Abstract
According to the application scenarios of the size of the human flow in different consumption places, to solve the problem of crowd detection, distance estimation between crowds and the inability to monitor and calculate the human flow in real time, this paper designs a real-time crowd detection scheme for application scenarios where consumers pay attention to the size of the human flow in consumption places. The main use of the YOLO algorithm with the Darknet53 network as the main network is to separate pedestrians from the background. Pedestrians’ central two-dimensional coordinates are converted into three-dimensional coordinates, realizing crowd detection and apart from the distance estimation of crowds, real-time monitoring of current regional traffic and flow density, and solving the problem of being unable to monitor and calculate people in real time. It can be applied to many aspects, such as shop rating, traffic control and flow control of scenic spots. Existing monitors are affected by different lights and cannot provide accurate data. In addition, the processing algorithm of this scheme is stable and accurate, and preprocessing is performed before judging the human flow and the position of the human body to reduce the interference of light. This scheme has the performance of real-time monitoring and calculation through experimental verification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
**gcheng, Z., **nru, F.U., Zongkai, Y., et al.: UAV detection and identification in the Internet of Things. In: 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), pp. 1499–1503. IEEE (2019)
Wenxuan, D., Hongtao, L., Guozhu, L., et al.: A review of deep convolution algorithms for object detection [J/OL]. Comput. Sci. Explor. 1–20 [2022–02–07]
Yang, Z., Wang, H., Liu, C.: Traffic monitoring method based on wireless perception and integration of learning. Comput. Eng. Des. Lancet (11), 3243–3249 (2022). https://doi.org/10.16208/j.issn1000-7024.2022.11.032
Cai,J., Wang, S., Gan, X., Wang, L.: Traffic monitoring system design and implementation based on LabVIEW. J. Tonghua Normal Univ. J. lancet (10), 67-722022). https://doi.org/10.13877/j.carolcarrollnkicn22-1284.2022.10.011
Liu, X., et al.: Development of intelligent analysis system for human flow Monitoring and query based on photoelectric sensing. Phys. Eng. 32(04), 218–223 (2022). (in Chinese)
Chen, J., Yantao, Q., Feng, Y., Fu, S., Wang, L., Fan, C.: Human flow monitoring method with millimeter wave Radar based on dual time point detection. Telecommun. Technol. 202, 62(11), 1593–1599
king inside. Traffic monitoring method based on the CSI research. Nanchang aviation university (2021). https://doi.org/10.27233/dcnki.GNCHC.2021.000293
Liao, J., Zong, F.: Traffic monitoring system based on deep learning study. J. Electron. (9), 54–55 + 81 (2021). https://doi.org/10.16589/j.carolcarrollnkicn11-3571/tn.2021.09.017
Wang, C., Shi, G., Chen, T., Liu, D., Wang, Z., Zhou, S.: Traffic monitoring system based on OpenCV. Comput. Knowl. Technol. (7), 235–236+241 (2021). https://doi.org/10.14004/j.carolcarrollnkiCKT.2021.0802
Wang, C., Yang, Y., Ren, X., Zhang, X.: Indoor traffic monitoring system design . Autom. Instr. 33(09) 6, 49–51 (2018). https://doi.org/10.16086/j.carolcarrollnki. issn1000–0380.2018020013
Shi, Y., Chang, C., Liu, X., et al.: Advances in calibration methods of internal and external parameters of planar array cameras. Laser Optoelectron. Progress, 58, 707(24), 9–29 (2021)
Jia Shi-na. The small target detection algorithm based on improved YOLOv5 research. Nanchang university (2022). 10.27232/,dc nki. Gnchu. 2022.004449
Huang. Target detection based on deep learning applied research. Nan**g university of posts and telecommunications (2022). https://doi.org/10.27251/dcnki.GNJDC.2022.001250
Zhu, J., Feng, F., Shen, B.: People counting and pedestrian flow statistics based on convolutional neural network and recurrent neural network. In: 2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC) (Nan**g, China, 18–20 May 2018), pp. 993–998 (2018)
Wu, D., Wang, J., Li, B., Guo, T.: Large crowd count based on improved surf algorithm. J. **’an Univ. Sci. Technol. 27, 650–655 (2015)
Mizutani, M., Uchiyama, A., Murakami, T., Abeysekera, H., Higashino, T.: Towards people counting using Wi-Fi CSI of mobile devices. In: 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) (23–27 March 2020), pp. 1–6 (2020)
He, C.T., Zhu, M.: No-reference face image quality assessment based on deep learning for mobile devices. J. Chin. Mini-Micro Comput. Syst. 40(02), 407–412 (2019)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, X., Wang, Y., Xu, Y., Wang, T. (2023). People Flow Monitoring Based on Deep Learning. In: Yu, Z., et al. Data Science. ICPCSEE 2023. Communications in Computer and Information Science, vol 1880. Springer, Singapore. https://doi.org/10.1007/978-981-99-5971-6_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-5971-6_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5970-9
Online ISBN: 978-981-99-5971-6
eBook Packages: Computer ScienceComputer Science (R0)