Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb 10:1-20.
doi: 10.1007/s11042-023-14418-w. Online ahead of print.

A vision-based real-time traffic flow monitoring system for road intersections

Jahongir Azimjonov #  1 , Ahmet Özmen  2 , Metin Varan #  3
Affiliations

A vision-based real-time traffic flow monitoring system for road intersections

Jahongir Azimjonov et al. Multimed Tools Appl. .

Abstract

In this study, a vision based real-time traffic flow monitoring system has been developed to extract statistics passes through the intersections. A novel object tracking and data association algorithms have been developed using the bounding-box properties to estimate the vehicle trajectories. Then, rich traffic flow information such as directional and total counting, instantaneous and average speed of vehicles are calculated from the predicted trajectories. During the study, various parameters that affect the accuracy of vision based systems are examined such as camera locations and angles that may cause occlusion or illusion problems. In the last part, sample video streams are processed using both Kalman filter and new centroid-based algorithm for comparative study. The results show that the new algorithm performs 9.18% better than Kalman filter approach in general.

Keywords: Data association; Deep neural network; Image based traffic flow monitoring; Vehicle detection; Vehicle tracking.

PubMed Disclaimer

Conflict of interest statement

Conflict of InterestsEach of the authors confirms that this manuscript has not been previously published and is not currently under consideration for publication elsewhere. Additionally, we have no conflicts of interest to disclose.

Figures

Fig. 1
Fig. 1
Block diagram of online traffic video processing system. The input video stream is normalized by reducing the number of frames, and then sent to the object detection unit. After detecting the vehicles and their types in the frame, the tracking algorithm predicts/plots the trajectory and saves them in the database
Fig. 2
Fig. 2
Various camera placements at different intersections: a) a proper camera placement with high-angle, b) a low-angle camera placement causes occlusion, c) bird’s-eye view camera placement which causes object detection failure
Fig. 3
Fig. 3
Flow chart of centroid-based vehicle trajectory extraction algorithm. After normalizing the number of frames an object detection algorithm is used for vehicle recognition. The routes of the vehicles are determined by using the centroid based tracking algorithm
Fig. 4
Fig. 4
The loss graphs obtained from training logs: a) Netherlands, b) Sweden, c) Turkey, d) Japan, e) Ukraine
Fig. 5
Fig. 5
The test videos examined in the study with different camera placements at different intersections: a) Netherlands, b) Sweden, c) Turkey, d) Japan, e) Ukraine
Fig. 6
Fig. 6
A screen shot of form-based online tool that shows real-time traffic flow statistics acquired from the video stream
See this image and copyright information in PMC

References

    1. Hilbert EE, Rennie PA, Kneidl WA. A sensor for control of arterials and networks. IEEE Trans Veh Technol. 1980;29(2):208–215. doi: 10.1109/T-VT.1980.23842. - DOI
    1. Liu Y, Tian B, Chen S, Zhu F, Wang K (2013) A survey of vision-based vehicle detection and tracking techniques in ITS. In: Proceedings of 2013 IEEE international conference on vehicular electronics and safety, pp 72–77
    1. Shoeibi A, Khodatars M, Alizadehsani R, Ghassemi N, Jafari M, Moridian P et al (2020) Automated detection and forecasting of COVID-19 using deep learning techniques: a review. CoRR. arXiv:2007.10785
    1. Shoeibi A, Khodatars M, Jafari M, Moridian P, Rezaei M, Alizadehsani R, et al. Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: a review. Comput Biol Med. 2021;136:104697. doi: 10.1016/j.compbiomed.2021.104697. - DOI - PubMed
    1. Khodatars M, Shoeibi A, Ghassemi N, Jafari M, Khadem A, Sadeghi D et al (2020) Deep learning for Neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: a review. CoRR. arXiv:2007.01285 - PubMed

LinkOut - more resources