Abstract
Surveillance systems have undergone a drastic transformation over the years, with the advent of artificial intelligence (AI) in surveillance paving the way for better security and monitoring in public as well as private places, including hotels. But not without its considerable privacy implications since the introduction of the European Union (EU) law, the General Data Protection Regulation (GDPR), which aims to protect the privacy of EU citizens. The surveillance system collects sensitive guest data from personal information, facial data, and general appearance, making it paramount that hotels adhere to mandatory data protection laws such as the General Data Protection Regulation (GDPR) for visitors in the EU, to ensure that the data is not misused or accessed by unauthorized individuals. A privacy-protection framework for face detection and anonymization in hotel surveillance systems has been designed in this research to protect privacy from surveillance cameras based on YOLOv11, a top-tier convolutional neural network (CNN) model. The system checks for faces in video feeds/images and accurately applies a blurring mechanism, successfully anonymizing identities. The process is designed to comply with GDPR regulations while preserving essential capabilities of surveillance systems through anonymization. One of the inherent challenges is ensuring the privacy of the individuals going about their day-to-day business in front of such surveillance cameras, and at the same time, ensuring that the footage that could possibly be shared with authorities or even other stakeholders is useful. Such integration of YOLOv11 in hotel surveillance systems showcases the potential of artificial intelligence to provide security without compromising privacy.
References
Alif, M. A. R. (2024). YOLOv11 for Vehicle Detection: Advancements, Performance, and Applications in Intelligent Transportation Systems (No. arXiv:2410.22898). arXiv. https://doi.org/10.48550/arXiv.2410.22898
Ankan Ghosh. (2024). YOLO11: Faster Than You Can Imagine! https://learnopencv.com/yolo11/
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection (No. arXiv:2004.10934). arXiv. https://doi.org/10.48550/arXiv.2004.10934
Glenn Jocher. (2020). YOLOv5. https://github.com/ultralytics/yolov5
Glenn Jocher, & Jing Qiu. (n.d.). YOLO11 NEW. Https://Docs.Ultralytics.Com/Models/Yolo11/. Retrieved December 8, 2024, from https://docs.ultralytics.com/models/yolo11
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition (No. arXiv:1512.03385). arXiv. https://doi.org/10.48550/arXiv.1512.03385
Jyothis, Siva, Anand S. Nair, Kirandas VR, and Divya Visakh. "Developing a SmartRail Security System with YOLO and OpenCV." Journal of Ubiquitous Computing and Communication Technologies 6, no. 1 (2024): 28-38.
Hussain, M. (2024). YOLOv5, YOLOv8 and YOLOv10: The Go-To Detectors for Real-time Vision (No. arXiv:2407.02988). arXiv. https://doi.org/10.48550/arXiv.2407.02988
Jacob Solawetz & Francesco. (2024, October 23). What is YOLOv8? A Complete Guide. Roboflow Blog. https://blog.roboflow.com/what-is-yolov8/
Jane Austen. (2024, February 10). What is New in YOLOv8; Deep Dive into its Innovations-Yolov8. https://yolov8.org/what-is-new-in-yolov8/
Jhuang, Yun-Yun, Yu-Hui Yan, and Gwo-Jiun Horng. "GDPR Personal Privacy Security Mechanism for Smart Home System." Electronics 12, no. 4 (2023): 831.
Jocher, G., & Qiu, J. (2024). Ultralytics YOLO11 (Version 11.0.0)[Computer software]. https://github.com/ultralytics/ultralytics
Khanam, R., & Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements (No. arXiv:2410.17725). arXiv. https://doi.org/10.48550/arXiv.2410.17725
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in neural information processing systems 25, 1097–1105.
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324. https://doi.org/10.1109/5.726791
Li, C., Li, L., Geng, Y., Jiang, H., Cheng, M., Zhang, B., Ke, Z., Xu, X., & Chu, X. (2023). YOLOv6 v3.0: A Full-Scale Reloading (No. arXiv:2301.05586). arXiv. https://doi.org/10.48550/arXiv.2301.05586
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection (No. arXiv:1506.02640). arXiv. https://doi.org/10.48550/arXiv.1506.02640
Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6517–6525. https://doi.org/10.1109/CVPR.2017.690
Terven, J., & Cordova-Esparza, D. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716. https://doi.org/10.3390/make5040083
Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., & Ding, G. (2024). YOLOv10: Real-Time End-to-End Object Detection (No. arXiv:2405.14458). arXiv. https://doi.org/10.48550/arXiv.2405.14458
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (No. arXiv:2207.02696). arXiv. https://doi.org/10.48550/arXiv.2207.02696
Wang, C.-Y., & Liao, H.-Y. M. (2024). YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems (No. arXiv:2408.09332). arXiv. https://doi.org/10.48550/arXiv.2408.09332
Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (No. arXiv:2402.13616). arXiv. https://doi.org/10.48550/arXiv.2402.13616
Yang, S., Luo, P., Loy, C. C., & Tang, X. (2016). WIDER FACE: A Face Detection Benchmark. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). http://shuoyang1213.me/WIDERFACE/
Zhang, L., Moukafih, N., Alamri, H., Epiphaniou, G., & Maple, C. (2024). A BERT-based Empirical Study of Privacy Policies’ Compliance with GDPR (No. arXiv:2407.06778). arXiv. https://doi.org/10.48550/arXiv.2407.06778