Sistem Cerdas Pelacakan Individu Berbasis YOLO dan Deep SORT untuk Pengawasan Keamanan Kampus

Elvi Rahmi; Eva Yumami; Isna Yulia

doi:10.59061/jentik.v4i3.1541

Authors

Elvi Rahmi Politeknik Negeri Bengkalis
Eva Yumami Politeknik Negeri Bengkalis
Isna Yulia Politeknik Negeri Bengkalis

DOI:

https://doi.org/10.59061/jentik.v4i3.1541

Keywords:

Computer Vision, Deep SORT, Person Tracking, Smart Surveillance, YOLOv8

Abstract

Digital transformation in vocational higher education requires the integration of intelligent technology into campus security systems. This study develops an individual tracking system based on CCTV video using YOLOv8 for object detection and Deep SORT for identity tracking. The system detects people, assigns unique IDs, records movement automatically, and visualizes tracking data through a heatmap and an interactive Streamlit dashboard. Testing was conducted using an uploaded video and CCTV footage. The first scenario produced 1,371 detection records from 47 frames and 36 unique tracks, with an average confidence of 0.458. The CCTV scenario produced 715 records from 60 frames and 14 unique tracks, with an average confidence of 0.486. Overall evaluation yielded 97.9% precision, 100% recall, 99.0% F1-score, and 97.9% accuracy. The results show that the integration of YOLOv8 and Deep SORT can support consistent multi-object tracking and informative real-time visualization for data-driven campus security monitoring.

References

Direktorat Jenderal Pendidikan Vokasi. (2021). Peta jalan pendidikan vokasi 2021–2035. Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi Republik Indonesia.

Du, Y., Zhao, Z., Song, Y., Zhao, Y., Su, F., Gong, T., & Meng, H. (2023). StrongSORT: Make DeepSORT great again. IEEE Transactions on Multimedia, 25, 8725–8737. https://doi.org/10.1109/TMM.2023.3240881

Kumar, N., Goel, V., & Sharma, A. (2021). Object tracking and counting in a zone using YOLOv4, DeepSORT, and TensorFlow. International Journal of Engineering Research & Technology, 10(4), 156–162.

Liu, L., Hu, W., Li, T., & Yuan, B. (2025). Vehicle flow detection and tracking based on an improved YOLOv8n and ByteTrack framework. Information, 16(1), 13.

Luiten, J., Osep, A., Dendorfer, P., Torr, P. H. S., Geiger, A., Leal-Taixé, L., & Leibe, B. (2021). HOTA: A higher order metric for evaluating multi-object tracking. International Journal of Computer Vision, 129(2), 548–578. https://doi.org/10.1007/s11263-020-01375-2

Meinhardt, T., Kirillov, A., Leal-Taixé, L., & Feichtenhofer, C. (2022). TrackFormer: Multi-object tracking with transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8844–8854).

Razzok, M., Sulaiman, M., & Alani, R. (2023). Pedestrian detection and tracking system based on Deep-SORT, YOLOv5, and new data association metrics. Information, 14(4), 218.

Sharma, N., Baral, S., Paing, M. P., & Chawuthai, R. (2023). Parking time violation tracking using YOLOv8 and tracking algorithms. Sensors, 23(13), 5843. https://doi.org/10.3390/s23135843

Szeliski, R. (2022). Computer vision: Algorithms and applications (2nd ed.). Springer.

Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7464–7475).

Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In Proceedings of the IEEE International Conference on Image Processing (ICIP) (pp. 3645–3649).

Yadav, V., Prasad, A., & Kumar, R. (2023). Object detection and tracking using YOLOv8 and DeepSORT. ResearchGate. https://www.researchgate.net/publication/377677203

Yang, J., Zhang, H., & Wei, X. (2022). Video object tracking based on YOLOv7 and Deep SORT. ResearchGate. https://www.researchgate.net/publication/362252153_Video_object_tracking_based_on_YOLOv7_and_DeepSORT

Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022). ByteTrack: Multi-object tracking by associating every detection box. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer vision – ECCV 2022 (pp. 1–21). Springer. https://doi.org/10.1007/978-3-031-20047-2_1

Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021). FairMOT: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision, 129, 3069–3087. https://doi.org/10.1007/s11263-021-01513-4