Intelligent Surveillance System for Knife Detection Based on YOLOv8 Neural Networks
DOI:
https://doi.org/10.67294/97s55377Keywords:
Object Detection, YOLOv8, Intelligent Surveillance, Knives, Early Warning SystemsAbstract
Cold weapon violence in urban environments represents a growing problem that demands innovative technological solutions for its prevention and control. This article presents the design and implementation of an intelligent surveillance system based on the YOLOv8nano architecture for real-time detection of sharp objects, specifically knives, in images and video streams. The model was trained through transfer learning on an annotated dataset of 2,078 images obtained from the public platform DatasetNinja, employing a two-phase strategy: freezing the ImageNet-pretrained backbone followed by full fine-tuning. Experimental results obtained on the test set demonstrate outstanding performance with a precision of 97.04%, a recall of 91.35%, and an mAP@0.5 value of 97.62%, outperforming several comparable approaches reported in the literature. The system achieves an inference speed of 79.9 FPS with an average time of 12.5 ms per image on an NVIDIA RTX 3050 GPU, which enables its integration with an early warning module based on temporal persistence to automatically notify security personnel. Shopping centers, stadiums, and high-risk urban areas are proposed as target deployment scenarios, although their validation in these specific environments remains as future work, given that the current evaluation is limited to static images from the dataset used.
References
Ağdaş, M. T., & Gülséçen, S. (2022). Güvenlik Kameralarında Otomatik Silah ve Bıçak Tespit Sistemi: Karşılaştırmalı YOLO Modelleri. Avrupa Bilim ve Teknoloji Dergisi, 41, 16–22. https://doi.org/10.31590/ejosat.1163675 DOI: https://doi.org/10.31590/ejosat.1163675
Ağdaş, M. T., Türkoğlu, M., & Gülséçen, S. (2021). Deep neural networks based on transfer learning approaches to classification of gun and knife images. Sakarya University Journal of Computer and Information Sciences, 4(1), 131–141. https://doi.org/10.35377/saucis.04.01.891308 DOI: https://doi.org/10.35377/saucis.04.01.891308
Aljami, H. M., Alrowais, N. A., AlAwajy, A. M., Alhrgan, S. O., Aldwaani, R. A., Alsawadi, M. S., Saqib, N. U., Alam, S. S., & Alsubaie, R. (2026). Benchmarking YOLOv8 variants for object detection efficiency on Jetson Orin NX for edge computing applications. Computers, 15(2), 74. https://doi.org/10.3390/computers15020074 DOI: https://doi.org/10.3390/computers15020074
Alqahtani, D. K., Cheema, M. A., Rodriguez, M. A., & Toosi, A. N. (2024). A comprehensive evaluation of deep learning object detection models on heterogeneous edge devices. arXiv. https://doi.org/10.48550/arXiv.2409.16808
Arif, E., Shahzad, S. K., Iqbal, M. W., Jaffar, M. A., Alshahrani, A. S., Alghamdi A. (2022). Automatic detection of weapons in surveillance cameras using Efficient-Net. Computers, Materials & Continua, 72(3), 4615–4630. https://doi.org/10.32604/cmc.2022.027571 DOI: https://doi.org/10.32604/cmc.2022.027571
Bhatti, M. T., Khan, M. G., Aslam, M., & Fiaz, M. J. (2021). Weapon detection in real-time CCTV videos using deep learning. IEEE Access, 9, 34366–34382. https://doi.org/10.1109/ACCESS.2021.3059170 DOI: https://doi.org/10.1109/ACCESS.2021.3059170
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv. https://doi.org/10.48550/arXiv.2004.10934
Cantero, D., Esnaola-Gonzalez, I., Miguel-Alonso, J., & Jauregi, E. (2022). Benchmarking object detection deep learning models in embedded devices. Sensors, 22(11), 4205. https://doi.org/10.3390/s22114205 DOI: https://doi.org/10.3390/s22114205
Choudhry, N., Abawajy, J., Huda, S., & Rao, I. (2023). A comprehensive survey of machine learning methods for surveillance videos anomaly detection. IEEE Access, 11, 114680–114713. https://doi.org/10.1109/ACCESS.2023.3321800 DOI: https://doi.org/10.1109/ACCESS.2023.3321800
Cordova-Cardenas, R., Amor, D., & Gutiérrez, Á. (2025). Edge AI in practice: A survey and deployment framework for neural networks on embedded systems. Electronics, 14(24), 4877. https://doi.org/10.3390/electronics14244877 DOI: https://doi.org/10.3390/electronics14244877
DatasetNinja. (2024). Knife detection dataset. https://datasetninja.com/
Duong, H.-T., Le, V.-T., & Hoang, V. T. (2023). Deep learning-based anomaly detection in video surveillance: A survey. Sensors, 23(11), 5024. https://doi.org/10.3390/s23115024 DOI: https://doi.org/10.3390/s23115024
Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M. W., & Keutzer, K. (2021). A survey of quantization methods for efficient neural network inference. arXiv. https://doi.org/10.48550/arXiv.2103.13630 DOI: https://doi.org/10.1201/9781003162810-13
Grega, M., Matiolański, A., Guzik, P., & Leszczuk, M. (2016). Automated detection of firearms and knives in a CCTV image. Sensors, 16(1), 47. https://doi.org/10.3390/s16010047 DOI: https://doi.org/10.3390/s16010047
Jiang, P., Yang, X., Wan, Y., Zeng, T., Nie, M., & Liu, Z. (2024). DRBD-YOLOv8: A lightweight and efficient anti-UAV detection model. Sensors, 24(22), 7148. https://doi.org/10.3390/s24227148 DOI: https://doi.org/10.3390/s24227148
Kang, P., & Somtham, A. (2022). An evaluation of modern accelerator-based edge devices for object detection applications. Mathematics, 10(22), 4299. https://doi.org/10.3390/math10224299 DOI: https://doi.org/10.3390/math10224299
Lema, D. G., Usamentiaga, R., & García, D. F. (2024). Quantitative comparison and performance evaluation of deep learning-based object detection models on edge computing devices. Integration, 95, 102127. https://doi.org/10.1016/j.vlsi.2023.102127 DOI: https://doi.org/10.1016/j.vlsi.2023.102127
Meimetis, D., Daramouskas, I., Patrinopoulou, N., Lappas, V., & Kostopoulos, V. (2025). Comparative analysis of object detection models for edge devices in UAV swarms. Machines, 13(8), 684. https://doi.org/10.3390/machines13080684 DOI: https://doi.org/10.3390/machines13080684
Noever, D., & Noever, S. E. M. (2020). Knife and threat detectors. arXiv. https://doi.org/10.48550/arXiv.2004.03366
Olmos, R., Tabik, S., & Herrera, F. (2017). Automatic handgun detection alarm in videos using deep learning. arXiv. https://doi.org/10.48550/arXiv.1702.05147 DOI: https://doi.org/10.1016/j.neucom.2017.05.012
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. arXiv. https://doi.org/10.48550/arXiv.1506.02640 DOI: https://doi.org/10.1109/CVPR.2016.91
Shalash, O., Khatab, E., El-Agamy, A., Elmokadem, L., Abouelsaad, Y., Zaki, J., El-Sayed, M., & Said, H. (2026). Benchmarking YOLOv8–YOLOv12 for real-time object detection on single-board computers. Machine Learning and Knowledge Extraction, 8(7), 204. https://doi.org/10.3390/make8070204 DOI: https://doi.org/10.3390/make8070204
Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (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 DOI: https://doi.org/10.3390/make5040083
Thakur, A., Shrivastav, A., Sharma, R., Kumar, T., & Puri, K. (2024). Real-time weapon detection using YOLOv8 for enhanced safety. arXiv. https://doi.org/10.48550/arXiv.2410.19862
Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., & Ding, G. (2024). YOLOv10: Real-time end-to-end object detection. arXiv. https://doi.org/10.48550/arXiv.2405.14458 DOI: https://doi.org/10.52202/079017-3429
Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. arXiv. https://doi.org/10.48550/arXiv.2402.13616 DOI: https://doi.org/10.1007/978-3-031-72751-1_1
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Luis Fernando Juarez Peña, Dr. Manuel Ibarra Cabrera (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
