Abstract
With the deployment of 5th Generation networks, characterized by a wider bandwidth and an increased computational capability, is now possible to develop more complex services that requires low latency, such as applications for public safety based on artificial intelligence. To this aim, it has been studied a possible use of the so-called Multi-access Edge Computing (MEC) enabled by 5G that reduces the latency thanks to computational resources located closer to the user. This allows to deploy an application that recognizes the formation of traffic queues on the highway through the analysis of video streams, to be used in the context of smart mobility. In order to do so, it is needed to detect the travelling vehicles and to track their movement to understand when a traffic jam is occurring. For the implementation, the Convolutional Neural Network (CNN) paradigm has been leveraged for the detection of the vehicles. Among the several alternatives compared, it has been chosen the third version of You Only Look Once (YOLO) for its trade-off between accuracy and real-time computation. Then, the detections tracked through the Simple Online and Realtime Tracking (SORT) algorithm are exploited to identify the direction of the traffic flows and then to calculate when the vehicles are slowing down or stop**, by either measuring the number of stationary vehicles or the travelling time of the vehicles within a region of interest. The service has been developed with the objective of being employed through the parallel computation offered by 5G MEC servers equipped with modern GPUs, in order to obtain real-time performances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
IoU is an index that measures the closeness between the anchor box and the ground truth box through the division of the area obtained by intersecting the two boxes with the area obtained by the union of them.
- 2.
Common Objects in COntext (COCO): https://cocodataset.org/.
- 3.
Imagenet: http://www.image-net.org/.
- 4.
Pascal VOC 2007: http://host.robots.ox.ac.uk/pascal/VOC/voc2007/.
- 5.
For the sake of simplicity we will refer to them as Video 1 and Video 2, but the original title are: M6 Motorway Traffic uploaded by the channel “DriveCamUK” (https://youtu.be/PNCJQkvALVc) for Video 1, and 4K Road traffic video for object detection and tracking uploaded by Karol Majek (https://youtu.be/MNn9qKG2UFI). Due to copyright reasons, in this section will be shown frames extracted by the second video that have been published under the Creative Commons license.
References
Maaloul, B., et al.: Adaptive video-based algorithm for accident detection on highways. In: 2017 12th IEEE International Symposium on Industrial Embedded Systems (SIES). IEEE (2017)
Khan, S., et al.: An intelligent monitoring system of vehicles on highway traffic. In: 2018 12th International Conference on Open Source Systems and Technologies (ICOSST). IEEE (2018)
Chen, L., et al.: An algorithm for highway vehicle detection based on convolutional neural network. Eurasip J. Image and Video Process. 2018(1), 109 (2018)
Jiang, T., et al.: Fast video-based queue length detection approach for self-organising traffic control. IET Intell. Transp. Syst. 13(4), 670–676 (2018)
Russell, S., Norvig, P.: Artificial intelligence: a modern approach (2002)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Rojas, R.: Neural Networks: A Systematic Introduction. Springer Science & Business Media, Berlin (2013)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 160(1), 106 (1962)
Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J. Neurophysiol. 28(2), 229–289 (1965)
Fukushima, K., Miyake, S.: Neocognitron: a self-organizing neural network model for a mechanism of visual pattern recognition. In: Competition and cooperation in neural nets, pp. 267–285. Springer, Berlin (1982)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
LeCun, Y.: Generalization and network design strategies. Connect. Perspect. 19, 143–155 (1989)
LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision. Springer, Cham (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ar**v preprint ar**v:1409.1556 (2014)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Huang, G., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Girshick, R., et al.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Machine Intell. 38(1), 142–158 (2015)
He, K., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 2. IEEE (2006)
Grauman, K., Darrell, T.: The pyramid match kernel: discriminative classification with sets of image features. In: Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, vol. 2. IEEE (2005)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (2015)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)
Lin, T.Y., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
He, K., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (2017)
Dai, J., et al.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems (2016)
Redmon, J., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Liu, W., et al.: SSD: single shot multibox detector. In: European Conference on Computer Vision. Springer, Cham (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. ar**v preprint ar**v:1502.03167 (2015)
Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. ar**v preprint ar**v:1804.02767 (2018)
Lin, T.Y., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (2017)
Fu, C.Y., et al.: DSSD: Deconvolutional single shot detector. ar**v preprint ar**v:1701.06659 (2017)
ICT4CART (2020). WP8 - Evaluation & impact assessment. https://ict4cart.eu/hub/deliverables
ICT4CART (2019). WP9 - Communication, Dissemination and Exploitation. https://ict4cart.eu/hub/deliverables
Bewley, A., et al.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP). IEEE (2016)
Kalman, R.E.: A new approach to linear filtering and prediction problems, pp. 35–45 (1960)
Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2(1–2), 83–97 (1955)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Grilli, S., Panza, G. (2021). AI-Based Traffic Queue Detection for IoV Safety Services in 5G Networks. In: Magaia, N., Mastorakis, G., Mavromoustakis, C., Pallis, E., Markakis, E.K. (eds) Intelligent Technologies for Internet of Vehicles. Internet of Things. Springer, Cham. https://doi.org/10.1007/978-3-030-76493-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-76493-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76492-0
Online ISBN: 978-3-030-76493-7
eBook Packages: Computer ScienceComputer Science (R0)