEE 18th International Conference on Industrial Informatics (INDIN), 2020, pp. 579–584. https://doi.org/10.1109/INDIN45582.2020.9442166

13. Zhukova N.A., Subbotin A.N. Dynamic distribution algorithm for image processing in cloud-based intelligent video surveillance systems. Information and Control Systems, 2024, no. 6 (133). pp. 15–26. (in Russian). https://doi.org/10.31799/1684-8853-2024-6-15-26

14. Bhatia J., Patel T., Trivedi H., Majmudar V. Htv dynamic load balancing algorithm for virtual machine instances in cloud. Proc. of the International Symposium on Cloud and Services Computing, 2012, pp. 15–20. https://doi.org/10.1109/ISCOS.2012.25

15. Rahm E., Do H.H. Data cleaning: problems and current approaches. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, 2000, vol. 23 no. 4, pp. 3–13.

16. Saecker M., Markl V. Big data analytics on modern hardware architectures: a technology survey. Lecture Notes in Business Information Processing, 2013, vol. 138, pp. 125–149. https://doi.org/10.1007/978-3-642-36318-4_6