YOLOv11-based Real-Time Desk Tracking and Seating Time Analysis System
Abstract views: 25
/ 
PDF downloads: 9
Keywords:
Cafe Seating Time, Table Occupancy, Image Processing, Deep Learning, Live Dashboard, YOLOAbstract
This study proposes and develops an automated computer vision system for real-time table
occupancy monitoring and session duration analysis in cafes and similar venues. Addressing the
limitations of manual tracking methods, the system utilizes image processing techniques to analyze video
feeds from fixed cameras. The core methodology involves defining table regions of interest (ROI) and
employing object detection models, specifically YOLOv11, to identify patrons. By detecting the moments
of sitting and standing, the system calculates and records the exact occupancy duration per table. The
implemented architecture processes this data in real-time, storing session records in a database to support
both a live operational dashboard and historical reporting tools for business analytics. The results indicate
a high-performance human detection accuracy of 92% with the YOLOv11 model and demonstrate
successful system adaptability through automatic ROI calibration. While the prototype effectively
provides real-time tracking and actionable business intelligence, the study identifies avenues for future
enhancement. These include improving robustness to variable lighting conditions and refining the
algorithmic distinction between sitting and standing postures with more advanced behavioral models. The
research contributes a comprehensive framework that integrates theoretical foundations with practical
application, offering a scalable solution to improve operational efficiency and space utilization analysis in
the hospitality sector.
Downloads
References
E. Gürsel, S. Kalkan, and A. A. Alatan, "Vision-based estimation of the number of occupants using video cameras," Advanced Engineering Informatics, vol. 53, p. 101662, Aug. 2022, doi: 10.1016/j.aei.2022.101662.
F. A. Şenel and S. Tokat, "Görüntü işleme teknikleri kullanılarak bir ortamın insan sayısının tespiti," in Proc. 9th Elektrik-Elektronik ve Bilgisayar Mühendisliği Sempozyumu (ELECO), Bursa, Turkey, 2012, pp. I-224-I-228.
NetOP Teknoloji, "Akıllı mekân yönetimi: IoT tabanlı masa doluluk analizi," NetOP Teknoloji, Teknik Rapor NTR-2020-01, 2020.
(2023) G. Yang, X. Chang, Z. Wang, M. Yang, and X. Chen, "A serial dual-channel library occupancy detection system based on faster R-CNN," arXiv preprint arXiv:2306.16080. [Online]. Available: https://arxiv.org/abs/2306.16080
Lakshmi, G. S. P., Kumar, A., Raj, A., Wani, A. Y., & Sahana, S. (2023). Seat Sight: Public Space Occupancy Detection System. International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 12(6), Article 1206035. https://doi.org/10.15680/IJIRSET.2023.1206035
Zhenghan, L., Miyaji, H., & Yamamoto, H. (2024, July). Health monitoring system for desk workers using non-contact multi-sensors. In 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC) (pp. 1484-1487). IEEE.
Sundari, M. V. R., Islavath, N., Gopalda, S., Vajja, K. S., Anil, K., Aljawahry, H. M., ... & Sehgal, A. (2025, August). Café vision: Coffee shop sales and customer analytics. In AIP Conference Proceedings (Vol. 3263, No. 1, p. 150012). AIP Publishing LLC.
Choi, Y., Jang, M., Kim, Y. S., & Lee, S. (2011). Automated user behavior monitoring system for dynamic work environments. In DS 68-4: Proceedings of the 18th International Conference on Engineering Design (ICED 11), Impacting Society through Engineering Design, Vol. 4: Product and Systems Design, Lyngby/Copenhagen, Denmark, 15.-19.08. 2011 (pp. 230-237).
Vayadande, K., Deshpande, R., Deshpande, M., Chaudhary, P., Dhangar, A., & Dhangar, T. (2024, November). Tracking Barista Productivity and Customer Demographics. In 2024 5th International Conference on Data Intelligence and Cognitive Informatics (ICDICI) (pp. 891-898). IEEE.
Ojo, O., Kareem, M. K., Odunuyi, S., & UGWUNNA, C. (2022). An internet-of-things based real-time monitoring system for smart classroom. Journal of the Nigerian Society of Physical Sciences, 297-309.
Ningsih, Y. K., & Bonita, F. (2024). Design and development of a smart café system utilizing IoT for real-time remote monitoring and updates. Emitor: Jurnal Teknik Elektro, 191-199.
Ying, T., Zhu, D., Zou, Y., Huang, Y., & Zhao, P. (2023, February). Design of restaurant intelligent seat-seeking system based on ESP32. In 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) (pp. 1828-1834). IEEE.
W. Zhang, J. Calautit, P. W. Tien, Y. Wu, and S. Wei, "Deep learning models for vision-based occupancy detection in high-density indoor environments," Journal of Building Engineering, vol. 66, p. 111355, Oct. 2024, doi: 10.1016/j.jobe.2024.111355.
(2024) Ultralytics, "YOLO11 vs YOLOv8: Detailed Comparison," Ultralytics, [Online]. Available: https://docs.ultralytics.com/compare/yolo11-vs-yolov8/
(2025) Pallets Projects, "Flask Web Development Documentation," [Online]. Available: https://flask.palletsprojects.com/
(2025) Pallets Projects, "Jinja Template Engine for Python," [Online]. Available: https://jinja.palletsprojects.com/
(2025) Vanilla-JS contributors, "Vanilla-JS - An open-source vanilla JavaScript site,". [Online]. Available: http://vanilla-js.com
(2025) PostgreSQL Global Development Group, PostgreSQL 16.2 Documentation, [Online]. Available: https://www.postgresql.org/docs/current/
M. Zeng, A. Nguyen, B. Yu, and O. J. Mengshoel, "Convolutional neural networks for human activity recognition using mobile sensors," Mobile Information Systems, vol. 2014, Article ID 381574, 2014, doi: 10.1155/2014/381574.
(2024) Ultralytics, "YOLOv11 Documentation," Ultralytics. [Online]. Available: https://docs.ultralytics.com/models/yolo11/
