Restoranlarda Nesne Tespiti ve Bilgisayarlı Görü Tekniklerini Kullanarak Gerçek Zamanlı Masa Doluluk Tespiti

Abstract

Bu çalışma, restoran ortamında masa doluluğunu izlemek ve analiz etmek için nesne tespiti algoritmalarını kullanan yeni bir yaklaşım sunmaktadır. Yöntem, farklı renk, şekil ve boyutlardaki masaların özel bir görüntü veri setini oluşturmayı ve bu veri setini YOLO (You Look Only Once) algoritması ile eğitmeyi içermektedir. Sistem, masaları tespit etmek ve her masanın etrafındaki ilgili alanda algılanan kişi sayısına dayalı olarak doluluk ölçümleri hesaplamak üzere tasarlanmıştır. Ayrıca, masa doluluğu bilgisi, gelecekteki operasyonel planlama ve zamana bağlı analizleri kolaylaştırmak için zaman serisi veri seti formatında kaydedilmektedir. Ön testlerde, belirli bir zaman aralığı için kamera kayıtları incelenerek masada oturan kişi sayısı manuel olarak belirlenmiştir. Daha sonra, bu manuel sayım ile sistem tarafından gerçekleştirilen otomatik tespit karşılaştırılmıştır. Bu karşılaştırmanın sonuçları, sistemin belirtilen zaman aralığında masada oturan kişi sayısını doğru bir şekilde tespit ettiğini ortaya koymuştur. Bu veriler kaydedilip analiz edilerek, işletmelerin bilinçli operasyonel kararlar alması ve müşteri memnuniyetini artırmak için hizmet kalitesini iyileştirmesi sağlanabilir.

Keywords

• Nesne Tanıma
• Görüntü İşleme
• Bilgisayarlı Görü
• Yolov8

Thanks

Bu çalışmada kullanılan test ortamını sağlayan ve araştırmada kullanılan verilerin elde edilmesine katkı sağlayan Protel A.Ş.'ye teşekkürlerimizi sunarız.

Real-Time Table Occupancy Detection in Restaurants Using Object Detection and Computer Vision Techniques

Abstract

This work presents a new approach to monitoring and analyzing table occupancy in a restaurant setting using object detection algorithms. The method involves creating a custom image dataset of tables of different colors, shapes, and sizes, and training a model on this dataset using the YOLO (You Look Only Once) algorithm. The system is designed to detect tables and calculate occupancy measurements based on the number of people detected in the relevant area around each table. In addition, information including table occupancy is recorded via logging in a time series dataset format to facilitate future operational planning and time-based analysis. In the preliminary tests, the number of individuals seated at the table was manually determined by reviewing camera recordings for a specific time interval. Subsequently, a comparison was made between this manual count and the automated detection performed by the system. The results of this comparison revealed that the system accurately detected the number of people seated at the table during the specified time interval. By saving and analyzing this data, enterprises can make informed operational decisions and improve their service quality to increase customer satisfaction.

Keywords

• Object Detection
• Image Processing
• Computer Vision
• Yolov8

Thanks

We express our thanks to Protel A.Ş. for providing the test environment used in this study and contributing to the acquisition of the data used in the research.

References

1. B. Esposito, M. R. Sessa, D. Sica, and O. Malandrino, “Service innovation in the restaurant sector during COVID-19: Digital technologies to reduce customers' risk perception,” The TQM Journal, vol. 34, no. 7, pp. 134–164, 2022.
2. M. E. Rodríguez-López, J. M. Alcántara-Pilar, S. Del Barrio-García, and F. Muñoz-Leiva, “A review of restaurant research in the last two decades: A bibliometric analysis,” International Journal of Hospitality Management, vol. 87, p. 102387, 2020.
3. D. Marr and T. Poggio, “A computational theory of human stereo vision,” Proceedings of the Royal Society of London. Series B. Biological Sciences, vol. 204, no. 1156, pp. 301–328, 1979.
4. J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 6, pp. 679–698, 1986.
5. D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, 2004.
6. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2014, pp. 580–587.
7. S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” Advances in Neural Information Processing Systems, vol. 28, 2015.
8. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 25, 2012.

9. J. Redmon, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2016.
10. J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2017, pp. 7263–7271.
11. A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint, arXiv:2004.10934, 2020.
12. G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics YOLOv8,” 2023. [Online]. Available: https://github.com/ultralytics/ultralytics. [Accessed: Aug. 13, 2024].
13. D. B. L. Bong, K. C. Ting, and K. C. Lai, “Integrated approach in the design of car park occupancy information system (COINS),” IAENG International Journal of Computer Science, vol. 35, no. 1, 2008.
14. J. Halgaš and R. Pirník, “Monitoring of parking lot traffic using a video detection,” Acta Technica Corviniensis - Bulletin of Engineering, vol. 8, no. 3, pp. 17–20, 2015.
15. K. Pannerselvam, “Adaptive parking slot occupancy detection using vision transformer and LLIE,” in 2021 IEEE International Smart Cities Conference (ISC2), 2021.
16. M. Kročka, P. Dakić, and V. Vranić, “Extending parking occupancy detection model for night lighting and snowy weather conditions,” in 2022 IEEE Zooming Innovation in Consumer Technologies Conference (ZINC), 2022.
17. J. D. Ellis, S. Sam, and H. A. Smit, “An analysis of lightweight convolutional neural networks for parking space occupancy detection,” in 2021 IEEE International Symposium on Multimedia (ISM), 2021.
18. S. Goumiri, D. Benboudjema, and W. Pieczynski, “One convolutional layer model for parking occupancy detection,” in 2021 IEEE International Smart Cities Conference (ISC2), 2021.
19. S. Funck, N. Mohler, and W. Oertel, “Determining car-park occupancy from single images,” in Proc. IEEE Intelligent Vehicles Symposium, 2004.
20. S. Petersen, M. Sønderskov, H. Rasmussen, and J. Thomsen, “Establishing an image-based ground truth for validation of sensor data-based room occupancy detection,” Energy and Buildings, vol. 130, pp. 787–793, 2016.
21. L. Monti, C. Bianchi, A. Venturini, and M. Capra, “Edge-based transfer learning for classroom occupancy detection in a smart campus context,” Sensors, vol. 22, no. 10, p. 3692, 2022.
22. H. H. Nguyen, J. Li, and W. Ng, “Real-time detection of seat occupancy & hogging,” in Proc. 2015 International Workshop on Internet of Things Towards Applications, 2015.
23. Datenwissen. (2023). Smart Occupancy Monitoring with Computer Vision. Available online: https://datenwissen.com/nwarch-ai/occupancy-monitoring/. Accessed: June 23, 2025.
24. Traf-Sys. (2023). How Restaurants Can Use People Counting Systems. Available online: https://www.trafsys.com/how-restaurants-can-use-people-counting-systems/. Accessed: June 23, 2025.
25. G. van Rossum and F. L. Drake, Python 3 Reference Manual, Scotts Valley, CA, USA: CreateSpace, 2009. [Online]. Available: http://www.python.org.. Accessed: June 23, 2025
26. G. Bradski, “The OpenCV library,” Dr. Dobb's Journal of Software Tools, 2000.
27. D. Tzutalin, LabelImg. Git code, 2015. [Online]. Available: https://github.com/HumanSignal/labelImg.
28. W. Rawat and Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural Computation, vol. 29, no. 9, pp. 2352–2449, 2017.
29. J. Terven, D. M. Córdova-Esparza, and J. A. Romero-González, “A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680–1716, 2023.
30. T. Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, and C. L. Zitnick, “Microsoft COCO: Common objects in context,” in Computer Vision – ECCV 2014: Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland, Sept. 6–12, 2014, Part V, pp. 740–755, Springer International Publishing.
31. M. A. Schwarz, “Linux job scheduling,” Linux Journal, vol. 2000, no. 77es, p. 8-es, 2000.
32. J. Flask documentation, Flask. [Online]. Available: https://flask.palletsprojects.com/en/stable/. [Accessed: Dec. 29, 2024].
33. E. S. Gardner Jr, “Exponential Smoothing: The State of the Art—Part II,” International Journal of Forecasting, vol. 22, no. 4, pp. 637–666, 2006.
34. S. J. Rigatti, “Random Forest,” Journal of Insurance Medicine, vol. 47, no. 1, pp. 31–39, 2017.