lmplementasi YOLOv11 untuk Penghitungan Kerumunan Real-Time dalam Arsitektur Microservices pada Video CCTV

M.Sultonun  Naim; Salamun Rohman Nudin

doi:10.32664/smatika.v16i02.2378

Authors

M.Sultonun Naim Universitas Negeri Surabaya
Salamun Rohman Nudin Universitas Negeri Surabaya

DOI:

https://doi.org/10.32664/smatika.v16i02.2378

Keywords:

Computer Vision, Crowd Counting, Deep Learning, Microservices, YOLOv11

Abstract

The provision of accurate and easily accessible public information regarding the condition of urban parks remains a challenge in the management of public open spaces. People still do not have a system that allows them to monitor park crowd levels directly, making real-time observation of park conditions difficult. Previous studies on crowd counting have mainly focused on improving object detection performance, while the implementation of crowd monitoring systems as public information services remains limited. Therefore, this research integrates the YOLOv11 algorithm with a microservices architecture to provide real-time crowd information through a public park monitoring website. This research develops a park visitor counting information system based on computer vision using the YOLOv11 algorithm to detect and count crowds from CCTV video streams. The system is designed using a microservices architecture with the FastAPI framework to support real-time detection and data integration into the Surabaya park monitoring website. The research process involves several stages, including dataset preparation, data labeling using Roboflow, YOLOv11 model training, selection of the most optimal optimizer, and implementation of the system on the detection backend. The results show that the YOLOv11m model with the SGD optimizer achieved the best performance, obtaining an mAP@50 score of 92.76%, a recall value of 89.75%, and an F1-score of 90.07%. In addition, the system successfully performed real-time crowd detection and counting under various crowd density levels, lighting conditions, and CCTV camera angles.

References

[1] M. K. Kadri, R. Armanda, G. Purba, dan Y. Fitriani, “Kesesuaian Pengadaan Ruang Terbuka Hijau Taman Kota Berdasarkan Standar Minimal Pelayanan Penduduk di Kota Surabaya Suitability of City Park Green Open Space Procurement Based on Minimum Standards of Resident Services in the City of Surabaya,” vol. 02, no. 01, hal. 95–99, 2023, doi: 10.35718/compact.v2i1.853.

[2] D. D. Saputri, “Penilaian Fungsi Taman Kota Sebagai Ruang Terbuka Publik di Kota Surabaya,” vol. 13, no. 2, hal. 40–47, 2018, doi: 10.12962/j2716179X.v13i2.7113.

[3] T. Abdul, R. Shyaa, dan A. A. Hashim, “Enhancing real human detection and people counting using YOLOv8,” vol. 00061, hal. 1–8, 2024, doi: https://doi.org/10.1051/bioconf/20249700061.

[4] S. Hassan, “Systematic scalability analysis for microservices granularity adaptation design decisions,” no. December 2021, hal. 1378–1401, 2022, doi: 10.1002/spe.3069.

[5] F. Aldi, I. Nozomi, dan S. Rahmawati, “Real-Time Human Detection and Counting System Based on YOLOv11 for Smart Campus Environment,” JET-UMY, vol. 9, no. 2, hal. 64–73, 2025, doi: 10.18196/jet.v9i2.29213.

[6] A. A. Lubis, A. Prasasta, dan D. A. Sari, “Towards Efficient Crowd Counting and Behavior Analysis Using,” vol. 4, no. 1, hal. 35–47, 2025, doi: https://doi.org/10.63876/ijtm.v4i1.128.

[7] M. Khanam, R , Hussain, “YOLOV11: AN OVERVIEW OF THE KEY ARCHITECTURAL ENHANCEMENTS,” vol. 2024, hal. 1–9, 2024, doi: 10.48550/arXiv.2410.17725.

[8] N. Dwivedi, D. Katiyar, dan G. Goel, “A Comparative Study of Various Software Development Life Cycle ( SDLC ) Models,” IJRESM, vol. 5, no. 3, hal. 141–144, 2022, doi: 10.51316/ijresm.2022.1881.

[9] J. R. Terven dan D. M. Cordova-esparaza, “A COMPREHENSIVE REVIEW OF YOLO: FROM YOLOV1 TO YOLOV8 AND BEYOND,” Mach. Learn. Knowl. Extr., hal. 1–27, 2023, doi: 10.3390/make5040083.

[10] G. Aurelia, N. Lubis, R. Purnamasari, dan K. Saleh, “Designing a Real-Time TOXMAP Backend Based on FastAPI and Firebase for B3 Waste,” vol. 8, no. 1, 2025, doi: 10.32877/bt.v8i1.2888.

[11] F. Ciaglia, F. S. Zuppichini, P. Guerrie, M. Mcquade, dan J. Solawetz, “Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark,” 2022, doi: 10.48550/arXiv.2211.13523.

[12] M. E. Khan, “A Comparative Study of White Box , Black Box and Grey Box Testing Techniques,” IJACSA, vol. 3, no. 6, hal. 12–15, 2012, doi: 10.14569/IJACSA.2012.030603.

[13] F. Zufari dan Y. Irawan, “Enhancing Real Time Crowd Counting Using YOLOv8 Integrated with Microservices Architecture for Dynamic Object Detection in High Density Environments,” KESATRIA, vol. 6, no. 1, 2025, doi: 10.30645/kesatria.v6i1.575.

[14] S. A. Rumapea dan M. F. Fawwaz, “Implementation of YOLOv8 in Object Recognition Systems for Public Area Security in Kebun Raya Bogor,” Ultim. J. Tek. Inform., vol. 17, no. 1, hal. 1–10, 2025, doi: 10.31937/ti.v17i1.4133.

[15] N. Sujana, M. M. Mutoffar, dan A. A. Haryanto, “ANALISIS KINERJA YOLOV8 OPTIMALISASI ROBOFLOW UNTUK DETEKSI EKSPRESI WAJAH EMOSIONAL DENGAN MACHINE LEARNING,” NARATIF, vol. 06, no. 02, hal. 115–124, 2024, doi: 10.53580/naratif.v6i2.292.

[16] C. Shorten dan T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, 2019, doi: 10.1186/s40537-019-0197-0.

[17] J. Meng, Y. Li, Z. Li, dan W. Xie, “TARGET DETECTION FOR WEEDING ROBOTS BASED ON IMPROVED YOLOv11 MODELS,” engenhariaagricola, vol. 4430, 2025, doi: 10.1590/1809-4430-eng.agric.v45e20250032/2025.

[18] T. H. Pinem dan Z. P. Putra, “Evaluasi Kinerja Algoritma Klasifikasi Deep Learning dalam Prediksi Diabetes,” vol. 17, no. 1, hal. 17–28, 2025, doi: 10.22441/fifo.2025.v17i1.003.

[19] C. S. B. Sakti dan I. Hermawan, “IMPLEMENTASI ARSITEKTUR MICROSERVICE PADA BACK END SISTEM INFORMASI I ATLANTAS BERBASIS WEBSITE,” J. Teknol. terpadu, vol. 6, no. 2, hal. 96–104, 2020, doi: 10.54914/jtt.v6i2.281.

[20] S. Atmojo, R. Utami, S. Dewi, dan N. Widhiyanta, “Implementasi Sistem-informasi DesaBerbasisArsitektur Microservices,” SMATIKA STIKI Inform. J., vol. 12, no. 1, hal. 55–66, 2022, doi: https://doi.org/10.32664/smatika.v12i01.658.

[21] J. Chen, “Model Algorithm Research based on Python Fast API,” vol. 3, no. 9, hal. 7–10, 2023, doi: 10.54691/fse.v3i9.5591.

[22] K. Boudjit dan N. Ramzan, “Human detection based on deep learning YOLO-v2 for real-time UAV applications Human detection based on deep learning YOLO-v2 for real-time,” J. Exp. Theor. Artif. Intell., vol. 00, no. 00, hal. 1–18, 2021, doi: 10.1080/0952813X.2021.1907793.

[23] R. Shi, T. Li, dan Y. Yamaguchi, “An attribution-based pruning method for real-time mango detection with YOLO network,” Comput. Electron. Agric., vol. 169, no. July 2019, hal. 105214, 2020, doi: 10.1016/j.compag.2020.105214.

[24] C. Wang dan H. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” 2020, doi: 10.48550/arXiv.2004.10934.

[25] H. T. Ngoc, K. H. Nguyen, H. K. Hua, H. Vu, N. Nguyen, dan L. Quach, “Optimizing YOLO Performance for Traffic Light Detection and End-to-End Steering Control for Autonomous Vehicles in Gazebo-ROS2,” vol. 14, no. 7, hal. 475–484, 2023, doi: 10.14569/IJACSA.2023.0140752.

[26] A. Syahputra, M. F. Azhary, A. Binti, A. Rahman, dan A. Saad, “Occupancy Measurement in Under-Actuated Zones : YOLO-based Deep Learning Approach,” vol. 15, no. 2, hal. 757–769, 2024, doi: 10.14569/IJACSA.2024.0150277.

[27] S. Woo, J. Park, J. Lee, dan S. Kweon, “CBAM: Convolutional Block Attention Module,” Eur. Conf. Comput. Vis., hal. 3–19, 2018, doi: 10.1007/978-3-030-01234-2_1.

[28] C. Guo et al., “Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement,” Conf. Comput. Vis. Pattern Recognit., hal. 1780–1789, 2020, doi: 10.1109/CVPR42600.2020.00343.

[29] W. Liu, M. Salzmann, P. Fua, dan D. L. Epfl, “Context-Aware Crowd Counting,” Conf. Comput. Vis. Pattern Recognit., hal. 5094–5103, 2019, doi: 10.1109/CVPR.2019.00524.