Detection of Unauthorised photography in Prohibited places through CCTV using Machine Learning
Keywords:
CCTV, CNN, MoveNet, Openpose, Pytorch, RPi, YOLOAbstract
Unauthorized photography is one of the most common and less accountable crimes. Because more and more people have access to a wider range of photographic technologies, it is becoming more difficult to ensure improved security and privacy protection in a number of contexts. Points of interest include company headquarters, government buildings, research centers, military stations, and other private areas where protecting privacy and avoiding illegal data collection are crucial. A YOLO based model helps to reduce the impact of such crimes and preserve privacy while the current surveillance infrastructure. In order to prevent unwanted data collection, the YOLO classifier in conjunction with the MoveNet for action detection offers a workable solution that promotes a more secure society. The societal impact of this technology is substantial, as it addresses growing concerns related to privacy infringement, industrial espionage, and unauthorized data gathering. With the help of the DarkNet backbone and Adam Optimiser an efficient system with a mean average precision of 89.7% and a mAP50-95 of 80% is achieved swiftly in around 150ms. Additional by using YOLOv8s and YOLOv8m parameter accuracy is improved by 2.1% and 3.3% respectively against the more lightweight and faster YOLOv8n. Objectness scores are penalized and scored based on the Binary Cross-Entropy Loss to improve object localization.
Downloads
References
A. Datta, M. Shah, and N. Da Vitoria Lobo. “Person-on-person violence detection in video data”. In IEEE International Conference on Pattern Recognition, volume 1, pages 433–438, 2002.
O. Deniz, I. Serrano, G. Bueno, and T-K. Kim. “Fast violence detection in video”. International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pages 478–485, 2014.
Hassner, Y. Itcher, and O. Kliper-Gross. “Violent flows: real-time detection of violent crowd behavior”. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pages 1–6, 2012.
Y. Gao, H. Liu, Xi. Sun, C. Wang, and Y. Liu. “Violence detection using oriented violent flows. image and vision computing”, 48-49(2015):37–41, 2016.
P.C. Ribeiro, R. Audigier, and Q. Cuong. “RIMOC, a feature to discriminate unstructured motions: application to violence detection for video-surveillance”. Computer Vision and Image Understanding, 144:121–143, 2016.
Tao Xiang, Shaogang Gong, “Incremental and adaptive abnormal behaviour detection, computer vision and image understanding”, Volume 111, Issue 1, 2008, Pages 59-73, ISSN 1077-3142.
V. Gajjar, Y. Khandhediya, and A. Gurnani, “Human detection and tracking for video surveillance: a cognitive science approach”, in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Institute of Electrical and Electronics Engineers Inc., Jul. 2017, pp. 2805–2809. doi: 10.1109/ICCVW.2017.330.
O. Sang-Hyun, K. Jin-Suk, B. Yung-Cheol, P. Gyung-Leen, B. Sang-Yong, “Intrusion detection based on clustering a data stream”, in: Third ACIS International Conference on Software Engineering Research, Management and Applications, 2005, pp. 220–227.
M.S. Ryoo, J.K. Aggarwal, “Stochastic representation and recognition of high-level group activities”, International Journal of Computer Vision 93, 2011 183–200.
N. Hoose, “Computer vision as a traffic surveillance tool”, IFAC Proceedings Volumes, Volume 23, Issue 2, 1990, Pages 57-64, ISSN 1474-6670,
T. Ellis, “Co-operative computing for a distributed network of security surveillance cameras”, IEE European Workshop Distributed Imaging (Ref. No. 1999/109), London, UK, 1999, pp. 10/1-10/5
P. Wonghabut, J. Kumphong, T. Satiennam, R. Ung-Arunyawee, and W. Leelapatra, “Automatic helmet-wearing detection for law enforcement using cctv cameras”, in IOP Conference Series: Earth and Environmental Science, Institute of Physics Publishing, Apr. 2018.
H. Dammalapati and M. Swamy Das, “An efficient criminal segregation technique using computer vision,” in Proceedings - IEEE 2021 International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2021, Institute of Electrical and Electronics Engineers Inc., Feb. 2021, pp. 636–641.
K. Lloyd, P. L. Rosin, A. D. Marshall, and S. C. Moore+, “Violent behaviour detection using local trajectory response,” 2016.
A. Wiliem, V. Madasu, W. Boles, and P. Yarlagadda, “A suspicious behaviour detection using a context space model for smart surveillance systems,” Computer Vision and Image Understanding, vol. 116, no. 2, pp. 194–209, Feb. 2012, doi: 10.1016/j.cviu.2011.10.001.
L. M. Fuentes and S. A. Velastin, “Tracking-based event detection for cctv systems,” Pattern Analysis and Applications, vol. 7, no. 4, pp. 356–364, Aug. 2005, doi: 10.1007/s10044-004-0236-z.
S. Tanjila Naurin, A. Saha, K. Akter and S. Ahmed, "A proposed architecture to suspect and trace criminal activity using surveillance cameras," 2020 IEEE Region 10 Symposium (TENSYMP), Dhaka, Bangladesh, 2020, pp. 431-435, doi: 10.1109/TENSYMP50017.2020.9230901.
A. F. D. Marsiano, I. Soesanti and I. Ardiyanto, "Deep learning-based anomaly detection on surveillance videos: recent advances," 2019 International Conference of Advanced Informatics: Concepts, Theory and Applications (ICAICTA), Yogyakarta, Indonesia, 2019, pp. 1-6, doi: 10.1109/ICAICTA.2019.8904395.
S. Shirsat, A. Naik, D. Tamse, J. Yadav, P. Shetgaonkar and S. Aswale, "Proposed system for criminal detection and recognition on cctv data using cloud and machine learning," 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), Vellore, India, 2019, pp. 1-6, doi: 10.1109/ViTECoN.2019.8899441.
M. Grega, S. Łach and R. Sieradzki, "Automated recognition of firearms in surveillance video," 2013 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA), San Diego, CA, USA, 2013, pp. 45-50, doi: 10.1109/CogSIMA.2013.6523822.
Y. Yoon et al., “Analyzing basketball movements and pass relationships using realtime object tracking techniques based on deep learning,” IEEE Access, vol. 7, pp. 56564–56576, 2019.
J. Guo et al., “Revolutionizing agriculture: real-time ripe tomato detection with the enhanced tomato-yolov7 system,” IEEE Access, vol. 11, pp. 133086–133098, 2023.
D. Luo, Y. Xue, X. Deng, B. Yang, H. Chen, and Z. Mo, “Citrus diseases and pests detection model based on self-attention yolov8,” IEEE Access, vol. 11, pp. 139872–139881, 2023.
T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using yolo: challenges, architectural successors, datasets and applications,” Multimed Tools Appl, vol. 82, no. 6, pp. 9243–9275, Mar. 2023.
Z. Dozdor, Z. Kalafatic, Z. Ban, and T. Hrkac, “TY-Net: transforming yolo for hand gesture recognition,” IEEE Access, vol. 11, pp. 140382–140394, 2023.
S. Juraev, A. Ghimire, J. Alikhanov, V. Kakani, and H. Kim, “Exploring human pose estimation and the usage of synthetic data for elderly fall detection in real-world surveillance,” IEEE Access, vol. 10, pp. 94249–94261, 2022.
X. Zhao, Z. Li, Y. Liu, and Y. Xia, “A progressive decoding strategy for action recognition,” IEEE Access, vol. 11, pp. 92424–92432, 2023.
F. Sajid, A. R. Javed, A. Basharat, N. Kryvinska, A. Afzal, and M. Rizwan, “An efficient deep learning framework for distracted driver detection,” IEEE Access, vol. 9, pp. 169270–169280, 2021.
Z. Zhou, F. Shi, and W. Wu, “Learning spatial and temporal extents of human actions for action detection,” IEEE Trans Multimedia, vol. 17, no. 4, pp. 512–525, Apr. 2015.
M. Mudgal, D. Punj, and A. Pillai, “Suspicious action detection in intelligent surveillance system using action attribute modelling,” Journal of Web Engineering, vol. 20, no. 1, pp. 129–145, Feb. 2021
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
