Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy

Muhammad Rizqi Sholahuddin; Maisevli Harika; Iwan Awaludin; Yunita Citra Dewi; Fachri Dhia Fauzan; Bima Putra Sudimulya; Vandha Pradiyasma Widarta

doi:10.15575/join.v8i2.1196

Authors

Muhammad Rizqi Sholahuddin Department of Computer and Informatics, Politeknik Negeri Bandung, Bandung, Indonesia
Maisevli Harika Department of Computer and Informatics, Politeknik Negeri Bandung, Bandung, Indonesia
Iwan Awaludin Department of Computer and Informatics, Politeknik Negeri Bandung, Bandung; Department of Mechanical Enginering, Politeknik Negeri Bandung, Bandung, Indonesia
Yunita Citra Dewi Department of Mechanical Enginering, Politeknik Negeri Bandung, Bandung, Indonesia
Fachri Dhia Fauzan Department of Computer and Informatics, Politeknik Negeri Bandung, Bandung, Indonesia
Bima Putra Sudimulya Department of Computer and Informatics, Politeknik Negeri Bandung, Bandung, Indonesia
Vandha Pradiyasma Widarta Department of Information System, Pukyong National University, Busan, Korea, Republic of

DOI:

https://doi.org/10.15575/join.v8i2.1196

Keywords:

YOLOv8, CCTV Surveillance, Model Pruning, Face Detection, Streamlit

Abstract

Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.

References

Majeed, F., Khan, F.Z., Iqbal, M.J., Nazir, M.: Real-Time Surveillance System based on Facial Recognition using YOLOv5. In: Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing, MAJICC 2021. Institute of Electrical and Electronics Engineers Inc. (2021)

Kwaghe, O.P., Gital, A.Y., Madaki, A.G., Abdulrahman, M.L., Yakubu, I.Z., Shima, I.S.: A Deep Learning Approach for Detecting Face Mask Using an Improved Yolo-V2 With Squeezenet. In: 2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022. Institute of Electrical and Electronics Engineers Inc. (2022)

Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. (2022)

Ultralytics: Ultralytics - YOLOv8, https://github.com/ultralytics/ultralytics

Purwita Sary, I., Ucok Armin, E., Andromeda, S., Engineering, E., Singaperbangsa Karawang, U.: Performance Comparison of YOLOv5 and YOLOv8 Architectures in Human Detection Using Aerial Images. Ultima Computing?: Jurnal Sistem Komputer. 15, (2023)

Reis, D., Kupec, J., Hong, J., Daoudi, A.: Real-Time Flying Object Detection with YOLOv8. (2023)

Li, Y., Fan, Q., Huang, H., Han, Z., Gu, Q.: A Modified YOLOv8 Detection Network for UAV Aerial Image Recognition. Drones. 7, (2023). https://doi.org/10.3390/drones7050304

Kuzlu, M., Catak, F.O., Sarp, S., Cali, U., Gueler, O.: A Streamlit-based Artificial Intelligence Trust Platform for Next-Generation Wireless Networks. In: Proceedings - 2022 IEEE Future Networks World Forum, FNWF 2022. pp. 94–97. Institute of Electrical and Electronics Engineers Inc. (2022)

Khorasani, M., Abdou, M., Hernández Fernández, J.: Streamlit Use Cases. In: Web Application Development with Streamlit. pp. 309–361. Apress (2022)

Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: Optimal Speed and Accuracy of Object Detection. (2020)

Lin, J.: MultiStream: A Simple and Fast Multiple Cameras Visual Monitor and Directly Streaming. (2022)

Li, M., Yeh, C.L., Lu, S.Y.: Real-time QoE monitoring system for video streaming services with adaptive media playout. International Journal of Digital Multimedia Broadcasting. 2018, (2018). https://doi.org/10.1155/2018/2619438

Castellano, G., Castiello, C., Mencar, C., IEEE Systems, M., IEEE Computational Intelligence Society, Institute of Electrical and Electronics Engineers: 2020 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS)?: conference proceedings?: Bari, Italy, 27-29 May 2020 (online). (2020)

Terven, J., Cordova-Esparza, D.: A Comprehensive Review of YOLO: From YOLOv1 and Beyond. (2023)

Van Rijthoven, M., Swiderska-Chadaj, Z., Seeliger, K., Van Der Laak, J., Ciompi, F.: You Only Look on Lymphocytes Once.

Powers, D.M.W., Ailab: EVALUATION: FROM PRECISION, RECALL AND F-MEASURE TO ROC, INFORMEDNESS, MARKEDNESS & CORRELATION. (2011)

Park, L., Park, L.A.F.: Bootstrap confidence intervals for Mean Average Precision Bootstrap confidence intervals for Mean Average Precision Bootstrap confidence intervals for Mean Average Precision Bootstrap confidence intervals for Mean Average Precision Bootstrap confidence intervals for Mean Average Precision. (2011)

Su, W., Yuan, Y., Zhu, M.: A relationship between the average precision and the area under the ROC curve. In: ICTIR 2015 - Proceedings of the 2015 ACM SIGIR International Conference on the Theory of Information Retrieval. pp. 349–352. Association for Computing Machinery, Inc. (2015)

Tan, L., Huangfu, T., Wu, L., Chen, W.: Comparison of RetinaNet, SSD, and YOLO v3 for real-time pill identification. BMC Med Inform Decis Mak. 21, (2021). https://doi.org/10.1186/s12911-021-01691-8

Nápoles-Duarte, J.M., Biswas, A., Parker, M.I., Palomares-Baez, J.P., Chávez-Rojo, M.A., Rodríguez-Valdez, L.M.: Stmol: A component for building interactive molecular visualizations within streamlit web-applications. Front Mol Biosci. 9, (2022). https://doi.org/10.3389/fmolb.2022.990846

Khorasani, M., Abdou, M., Fernández, J.H.: Web Application Development with Streamlit: Develop and Deploy Secure and Scalable Web Applications to the Cloud Using a Pure Python Framework. Apress Media LLC (2022)