(49-2) 11 * << * >> * Russian * English * Content * All Issues

Design of a home video behavior recognition system based on visual privacy security mechanism
D.M. Zhao 1,2

1 Academic Affairs Office (Laboratory Center), Dongguan City University,
No. 1 Wenchang Road, Songshan Lake Avenue, Dongguan, 523419, China;
2 Graduate School, University of Perpetual Help System Laguna,
City of Biñan, Laguna, 4024, Philippines

 PDF, 3443 kB

DOI: 10.18287/2412-6179-CO-1456

Pages: 263-272.

Full text of article: English language.

Abstract:
The rapid development of the Internet and advanced technology has brought great convenience to people’s lives; However, real-time video and other privacy information obtained from computers can be leaked, resulting in economic losses and not conducive to the construction of computer network security. In response to the above issues, this study introduces compressed perception theory and temporal adaptive modules to achieve visual shielding, and based on this, designs a home video behavior system based on visual privacy security mechanism. The research results show that in the comparison of measurement matrices at different levels, the Bernoulli random matrix has the highest recognition accuracy, with recognition accuracy rates of 100 %, 98.73 %, 98.76 %, and 85.62 % from the first layer to the fourth layer, respectively. In the recognition performance results of different video behavior recognition systems in the YouTube database, UCF Sports database, and Hollywood2 database, the average recognition accuracy of the proposed system is the highest in most cases, with 94.6 %, 73.5 %, and 77.1 %, respectively. In summary, the system proposed in the study can achieve accurate recognition of home video behavior after visual masking, and has good results in practical applications.

Keywords:
visual privacy security, home videos, behavior recognition, time series adaptive network, compression perception.

Citation:
Zhao, DM. Design of a home video behavior recognition system based on visual privacy security mechanism. Computer Optics 2025; 49(2): 263-272. DOI: 10.18287/2412-6179-CO-1456.

Acknowledgements:
The research was supported by Design and Implementation of RFID-based Experimental Equipment Management Platform (No. 2022QJY001Z), “Young Teachers Development Fund” of Dongguan City University.

References:
  1. Yang Y, Song X. Research on face intelligent perception technology integrating deep learning under different illumination intensities. Journal of Computational and Cognitive Engineering 2022; 1(1): 32-36. DOI: 10.47852/bonviewJCCE19919.
  2. Lei Y. Research on microvideo character perception and recognition based on target detection technology. Journal of Computational and Cognitive Engineering 2022, 1(2): 83-87. DOI: 10.47852/bonviewJCCE19522514.
  3. Dey P, Jana DK. Evaluation of the convincing ability through presentation skills of pre-service management wizards using AI via T2 linguistic fuzzy logic. Journal of Computational and Cognitive Engineering 2022; 2(2): 133-142. DOI: 10.47852/bonviewJCCE2202158.
  4. Hui Z, Li J, Gao X, et al. Progressive perception-oriented network for single image super-resolution. Inf Sci 2021; 546(2): 769-786. DOI: 10.1016/j.ins.2020.08.114.
  5. Fante KA, Abdurahman F, Gemeda MT. An ingenious application-specific quality assessment methods for compressed wireless capsule endoscopy images. Trans Environ Electr Eng 2020; 4(1): 18-24. DOI: 10.22149/teee.v4i1.139.
  6. Chi Z. Research on satellite remote sensing image fusion algorithm based on compression perception theory. J Comput Methods Sci Eng 2021; 21(2): 341-356. DOI: 10.3233/JCM-204411.
  7. Wang W, Dong J, Ziwen HE, et al. A brief introduction to visual adversarial samples. J Cyber Secur 2020; 5(2): 39-48. DOI: 10.19363/J.cnki.cn10-1380/tn.2020.02.04.
  8. Zhang L, Zhang Z, Zhao T. A novel spatio-temporal access control model for online social networks and visual verification. Int J Cloud Appl Comput 2021; 11(2): 17-31. DOI: 10.4018/IJCAC.2021040102.
  9. Liu R, Song J, Huang Z, et al. EQRC: A secure QR code-based E-coupon framework supporting online and offline transactions. J Comput Secur 2020; 28(5): 577-605. DOI: 10.3233/JCS-191416.
  10. Gangwar G, Kaur P, Taylor G. User's perception of the relevance of courtyard designs in a modern context: A case of Traditional Pol Houses, Ahmedabad. Civ Eng Archit 2020; 8(3): 379-389. DOI: 10.13189/cea.2020.080323.
  11. Liu J X, Zhang M, Sun N, et al. Home video behavior recognition based on convolutional residual network with visual privacy protection mechanism and temporal adaptive module. 2021 6th Int Conf on Communication, Image and Signal Processing (CCISP) 2021: 150-154. DOI: 10.1109/CCISP52774.2021.9639335.
  12. Muhammad K, Mustaqeem, Ullah A, et al. Human action recognition using attention based LSTM network with dilated CNN features. Future Gener Comput Syst 2021; 125: 820-830. DOI: 10.1016/j.future.2021.06.045.
  13. Miao A, Liu F. Application of human motion recognition technology in extreme learning machine. Int J Adv Robot Syst 2021; 18(1): 4-18. DOI: 10.1177/1729881420983219.
  14. Li YZ, Yuan JZ, Liu HZ. Human skeleton-based action recognition algorithm based on spatiotemporal attention graph convolutional network model. J Comput Appl 2021; 41(7): 1915-1921. DOI: 10.11772/j.issn.1001-9081.2020091515.
  15. Qi W, Wang X, Liu Z, et al. Visual recognition of ortho-xylene based on its host-guest crystalline self-assembly with α-cyclodextrin. J Colloid Interface Sci 2021; 597(21): 325-333. DOI: 10.1016/j.jcis.2021.03.024.
  16. Moskovsky AD, Burgov EV, Ovsyannikova EE. An approach to scene recognition based on the local interaction of a group of robots. Mekhatronika Avtomatizatsiya Upravlenie 2021; 22(2): 94-103. DOI: 10.17587/mau.22.94-103.
  17. Nougrara Z, Hachemi K. A new method of drainage network extraction using SAR radar images: A case study of Djanet (Algeria). J Taibah Univ Sci 2021; 15(1): 1101-1107. DOI: 10.1080/16583655.2021.2018816.
  18. Pu Y, Jiang Y, Hu HM. HR-HAR: A hierarchical relation representation for human activity recognition based on Wi-Fi. IET Commun 2023; 17(1): 29-44. DOI: 10.1049/cmu2.12497.
  19. Lyu Y, Yang Z, Liang H, et al. Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks. Fatigue & Fracture of Engineering Materials and Structures 2022; 45(6): 1690-1702. DOI: 10.1111/ffe.13693.
  20. Herman M, Wagner J, Prabhakaran V, et al. Pedestrian behavior prediction for automated driving: requirements, metrics, and relevant features. IEEE Trans Intell Transp Syst 2022; 23(9): 14922-14937. DOI: 10.1109/TITS.2021.3135136.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20