Article Details

Abstract

Currently, the construction of smart campus in China is booming, but there are still deficiencies in the campus waiting point crowd counting. Due to the overlapping recognition targets and the complex background environment, it is difficult to balance the recognition speed and accuracy. Aiming at this problem, this paper proposes a method based on CNN and YOLOv8 models. Through deep exploration and analysis of the innovative points of YOLOv8 model, a campus waiting point crowd counting system based on YOLOv8 is designed. Finally, the average accuracy of the model on the self-designed dataset reaches 87.4%. In addition, combined with visual design, it is integrated into the system to realize a relatively accurate counting of waiting crowd, which provides help to solve the problem of crowd counting at campus waiting points.

Keywords

crowd counting; CNN; YOLOv8; Deep Learning; Object Detection

References

1. [1] BHATT C，KUKRETI A，PRATAP A，et al. Deep Learning for Crowd Counting: Addressing Crowd Density with Advanced Methods [C]//2024 Second International Conference on Advances in Information Technology （ICAIT）.Chikkamagaluru：IEEE，2024：1-5.
2. [2] GUO W Y，YANG S P，HUANG Y Z，et al. CrowdTrans: Learning Top-down Visual Perception for Crowd Counting by Transformer [J].Neurocomputing，2024，587：127650.
3. [3] JIANG X H，ZHANG L，XU M L，et al. Attention Scaling for Crowd Counting [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）.Seattle：IEEE，2020：4705-4714.
4. [4] Li Miao, Chen Nuo, An Wei, etc Dual view fusion detection method for event camera detection of unmanned aerial vehicles [J]. Optoelectronic Engineering, 2024, 51 (11): 49-59
5. [5] YU J L，YIN H Z，LI J D，et al. Enhancing Social Recommendation with Adversarial Graph Convolutional Networks [J].IEEE Transactions on Knowledge and Data Engineering，2022，34（8）：3727-3739.
6. [6] TONG M L，FAN L Y，NAN H，et al. Smart Camera Aware Crowd Counting via Multiple Task Fractional Stride Deep Learning [J].Sensors，2019，19（6）：1346.
7. [7] JIANG X H，ZHANG L，ZHANG T Z，et al. Density-aware Multi-task Learning for Crowd Counting [J].IEEE Transactions on Multimedia，2021，23：443-453.
8. [8] HU Q，LI G P. Crowd Counting Study Based on Low Light Image Enhancement [C]//2023 4th International Conference on Computer Engineering and Application （ICCEA）.Hangzhou：IEEE，2023：792-796.
9. [9] KHAN D，HO I W-H. CrossCount: Efficient Device-free Crowd Counting by Leveraging Transfer Learning [J].IEEE Internet of Things Journal，2023，10（5）：4049-4058.
10. [10] Zhao Haoyu Research on Dense Crowd Counting Algorithm Based on Multiscale Neural Networks and Meta Learning [D]. Nanchang: Nanchang University, 2022
11. [11] Yao Zhaoliang Research on Crowd Counting Algorithm in Dense Scenes [D]. Nanjing: Nanjing University of Science and Technology, 2021

Funding

Guizhou University Student Innovation and Entrepreneurship Training Program (gzusc2023056)

About the authors

Chen Jun (2002-), male, Han ethnicity, from Chishui, Guizhou, undergraduate studies, research direction: object detection.