Abstract
A moveable lane barrier along the Auckland Harbour Bridge (AHB) enables two-way traffic flow optimisation and control. However, the AHB barrier transfer machines are not equipped with an automated solution for screening of the pins that link the barrier segments. To improve traffic safety, the aim of this paper is to combine traditional machine with deep learning approaches to aid visual pin inspection. For model training with imbalanced dataset, we have included additional synthetic frames depicting unsafe pin positions produced from collected videos. Preliminary experiments on produced models indicate that we are able to identify unsafe pin positions with precision and recall up to 0.995. To improve traffic safety beyond the AHB case study, future developments will include extended datasets to produce near-real time IoT alerting solutions using mobile and other video sources.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bačić, B.: Predicting golf ball trajectories from swing plane: an artificial neural networks approach. Expert Syst. Appl. 65, 423–438 (2016). https://doi.org/10.1016/j.eswa.2016.07.014
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). https://www.deeplearningbook.org
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and \({<}0.5\) MB model size (2016). arXiv:1602.07360
Lee, H.J., Ullah, I., Wan, W., Gao, Y., Fang, Z.: Real-time vehicle make and model recognition with the residual SqueezeNet architecture. Sensors 19(5), 982 (2019)
MathWorks: Pretrained deep neural networks (2019). https://au.mathworks.com/help/deeplearning/ug/pretrained-convolutional-neural-networks.html
New Zealand Ministry for Culture and Heritage: Auckland harbour bridge opens 30 May 1959 (1959). https://nzhistory.govt.nz/the-auckland-harbour-bridge-is-officially-opened
NZ Transport Agency: How to move a concrete motorway barrier (2014). https://www.nzta.govt.nz/media-releases/how-to-move-a-concrete-motorway-barrier/
Stanford vision lab: ImageNet (2016). www.image-net.org
University of Ljubljana: Image embedding. https://orange.biolab.si/widget-catalog/image-analytics/imageembedding/
Wikipedia: Auckland harbour bridge from Wikipedia (2020). https://en.wikipedia.org/wiki/Auckland_Harbour_Bridge
Wilson, S.: The next harbour crossing: Road and rail, or just rail? (2019). https://www.nzherald.co.nz/nz/news/article.cfm?c_id=1&objectid=12210993
Acknowledgement
The authors wish to thank Gary Bonser, Angela Potae and Martin Olive from NZ Transport Agency and Auckland System Management for their assistance including safety briefings, transport to the site, video recording under their supervision, various problem insights project requirements, availability and ongoing enthusiasm to assist with this project. We also wish to express our gratitude for the comprehensive documentations provided by the contributors to ImageNet, TensorFlow, Orange Data Mining, Google Cloud, MathWorks, OpenCV and SqueezeNet and for sharing their tools and libraries.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Bačić, B., Rathee, M., Pears, R. (2020). Automating Inspection of Moveable Lane Barrier for Auckland Harbour Bridge Traffic Safety. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12532. Springer, Cham. https://doi.org/10.1007/978-3-030-63830-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-63830-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63829-0
Online ISBN: 978-3-030-63830-6
eBook Packages: Computer ScienceComputer Science (R0)