Nothing Special   »   [go: up one dir, main page]
Top > JACIII > Reclining Public Chair Behavior Detection Based on Improved YO ...

single-jc.php

JACIII Vol.27 No.6 pp. 1175-1182
doi: 10.20965/jaciii.2023.p1175
(2023)

Research Paper:

Views over last 60 days: 219

Reclining Public Chair Behavior Detection Based on Improved YOLOv5

Liu-Ying Zhou*, Dong Wei*,†, Yi-Bing Ran**, Chen-Xi Liu*, Si-Yue Fu*, and Zhi-Yi Ren*

*School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture
No.15 Yongyuan Road, Huangcun Town, Daxing District, Beijing 102616, China

†Corresponding author

**Siemens Ltd., China
No.7 Wangjing Zhonghuan South Road, Chaoyang District, Beijing 100102, China

Received:
March 12, 2023
Accepted:
August 3, 2023
Published:
November 20, 2023
Creative Commons License
Keywords:
YOLOv5, object detection, reclining public chair, deep learning
Abstract

This study proposes an object detection algorithm based on the improved YOLOv5 network for the uncivilized behavior of reclining public chair, which often occurs in cities. The current object detection field is studied by a single object. For the behavior of a lying public chair, the object to be measured is composed of two parts: the chair and the human posture jointly. Furthermore, the features of the object will show a large variability under different shooting angles, so the model’s ability to extract features of the object is extremely important. This paper incorporates the Ghost module based on the YOLOv5 network to enable the model to learn more object features. The Ghost makes the neural network lighter by using linear convolution instead of nonlinear convolution, and its generated redundant features can help the model learn more object features and improve the model performance. In addition, this paper uses a new loss function EIoU to replace the original loss function CIoU. By comparison, EIoU solves the problem that CIoU fails in penalty terms under specific conditions. EIoU enables the model to converge faster and better. After experimental validation on the test set, it is shown that the improved YOLO network improves F1 by 3.5% and mAP by 4.2% compared to the original algorithm.

Cite this article as:
L. Zhou, D. Wei, Y. Ran, C. Liu, S. Fu, and Z. Ren, “Reclining Public Chair Behavior Detection Based on Improved YOLOv5,” J. Adv. Comput. Intell. Intell. Inform., Vol.27 No.6, pp. 1175-1182, 2023.
Data files:
References
  1. [1] L.-Y. Zhou et al., “Detection of public chair uncivilized lying behavior based on YOLOv5,” 10th Int. Symp. on Computational Intelligence and Industrial Applications (ISCIIA2022), A2-5, 2022.
  2. [2] D. Tian et al., “The cooperative vehicle infrastructure system based on machine vision,” Proc. of the 6th ACM Symp. on Development and Analysis of Intelligent Vehicular Networks and Applications (DIVANet’17), pp. 85-89, 2017. https://doi.org/10.1145/3132340.3132347
  3. [3] P. F. Felzenszwalb et al., “Object detection with discriminatively trained part-based models,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.32, No.9, pp. 1627-1645, 2010. https://doi.org/10.1109/TPAMI.2009.167
  4. [4] M. Drożdż and T. Kryjak, “FPGA implementation of multi-scale face detection using HOG features and SVM classifier,” Image Processing & Communications, Vol.21, No.3, pp. 27-44, 2016.
  5. [5] R. Girshick, “Fast R-CNN,” 2015 IEEE Int. Conf. on Computer Vision (ICCV), pp. 1440-1448, 2015. https://doi.org/10.1109/ICCV.2015.169
  6. [6] S. Ren et al., “Faster R-CNN: Towards real-time object detection with region proposal networks,” Proc. of the 28th Int. Conf. on Neural Information Processing Systems (NIPS’15), Vol.1, pp. 91-99, 2015.
  7. [7] K. He et al., “Mask R-CNN,” 2017 IEEE Int. Conf. on Computer Vision (ICCV), pp. 2980-2988, 2017. https://doi.org/10.1109/ICCV.2017.322
  8. [8] J. Redmon et al., “You only look once: Unified, real-time object detection,” 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016. https://doi.org/10.1109/CVPR.2016.91
  9. [9] J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 6517-6525, 2017. https://doi.org/10.1109/CVPR.2017.690
  10. [10] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv: 1804.02767, 2018. https://doi.org/10.48550/arXiv.1804.02767
  11. [11] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv: 2004.10934, 2020. https://doi.org/10.48550/arXiv.2004.10934
  12. [12] W. Liu et al., “SSD: Single Shot MultiBox Detector,” Proc. of the 14th European Conf. on Computer Vision (ECCV 2016), Part 1, pp. 21-37, 2016. https://doi.org/10.1007/978-3-319-46448-0_2
  13. [13] Z. Li and F. Zhou, “FSSD: Feature fusion single shot multibox detector,” arXiv: 1712.00960, 2017. https://doi.org/10.48550/arXiv.1712.00960
  14. [14] Z. Shen et al., “DSOD: Learning deeply supervised object detectors from scratch,” 2017 IEEE Int. Conf. on Computer Vision (ICCV), pp. 1937-1945, 2017. https://doi.org/10.1109/ICCV.2017.212
  15. [15] C.-Y. Fu et al., “DSSD: Deconvolutional single shot detector,” arXiv: 1701.06659, 2017. https://doi.org/10.48550/arXiv.1701.06659
  16. [16] I. R. S. Evangelista et al., “Detection of Japanese quails (Coturnix japonica) in poultry farms using YOLOv5 and Detectron2 faster R-CNN,” J. Adv. Comput. Intell. Intell. Inform., Vol.26, No.6, pp. 930-936, 2022. https://doi.org/10.20965/jaciii.2022.p0930
  17. [17] S. Tanaka and Y. Inoue, “Outdoor human detection with stereo omnidirectional cameras,” J. Robot. Mechatron., Vol.32, No.6, pp. 1193-1199, 2020. https://doi.org/10.20965/jrm.2020.p1193
  18. [18] J. Xue et al., “Garbage detection using YOLOv3 in Nakanoshima Challenge,” J. Robot. Mechatron., Vol.32, No.6, pp. 1200-1210, 2020. https://doi.org/10.20965/jrm.2020.p1200
  19. [19] A. A. Wardana et al., “Development of a multi-user remote video monitoring system using a single mirror-drive pan-tilt mechanism,” J. Robot. Mechatron., Vol.34, No.5, pp. 1122-1132, 2022. https://doi.org/10.20965/jrm.2022.p1122
  20. [20] J. Wang and N. Yu, “UTD-YOLOv5: A Real-time underwater targets detection method based on attention improved YOLOv5,” arXiv: 2207.00837, 2022. https://doi.org/10.48550/arXiv.2207.00837
  21. [21] J. Aveiro et al., “Identification of binary neutron star mergers in gravitational-wave data using YOLO one-shot object detection,” arXiv: 2207.00591, 2022. https://doi.org/10.48550/arXiv.2207.00591
  22. [22] D. Huang et al., “Bone marrow cell recognition: Training deep object detection with a new loss function,” 2021 IEEE Int. Conf. on Imaging Systems and Techniques (IST), 2022. https://doi.org/10.1109/IST50367.2021.9651340
  23. [23] R. Rahman, Z. B. Azad, and M. B. Hasan, “Densely-populated traffic detection using YOLOv5 and non-maximum suppression ensembling,” Proc. of the Int. Conf. on Big Data, IoT, and Machine Learning (BIM 2021), pp. 567-578, 2022. https://doi.org/10.1007/978-981-16-6636-0_43
  24. [24] Y. Fan et al., “Application of improved YOLOv5 in aerial photographing infrared vehicle detection,” Electronics, Vol.11, No.15, Article No.2344, 2022. https://doi.org/10.3390/electronics11152344
  25. [25] K. Han et al., “GhostNet: More features from cheap operations,” 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1577-1586, 2020. https://doi.org/10.1109/CVPR42600.2020.00165
  26. [26] J. Hu et al., “PAG-YOLO: A portable attention-guided YOLO network for small ship detection,” Remote Sensing, Vol.13, No.16, Article No.3059, 2021. https://doi.org/10.3390/rs13163059

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Nov. 25, 2024