IRO Journals
Journal of Soft Computing Paradigm

Real-Time Seat Vacancy Detection in Public Transport Using YOLOv5-Based Deep Learning

Open Access
Published: 30 April, 2026
Pages: 119-130
  • Elakkiya S. , Elakkiya S.
    Department of Electronics and Communication Engineering, Dr. M.G.R Educational and Research Institute, Chennai, India
    Department of Electronics and Communication Engineering, Dr. M.G.R Educational and Research Institute, Chennai, India
  • Amuthanantham K. , Amuthanantham K.
    Department of Electronics and Communication Engineering, Dr. M.G.R Educational and Research Institute, Chennai, India
    Department of Electronics and Communication Engineering, Dr. M.G.R Educational and Research Institute, Chennai, India
  • Anandhi S. Anandhi S.
    Department of Electronics and Communication Engineering, Dr. M.G.R Educational and Research Institute, Chennai, India
    Department of Electronics and Communication Engineering, Dr. M.G.R Educational and Research Institute, Chennai, India
view PDF
view PDF

How to Cite

S., Elakkiya, Amuthanantham K., and Anandhi S. 2026. “Real-Time Seat Vacancy Detection in Public Transport Using YOLOv5-Based Deep Learning”. Journal of Soft Computing Paradigm 8 (2): 119-30. https://doi.org/10.36548/jscp.2026.2.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Deep Learning
YOLOV5
Seat Detection
Image Processing
Smart Transportation

Abstract

Public transport systems have always faced the challenge of accurately identifying the availability of seats in public transport systems in ‘real time’ due to constantly changing passenger flow patterns, different levels of natural light, and obstructions. This paper presents a novel framework for automated detection of vacant seats on a vehicle through the use of deep learning techniques using the YOLOv5 object detection model through continuous streaming video from inside the vehicle. In addition to being able to correctly classify the occupied or non-occupied state of a seat, the system can also accurately provide the location of each of the classified objects. A dataset containing 500 images taken under different environmental conditions was utilized for the training and evaluation of the model, and the images in the data set were subject to various techniques for improving the generalization of the model. The model achieved a classification accuracy of 94.2 percent, a precision of 92.8 percent, a recall of 91.6 percent, and an F1 score of 92.2 percent, and performed very well across the various evaluation scenarios. Furthermore, the system can operate in “real-time” at a frame rate of 20-25 fps, which allows it to be implemented in a real-world environment. A comparison between the method and conventional methods for image processing and face detection has also been done, and the findings reveal that the new method outperforms both traditional approaches when it comes to managing occlusions and handling complicated backgrounds. In conclusion, the results of this analysis show that the proposed system can provide an efficient, scalable and reliable solution for intelligent public transportation systems. The system can be applied to smart city applications.

References

  1. Jones, Michael. "Rapid Object Detection Using a Boosted Cascade of Simple." In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA, 2001, 8-14.
  2. Sharma, Himanshu, Sumeet Saurav, Sanjay Singh, Anil K. Saini, and Ravi Saini. "Analyzing Impact of Image Scaling Algorithms on Viola-Jones Face Detection Framework." In 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2015, 1715-1718.
  3. Mondal, Tarutal Ghosh, and Mohammad Reza Jahanshahi. "Applications of Computer Vision-Based Structural Health Monitoring and Condition Assessment in Future Smart Cities." The rise of smart cities (2022): 193-221.
  4. Liu, Li, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, and Matti Pietikäinen. "Deep Learning for Generic Object Detection: A Survey." International journal of computer vision 128, no. 2 (2020): 261-318.
  5. Chary, Podakanti Satyajith. "Real Time Object Detection Using Yolov4." Int. J. Res. Appl. Sci. Eng. Technol 11, no. 12 (2023): 1375-1379.
  6. Mahaur, Bharat, and K. K. Mishra. "Small-Object Detection Based on YOLOv5 in Autonomous Driving Systems." Pattern Recognition Letters 168 (2023): 115-122.
  7. Alve, Shahran Rahman. "Deep Learning and Hybrid Approaches for Dynamic Scene Analysis, Object Detection and Motion Tracking." 2014, arXiv preprint arXiv:2412.05331.
  8. Aharon, Nir, Roy Orfaig, and Ben-Zion Bobrovsky. "BoT-SORT: Robust Associations Multi-Pedestrian Tracking." 2022, arXiv preprint arXiv:2206.14651.
  9. Alameri, Mohammed, and Qurban A. Memon. "YOLOv5 Integrated with Recurrent Network for Object Tracking: Experimental Results from a Hardware Platform." IEEE Access 12 (2024): 119733-119742.
  10. Chang, Yupeng, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen et al. "A Survey on Evaluation of Large Language Models." ACM transactions on intelligent systems and technology 15, no. 3 (2024): 1-45.
  11. Redmon, Joseph, Santosh Divvala, Ross Girshick, and Ali Farhadi. "You Only Look Once: Unified, Real-Time Object Detection." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, 779-788.
  12. Lee, Jeonghun, and Kwang-il Hwang. "YOLO with Adaptive Frame Control for Real-Time Object Detection Applications." Multimedia tools and applications 81, no. 25 (2022): 36375-36396.
  13. Dataset - https://www.kaggle.com/datasets/samuelayman/bus-dataset