Geodesic
Car parking detection in images by using a semi-supervised modified YOLOv5 model
Journal of the Belarusian State University. Mathematics and Informatics, Tome 3 (2023), pp. 72-81.

Voir la notice de l'article provenant de la source Math-Net.Ru

The problem of car parking detection in images attracts the attention of many researchers. In this task, it is quite difficult to identify rectangular, continuous parking spaces in all kinds of city images under different weather conditions, combining the low-light environment and the system’s low cost with high detection accuracy. In this paper, we propose a modified version of the YOLOv5 model joined with semi-supervised learning that allows us to detect parking lots in any complex scene, independent of parking space lines and parking environments. Due to the combination of the nature of semi-supervised learning and the high accuracy of supervised learning models, the modified version of YOLOv5 model permits to use very little labeled data and a large amount of unlabeled data. It can significantly reduce training time while maintaining recognition accuracy. Compared with other neural network models, the modified version of YOLOv5 model has the characteristics of fast training speed, persistent operation, small model size, and high model precision and recall values.
Keywords: Car parking detection; semi-supervised learning; YOLOv5 neural network. 
@article{BGUMI_2023_3_a6,
     author = {Zh. Shuai and G. Ma and Ya. Weichen and F. Zuo and S. V. Ablameyko},
     title = {Car parking detection in images by using a semi-supervised modified {YOLOv5} model},
     journal = {Journal of the Belarusian State University. Mathematics and Informatics},
     pages = {72--81},
     publisher = {mathdoc},
     volume = {3},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/BGUMI_2023_3_a6/}
}
TY  - JOUR
AU  - Zh. Shuai
AU  - G. Ma
AU  - Ya. Weichen
AU  - F. Zuo
AU  - S. V. Ablameyko
TI  - Car parking detection in images by using a semi-supervised modified YOLOv5 model
JO  - Journal of the Belarusian State University. Mathematics and Informatics
PY  - 2023
SP  - 72
EP  - 81
VL  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/BGUMI_2023_3_a6/
LA  - ru
ID  - BGUMI_2023_3_a6
ER  - 
%0 Journal Article
%A Zh. Shuai
%A G. Ma
%A Ya. Weichen
%A F. Zuo
%A S. V. Ablameyko
%T Car parking detection in images by using a semi-supervised modified YOLOv5 model
%J Journal of the Belarusian State University. Mathematics and Informatics
%D 2023
%P 72-81
%V 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/BGUMI_2023_3_a6/
%G ru
%F BGUMI_2023_3_a6
Zh. Shuai; G. Ma; Ya. Weichen; F. Zuo; S. V. Ablameyko. Car parking detection in images by using a semi-supervised modified YOLOv5 model. Journal of the Belarusian State University. Mathematics and Informatics, Tome 3 (2023), pp. 72-81. http://geodesic.mathdoc.fr/item/BGUMI_2023_3_a6/

[1] M. Alam, D. Moroni, G. Pieri, M. Tampucci, M. Gomes, J. Fonseca, “Real-time smart parking systems integration in distributed ITS for smart cities”, Journal of Advanced Transportation, 2018 (2018), 1485652 | DOI

[2] F. Faheem, S. A. Mahmud, G. M. Khan, M. Rahman, H. Zafar, “A survey of intelligent car parking system”, Journal of Applied Research and Technology, 11(5) (2013), 714–726 | DOI

[3] R. Yusnita, F. Norbaya, N. Basharuddin, “Intelligent parking space detection system based on image processing”, International Journal of Innovation, Management and Technology, 3(3) (2012), 232–235 | DOI

[4] Ching-Chun. Huang, Hoang. Vu, Yi-Ren. Chen, “A multiclass boosting approach for integrating weal classifiers in parking space detection”, IEEE International conference on consumer electronics, IEEE, 2015, 314–315 | DOI

[5] R. Bohush, P. Yarashevich, S. Ablameyko, T. Kalganova, “Extraction of image parking spaces in intelligent video surveillance systems”, Machine Graphics and Vision, 27(1–4) (2018), 47–62 | DOI

[6] Hai. Wang, Yljie. Yu, Yingfeng. Cai, Xiaobo. Chen, Long. Chen, Qingchao. Liu, “A comparative study of state-of-the-art deep learning algorithms for vehicle detection”, IEEE Intelligent Transportation Systems Magazine, 11(2) (2019), 82–95 | DOI

[7] D. Acharya, W. Yan, K. Khoshelham, “Real-time image-based parking occupancy detection using deep learning”, Proceedings of the 5th annual conference, 2018, 33–40

[8] J. Nyambal, R. Klein, “Automated parking space detection using convolutional neural networks”, arXiv:2106.07228v1, 2021, 6 | DOI

[9] A. A. Naufal, C. Fatichah, N. Suciati, “Preprocessed mask RCNN for parking space detection in smart parking systems”, International Journal of Intelligent Engineering and Systems, 13(6) (2020), 255–265 | DOI

[10] J. Ahmad, Z. Lewis, P. Duraisamy, T. McDonald, “Parking lot monitoring using MRCNN”, 10th International conference on computing, communication and networking technologies, IEEE, 2019, 10–13 | DOI

[11] T. Agrawal, S. Urolagin, “Multi-angle parking detection system using mask R-CNN”, BDET-2020. Proceedings of the 2nd International conference on big data engineering and technology, Association for Computing Machinery, New York, 2020, 76–80 | DOI

[12] Guo. Yucheng, Shi. Hongtao, “Automatic parking system based on improved neural network algorithm and intelligent image analysis”, Computational Intelligence and Neuroscience, 2021 (2021), 4391864 | DOI

[13] Y. Miao, F. Liu, T. Hou, L. Liu, Y. Liu, “A nighttime vehicle detection method based on YOLOv3”, 2020 Chinese automation congress, IEEE, 2020, 6617–6621 | DOI

[14] Hai. Wang, Xinyu. Lou, Yingfeng. Cai, Yicheng. Li, Long. Chen, “Real-time vehicle detection algorithm based on vision and lidar point cloud fusion”, Journal of Sensors, 2019 (2019), 8473980 | DOI

[15] D. P. Carrasco, H. A. Rashwan, M. García, D. Puig, “T-YOLO: tiny vehicle detection based on YOLO and multi-scale convolutional neural networks”, IEEE Access, 11 (2023), 22430–22440 | DOI

[16] H. Bura, N. Lin, N. Kumar, S. Malekar, S. Nagaraj, K. Liu, “An edge based smart parking solution using camera networks and deep learning”, 2018 IEEE International conference on cognitive computing, IEEE, 2018, 17–24 | DOI

[17] M. Uzar, S. Ozturk, O. C. Bayrak, T. Arda, N. T. Ocalan, “Performance analysis of YOLO versions for automatic vehicle detection from UAV images”, Advanced Remote Sensing Journal, 1(1) (2021), 16–30

[18] F. F. F, Detailed YOLOv5 model framework [Internet], Lezhi Network Technology Co, Beijing, 2021 | DOI

[19] X. Zhu, A. B. Goldberg, Introduction to semi-supervised learning, Springer, Cham, 2009, XII+116 pp. | DOI | MR

[20] C. Rosenberg, M. Hebert, H. Schneiderman, “Semi-supervised self-training of object detection models”, Seventh IEEE workshops on applications of computer vision, IEEE, 2005, 29–36 | DOI

[21] Dong-Hyun. Lee, “Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks”, ICML 2013 workshop. challenges in representation learning. Volume 3, 2013, 2–4

[22] K. Sohn, Z. Zhang, C-L. Li, H. Zhang, C-Y. Lee, T. Pfister, “A simple semi-supervised learning framework for object detection”, arXiv:2005.04757, 2020, 15 | DOI | MR | Zbl

[23] K. Janocha, W. M. Czarnecki, “On loss functions for deep neural networks in classification”, arXiv:1702.05659, 2017, 10 | DOI

[24] Haoting. Zhang, Mei. Tian, Gaoping. Shao, Juan. Cheng, Jingjing. Liu, “Target detection of forward-looking sonar image based on improved YOLOv5”, IEEE Access, 10 (2022), 18023–18034 | DOI