Privacy-aware smart camera for abnormal event detection in home environments
9 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.109.2026.137-145Keywords:
Convolutional neural network; Deep learning; Optical flow; Anomaly detection; Smart camera.Abstract
Ensuring both effective monitoring and user privacy is essential in home surveillance applications. This study proposes a privacy-aware smart camera system integrating a servo-controlled mechanical housing with a dual-branch deep learning framework. That is a smart camera housing equipped with servo-controlled lids and dual operation modes, local button control and WiFi-based remote control, providing convenient usage while preventing unintended image capture. To detect hazardous household events, we constructed the EPUabInhouse dataset and proposed a dual-branch framework that integrates YOLOv8 for spatial analysis with RAFT optical flow for motion representation. Experimental results show that incorporating RAFT leads to a relative improvement of 2.02% to 4.15% in F1-score across different classes and significantly reduces background misclassification. These enhancements demonstrate the effectiveness and practical applicability of the proposed privacy-aware home surveillance system.
References
[1]. Hồ Anh Dũng, Đoàn Thị Hương Giang, Trần Đình Hùng, Ma Khánh Tùng, Nguyễn Huyền Tiến An, Bùi Thị Duyên, “Hệ thống phát hiện khói và cháy thông minh đa thể thức”, Tạp chí Khoa học và Kỹ thuật – Học viện Kỹ thuật Quân sự, vol. 97, no. 97, pp. 138–147, (2024) (in Vietnamese). DOI: https://doi.org/10.54939/1859-1043.j.mst.97.2024.138-147
[2]. Elhanashi, S. Essahraui, P. Dini, S. Saponara, “Early Fire and Smoke Detection Using Deep Learning: A Comprehensive Review”, Applied Sciences, vol. 15, no. 18, article 10255, pp. 1–34, (2025). doi:10.3390/app151810255. DOI: https://doi.org/10.3390/app151810255
[3]. D. Gragnaniello, A. Greco, C. Sansone, B. Vento, “Fire and Smoke Detection from Videos: A Literature Review under a Novel Taxonomy”, Expert Systems with Applications, vol. 260, article 124783, pp. 1–32, (2024). doi:10.1016/j.eswa.2024.124783. DOI: https://doi.org/10.1016/j.eswa.2024.124783
[4]. V. Carletti, A. Greco, A. Saggese, B. Vento, “A Smart Visual Sensor for Smoke Detection Based on Deep Neural Networks”, Sensors, vol. 24, article 4519, (2024). doi:10.3390/s24144519. DOI: https://doi.org/10.3390/s24144519
[5]. K.-S. Wong, N. A. Tu, A. Maratkhan, M. F. Demirci, “A Privacy-Preserving Framework for Surveillance Systems”, Proceedings of the 10th International Conference on Communication and Network Security (ICCNS), Tokyo, Japan, pp. 91–98, (2021). doi:10.1145/3442520.3442524. DOI: https://doi.org/10.1145/3442520.3442524
[6]. R. K. Yadav, R. Kumar, “A Survey on Video Anomaly Detection”, IEEE Delhi Section Conference (DELCON), New Delhi, India, pp. 1–5, (2022). doi:10.1109/DELCON54057.2022.9753580. DOI: https://doi.org/10.1109/DELCON54057.2022.9753580
[7]. E. Alam, A. Sufian, P. Dutta, M. Leo, “Vision-based Human Fall Detection Systems Using Deep Learning: A Review”, Computers in Biology and Medicine, vol. 146, article 105626, (2022). doi:10.1016/j.compbiomed.2022.105626. DOI: https://doi.org/10.1016/j.compbiomed.2022.105626
[8]. C. Li, M. Liu, X. Yan, G. Teng, “Research on CNN-BiLSTM Fall Detection Algorithm Based on Improved Attention Mechanism”, Applied Sciences, vol. 12, article 9671, (2022). doi:10.3390/app12199671. DOI: https://doi.org/10.3390/app12199671
[9]. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, (2016). doi:10.1109/CVPR.2016.91. DOI: https://doi.org/10.1109/CVPR.2016.91
[10]. Z. Teed, J. Deng, “RAFT: Recurrent All-Pairs Field Transforms for Optical Flow”, European Conference on Computer Vision (ECCV), LNCS 12347, pp. 402–419, Springer, (2020). doi:10.1007/978-3-030-58536-5_24. DOI: https://doi.org/10.1007/978-3-030-58536-5_24
[11]. G. Jocher et al., “YOLOv5 by Ultralytics”, GitHub Repository, (2020). Available: https://github.com/ultralytics/yolov5
[12]. C. Li et al., “YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications”, arXiv preprint arXiv:2209.02976, (2022).
[13]. C.-Y. Wang, A. Bochkovskiy, H.-Y. M. Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, pp. 7464–7475, (2023). DOI: https://doi.org/10.1109/CVPR52729.2023.00721
[14]. G. Jocher et al., “Ultralytics YOLOv8 Technical Report”, Ultralytics, pp. 1–45, (2023).
