A Convolutional Neural Network Model for Identifying Unclassified and Misclassified Vehicles Using Spatial Pyramid Pooling
Publication: Construction Research Congress 2022
ABSTRACT
Vehicles are classified as 13 classes in the Federal Highway Administration vehicle classification scheme, including motorcycles, passenger cars, buses, and various types of trucks. Truck traffic exerts a significant impact on pavement structure and is the main force causing pavement structure damages and distresses. Detailed truck traffic data are continuously recorded using Weight-in-Motion devices on the highway system. There usually exist a noticeable amount of unclassified and misclassified vehicles in the recorded dataset, which are those that the devices failed to identify their vehicle types based on the integrated criteria. As truck traffic is the main input of mechanistic-empirical pavement design, inaccurate vehicle classification would cause overdesign or underdesign of pavement structures and would consequently result in unnecessary extra construction costs as well as highway user costs. This paper presents a method to identify and reclassify the misclassified and unclassified vehicles utilizing the convolutional neural network in combination with spatial pyramid pooling. Through fine-tuning a series of hyperparameters, the proposed model successfully identified and reclassified a major portion of the unclassified and misclassified vehicles.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
AASHTO. (2008). Mechanistic-empirical pavement design guide, interim edition: A manual of practice. Washington, DC: American Association of State Highway and Transportation Offical (AASHTO), US Department of Transportation. Retrieved March 8, 2021 from https://www.fhwa.dot.gov/pavement/materials/hmec/pubs/module_e/participant_workbook.pdf.
Bao, J., Hu, X., Peng, C., Jiang, Y., Li, S., and Nantung, T. (2020). Truck traffic and load spectra of Indiana roadways for the mechanistic-empirical pavement design guide. Joint Transportation Research Program Publication No. FHWA/IN/JTRP-2020/21. West Lafayette, IN: Purdue University. https://doi.org/10.5703/1288284317227.
Chen, W. E. I., Sun, Q., Wang, J. U. E., Dong, J., and Xu, C. (2018). A novel model based on adaboost and deep cnn for vehicle classification. IEEE Access, 6(10), 60445–60455. https://doi.org/10.1109/ACCESS.2018.2875525.
Chen, Z., Pears, N., Freeman, M., and Austin, J. (2014). A gaussian mixture model and support vector machine approach to vehicle type and colour classification. IET intelligent transportation systems. 8(2). https://doi.org/10.1049/iet-its.2012.0104.
Dabiri, S., Marković, N., Heaslip, K., and Reddy, C. K. (2020). A deep convolutional neural network based approach for vehicle classification using large-scale GPS trajectory data. Transportation Research: Part C, 116(5). https://doi.prg/10.1016/j.trc.20200.102644.
FHWA (Federal Highway Administration). (2016). Traffic monitoring guide, pp 18–22. Washington, D.C.: Federal Highway Administration (FHWA), US Department of Transportation. Retrieved March 8, 2021 from https://www.fhwa.dot.gov/policyinformation/tmguide/tmg_fhwa_pl_17_003.pdf.
He, K., Zhang, X., Ren, S., and Sun, J. (2015). Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), Pages 1904–1916. DOI: https://doi.org/10.1109/TPAMI.2015.2389824.
Liang, M., Huang, X., Chen, C., Chen, X., and Tokuta, A. (2015). Counting and classification of highway vehicles by regression analysis. IEEE Transactions on Intelligent Transportation Systems, 16(5) Pages 2878–2888. doi: https://doi.org/10.1109/TITS.2015.2424917.
Li, S., Lin, J., Li, G., Bai, T., Wang, H., and Pang, Y. (2018). Vehicle type detection based on deep learning in traffic scence. Procedia Computer Science, 131 Pages 564–572. https://doi.org/10.1016/j.procs.2018.04.281.
Li, X., and Xu, J. (2008). Automatic Vehicle Classification Based on Video with BP Neural Networks. IEEE 4th international Conference on Wireless Communications, Networking and Mobile Computing, 2008. Page 1–3. Doi: https://doi.org/10.1109/WiCom.2008.3060.
Maungmai, W., and Nuthong, C. (2019). Vehicle classification with deep learning. IEEE 4th International Conference on Computer and Communication Systems (ICCCS), Singapore, 2019. Pages 294–298. Doi: https://doi.org/10.1109/CCOMS.2019.8821689.
Mo, X., Sun, C., Li, D., Huang, S., and Hu, T. (2020). Research on the method of determining highway truck load limit based on image processing. IEEE Access, 8(11), 205477–205486. https://doi.org/10.1109/access.2020.3037195.
Ni, X., and Huttunen, H. (2020). Vehicle attribute recognition by appearance: computer vision methods for vehicle type, make and model classification. J Sign Process Syst, 93, Pages 357–368. https://doi.org/10.1007/s11265-020-01567-6.
Peng, C., Jiang, Y., Li, S., and Nantung, T. (2021). Neural network optimal model for classification of unclassified vehicles in Weigh-in-Motion traffic data. Transportation Research Record: Journal of the Transportation Research Board, 036119812199067. https://doi.org/10.1177/0361198121990670.
Roecker, M. N., Costa, Y. M. G., Almeida, J. L. R., and Matsushita, G. H. G. (2019). Automation vehicle type classification with convolutional neural networks. 25 th International Conference on Systems, Signals and Image Processing (IWSSIP), Maribor, Slovenia, 2018, Pages 1–5. Doi: https://doi.org/10.1109/IWSSIP.2018.8439406.
Sarikan, S. S., Ozbayoglu, A. M., and Zilci, O. (2017). Automated vehicle classification with image processing and computational intelligence. Procedia Computer Science, 114(2017), 515–522. https://doi.org/10.1016/j.procs.2017.09.022.
Vatani, R., Olcay, N., and Mecit, S. (2019). Transfer learning using deep neural networks for classification of truck body types based on side‑fire lidar data. Journal of Big Data Analytics in Transportation, 1(1), Pages 71–82. https://doi.org/10.1007/s42421-019-00005-9.
Zhou, Y., Pei, Y., Li, Z., Fang, L., Zhao, Y., and Yi, W. (2020). Vehicle weight identification system for spatiotemporal load distribution on bridges based on non-contact machine vision technology and deep learning algorithms. Measurement: Journal of the International Measurement Confederation, 159(7), 107801. https://doi.org/10.1016/j.measurement.2020.107801.
Information & Authors
Information
Published In
Construction Research Congress 2022
Pages: 956 - 966
History
Published online: Mar 7, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.