As a way to incentivize more people to drive multi-passenger vehicles, policies for high-occupancy vehicle (HOV) lanes and congestion toll discount are put in place at various locations. Being able to identify the correct number of people in a vehicle using the lanes is paramount in deciding the toll for that vehicle. In general, these lanes are operated based on voluntary declarations by the drivers, which makes it prone to abuse where vehicles with fewer occupants than required illegally use the HOV lanes. Hence, the capability to detect violators in real time is very critical. However, in many of the cases, vehicle occupancy detection relies on a labor-intensive manual method. This is quite unreliable and costly in terms of significant loss of revenue. This study proposes to remedy this problem by applying an object detection algorithm based on a deep convolutional neural network, known as the YOLO algorithm. This algorithm can automatically detect the number of occupants in a vehicle with very high degree of accuracy. Images are captured through Near Infrared (NIR) cameras on the HOV lanes. With proper fusion, clear signatures or silhouettes of the front passengers' faces are distinguishable from other inanimate objects in the vehicle. Using YOLOv3 the accuracy reaches 96%. This information is then used to charge the express lane toll. It is estimated that up to 95% of potential loss of revenue could be avoided. It is, therefore, a viable and attractive solution.
| Published in | American Journal of Neural Networks and Applications (Volume 8, Issue 1) |
| DOI | 10.11648/j.ajnna.20220801.11 |
| Page(s) | 1-5 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2022. Published by Science Publishing Group |
Computer Vision, High Occupancy Vehicle, Machine Learning, Object Detection
| [1] | Number of cars in the US, (2019). [Online]. https://www.statista.com/statistics/183505/number-of-vehicles-in-the-united-states-since-1990/ |
| [2] | Department of Motor Vehicle, (2016). [Online]. https://www.dmv.ca.gov/portal/ |
| [3] | Pavlidis, L., Symosek, P., Morellas, V., Fritz, B., Papanikolopoulos, R. & Sfarzo, R. (1999). Automatic passenger counting in the HOV lane. University of Minnesota, USA. |
| [4] | Xu, B., P. Paul, P., Artan, Y. & Perronnin F. (2014). A machine learning approach to vehicle occupancy detection. Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems, China. https://doi.org/10.1109/ITSC.2014.6957856 |
| [5] | Lee, J., Byun, J., Lim J., & Lee, J. (2020). A framework for detecting vehicle occupancy based on the occupant labeling method. Journal of Advanced Transportation. https://doi.org/10.1155/2020/8870211 |
| [6] | Schijns S. & Mathews, P. (2005). A breakthrough in automated vehicle occupancy monitoring systems for hov/hot facilities. 12th HOV Systems Conference. |
| [7] | Kumar, A., Gupta A., Santra, B., Kolla, M., Gupta, M. & Singh, R. (2019). VPDS: An AI-based automated vehicle occupancy and violation detection system. Proceedings of the AAAI Conference on Innovative Applications of Artificial Intelligence, USA. https://doi.org/10.1609/aaai.v33i01.33019498 |
| [8] | Bulan, O., Kozitsky, V., Ramesh P. & Shreve, M. (2017). Segmentation and annotation free license plate recognition with deep localization and failure identification. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/TITS.2016.2639020 |
| [9] | Jang, J. (2021). High-occupancy vehicle lane enforcement system. The Open Transportation Journal. http://dx.doi.org/10.2174/1874447802115010194 |
| [10] | Szegedy, C., Liu, W., Jia Y. & Sermanet, P. (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA. https://doi.org/10.1109/CVPR.2015.7298594 |
| [11] | Redmon J. & Farhadi, A. (2017). YOLO9000: better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA. https://doi.org/10.1109/CVPR.2017.690 |
| [12] | Redmon, J. & Farhadi, A. (2015). YOLOv3: An incremental improvement. University of Washington, USA. |
| [13] | Caltrans. (2021). High-occupancy vehicle systems. [Online]. https://dot.ca.gov/programs/traffic-operations/hov/ |
| [14] | The Tool Roads of Orange County (2022). [Online]. https://thetollroads.com/about/investor/transactions |
APA Style
Rishabh Dara, Alex Sumarsono. (2022). Automated Passenger Detection and Toll Processing System Using Convolution Neural Network. American Journal of Neural Networks and Applications, 8(1), 1-5. https://doi.org/10.11648/j.ajnna.20220801.11
ACS Style
Rishabh Dara; Alex Sumarsono. Automated Passenger Detection and Toll Processing System Using Convolution Neural Network. Am. J. Neural Netw. Appl. 2022, 8(1), 1-5. doi: 10.11648/j.ajnna.20220801.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajnna.20220801.11,
author = {Rishabh Dara and Alex Sumarsono},
title = {Automated Passenger Detection and Toll Processing System Using Convolution Neural Network},
journal = {American Journal of Neural Networks and Applications},
volume = {8},
number = {1},
pages = {1-5},
doi = {10.11648/j.ajnna.20220801.11},
url = {https://doi.org/10.11648/j.ajnna.20220801.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20220801.11},
abstract = {As a way to incentivize more people to drive multi-passenger vehicles, policies for high-occupancy vehicle (HOV) lanes and congestion toll discount are put in place at various locations. Being able to identify the correct number of people in a vehicle using the lanes is paramount in deciding the toll for that vehicle. In general, these lanes are operated based on voluntary declarations by the drivers, which makes it prone to abuse where vehicles with fewer occupants than required illegally use the HOV lanes. Hence, the capability to detect violators in real time is very critical. However, in many of the cases, vehicle occupancy detection relies on a labor-intensive manual method. This is quite unreliable and costly in terms of significant loss of revenue. This study proposes to remedy this problem by applying an object detection algorithm based on a deep convolutional neural network, known as the YOLO algorithm. This algorithm can automatically detect the number of occupants in a vehicle with very high degree of accuracy. Images are captured through Near Infrared (NIR) cameras on the HOV lanes. With proper fusion, clear signatures or silhouettes of the front passengers' faces are distinguishable from other inanimate objects in the vehicle. Using YOLOv3 the accuracy reaches 96%. This information is then used to charge the express lane toll. It is estimated that up to 95% of potential loss of revenue could be avoided. It is, therefore, a viable and attractive solution.},
year = {2022}
}
TY - JOUR T1 - Automated Passenger Detection and Toll Processing System Using Convolution Neural Network AU - Rishabh Dara AU - Alex Sumarsono Y1 - 2022/04/09 PY - 2022 N1 - https://doi.org/10.11648/j.ajnna.20220801.11 DO - 10.11648/j.ajnna.20220801.11 T2 - American Journal of Neural Networks and Applications JF - American Journal of Neural Networks and Applications JO - American Journal of Neural Networks and Applications SP - 1 EP - 5 PB - Science Publishing Group SN - 2469-7419 UR - https://doi.org/10.11648/j.ajnna.20220801.11 AB - As a way to incentivize more people to drive multi-passenger vehicles, policies for high-occupancy vehicle (HOV) lanes and congestion toll discount are put in place at various locations. Being able to identify the correct number of people in a vehicle using the lanes is paramount in deciding the toll for that vehicle. In general, these lanes are operated based on voluntary declarations by the drivers, which makes it prone to abuse where vehicles with fewer occupants than required illegally use the HOV lanes. Hence, the capability to detect violators in real time is very critical. However, in many of the cases, vehicle occupancy detection relies on a labor-intensive manual method. This is quite unreliable and costly in terms of significant loss of revenue. This study proposes to remedy this problem by applying an object detection algorithm based on a deep convolutional neural network, known as the YOLO algorithm. This algorithm can automatically detect the number of occupants in a vehicle with very high degree of accuracy. Images are captured through Near Infrared (NIR) cameras on the HOV lanes. With proper fusion, clear signatures or silhouettes of the front passengers' faces are distinguishable from other inanimate objects in the vehicle. Using YOLOv3 the accuracy reaches 96%. This information is then used to charge the express lane toll. It is estimated that up to 95% of potential loss of revenue could be avoided. It is, therefore, a viable and attractive solution. VL - 8 IS - 1 ER -
Information
Email: