A comparison of machine learning methods for queue length detection

Abstract

Queues are formed by people waiting for a service in public institutions and they can be defined as orderly groups of people. Automatically counting the number of people waiting in a queue through video camera footage would provide these institutions with valuable information with regards to customer service quality. In this paper, our goal is to compare several machine learning methods for finding the total number of people waiting in a queue given video camera frames. We approached this problem as a regression task. We used a subset of the Collective Activity Dataset and compared three different methods. The first two methods used bounding box coordinates and orientations provided by the dataset, while the last method utilized the bounding box coordinates to extract feature maps from the frames using RoiAlign. The first method used XGBoost, while the latter methods used Convolutional Neural Networks (CNNs). Results show that the method using RoiAlign presents the best prediction performance in terms of mean squared error and mean absolute error, compared to other methods.

Keywords

• Queue length detection
• crowd counting
• machine learning

References

1. Wongun, C., Shahid, K. and Savarese, S., What are they doing?: Collective activity classification using spatio-temporal relationship among people, IEEE 12th Inter. Conf. on Comp. Vis. Wor. ICCV Work., (2009), 1282-1289, https://doi.org/10.1109/ICCVW.2009.5457461.
2. Chen, T. and Guestrin, C., XGBoost, Proc. of the 22nd ACM SIGKDD Int. Conf. on Know. Disc. and Data Min., (2016).
3. Yamashita, R., Nishio, M., Do, R. K. G. et al., Convolutional neural networks: an overview and application in radiology, Ins. Ima. 9, (2018), 611-629, https://doi.org/10.1007/s13244-018-0639-9.
4. He, K., Gkioxari, G., Dollar, P. and Girshick, R., Mask R-CNN, arXiv:1703.06870, (2018), https://doi.org/10.48550/arXiv.1703.06870.
5. Simonyan, K. and Zisserman, A., Very deep convolutional networks for large-scale image recognition, arXiv:1409:1556, (2015), https://doi.org/10.48550/arXiv.1409.1556.
6. Khan, M. A., Menouar, H. and Hamila, R., Revisiting crowd counting: State-of-the-art, trends, and future perspectives, Imag. and Vis. Comp., 129, (2023), 104597, https://doi.org/10.1016/j.imavis.2022.104597.
7. Sindagi, V. A. and Patel, V. M., A survey of recent advances in CNN-based single image crowd counting and density estimation, Pat. Rec. Let., 107, (2018), 3-16, https://doi.org/10.1016/j.patrec.2017.07.007.
8. Ruchika, R., Purwar, K. and Verma, S., Analytical study of YOLO and its various versions in crowd counting, Int. Data Com. Tech. and Int. of Thi., (2022), 975-989, https://doi.org/10.1007/978-981-16-7610-9 71.

9. Valencia, I. J. C., Dadios, E. P., Fillone, A. M., Puno, J. C. V., Baldovino, R. G. and Billones, R. K. C., Vision-based crowd counting and social distancing monitoring using tiny-YOLOv4 and DeepSORT, IEEE Int. Sma. Cit. Conf. (ISC2), (2021), 1-7, https://doi.org/10.1109/ISC253183.2021.9562868.
10. Muzamal, J. H., Tariq, Z. and Khan, U. G., Crowd counting with respect to age and gender by using faster R-CNN based detection, Int. Conf. on Appl. and Eng. Math. (ICAEM), (2019), 157-161, https://doi.org/10.1109/ICAEM.2019.8853723.
11. Akbar, N. and Jamal, E. C., Crowd counting using region convolutional neural networks, 8th Int. Conf. on Elec. Eng., Comp. Sci. and Info. (EECSI), (2021), 359-364, https://doi.org/10.23919/EECSI53397.2021.9624288.
12. Kingma, D. P. and Ba, J., Adam: A method for stochastic optimization, arXiv:1412.6980, (2017), https://doi.org/10.48550/arXiv.1412.6980.
13. People Queue Detection - ACTi Corporation, Available at: https://www.acti.com/technologies/people-queue-detection. [Accessed July 2023].
14. ACTi Corporation, Queue management whitepaper, ACTi Corporation, (2023). Available at: https://download.acti.com/?id=10618.
15. ShivamJalotra, Queue-Detection, (2023). Available at: https://github.com/jalotra/Queue-Detection. [Accessed July 2023].
16. Wu, J., Wang, L., Wang, L., Guo, J. and Wu, G., Learning actor relation graphs for group activity recognition, arXiv:1904.10117, (2019), https://doi.org/10.48550 /arXiv.1904.10117.