Download pdf
Designing a dual-camera highway monitoring system based on high spatiotemporal resolution using neural networks
- 1 Glasgow College, University of Electronic Science and Technology of China, Chengdu, 611731, China
* Author to whom correspondence should be addressed.
Abstract
The criticality of infrastructure to societal development has seen highways evolve into an essential component of this ecosystem. Within this, the camera system has assumed significant importance due to the necessity for monitoring, evidence collection, and danger detection. However, the current standard of using high frame rate and high-resolution (HSR-HFR) cameras presents substantial costs associated with installation and data storage. This project, therefore, proposes a solution in the form of a High Spatiotemporal Resolution process applied to dual-camera videos. After evaluating state-of-the-art methodologies, this project develops a dual-camera system designed to merge frames from a high-resolution, low frame rate (HSR-LFR) camera with a high frame rate, low-resolution (LSR-HFR) camera. The result is a high-resolution, high frame rate video that effectively optimizes costs. The system pre-processes data using frame extraction and a histogram equalization method, followed by video processing with a neural network. Further refinement of the footage is performed via color adjustment and sharpening prior to a specific application, which in this case is license plate recognition. The system employs YOLOv5 in conjunction with LPRNet for license plate recognition. The resulting outputs demonstrate significant improvement in both clarity and accuracy, providing a more cost-effective solution for highway monitoring systems.
Keywords
high spatiotemporal resolution, dual-camera videos, histogram equalization, neural network, sharpen, YOLOv5, LPRNet
[1]. C. Liu et al, "New Generation of Smart Highway: Framework and Insights," Journal of Advanced Transportation, vol. 2021, pp. 1-12, 2021.
[2]. A. Dosovitskiy et al, "FlowNet: Learning optical flow with convolutional networks," in 2015, DOI: 10.1109/ICCV.2015.316.
[3]. H. Zheng et al, "CrossNet: An end-to-end reference-based super resolution network using cross-scale warping," in Computer Vision – ECCV 2018Anonymous Cham: Springer International Publishing, 2018, pp. 87-104.
[4]. M. Cheng et al, "A Dual Camera System for High Spatiotemporal Resolution Video Acquisition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, (10), pp. 3275-3291, 2021.
[5]. W. Song et al, "Heterogeneous spatio-temporal relation learning network for facial action unit detection," Pattern Recognition Letters, vol. 164, pp. 268-275, 2022.
[6]. W. Burger, M. J. Burge and SpringerLink (Online service), Digital Image Processing: An Algorithmic Introduction. (3rd 2022. ed.) 2022. DOI: 10.1007/978-3-031-05744-1.
[7]. S. Luo and J. Liu, "Research on Car License Plate Recognition Based on Improved YOLOv5m and LPRNet," IEEE Access, vol. 10, pp. 1-1, 2022.
[8]. T. Xue, Jiajun Wu, Donglai Wei, and William T Freeman, “Video enhancement with taskoriented flow,” International Journal of Computer Vision (IJCV), vol. 127, no. 8, pp. 1106–1125, 2019.
[9]. Z. Zhang, Zhaowen Wang, and Hairong Qi, “Image super-resolution by neural texture transfer,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 7982–7991.
[10]. Z. Huang, Tianyuan Zhang, Wen Heng, Boxin Shi, and Shuchang Zhou, “Rife: Real-time intermediate flow estimation for video frame interpolation,” arXiv preprint arXiv:2011.06294, 2021.
[11]. L. Lu, Wenbo Li, Xin Tao, Lu Jiangbo, and Jiaya Jia, “Masa-sr: Matching acceleration and spatial adaptation for reference-based image super-resolution,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
Cite this article
Wang,Z. (2024). Designing a dual-camera highway monitoring system based on high spatiotemporal resolution using neural networks. Applied and Computational Engineering,31,139-149.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2023 International Conference on Machine Learning and Automation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).