Smart traffic control: Identifying driving-violations using fog devices with vehicular cameras in smart cities
- Authors
- Rathore, M.M.; Paul, A.; Rho, S.; Khan, M.; Vimal, S.; Shah, S.A.
- Issue Date
- Aug-2021
- Publisher
- Elsevier Ltd
- Keywords
- Lane detection; Mobile video processing; Smart city; Traffic governance and control; Vehicle detection
- Citation
- Sustainable Cities and Society, v.71
- Journal Title
- Sustainable Cities and Society
- Volume
- 71
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/62266
- DOI
- 10.1016/j.scs.2021.102986
- ISSN
- 2210-6707
2210-6715
- Abstract
- Growing vehicular traffic in urban areas creates a mess for authorities to handle city traffic. With the lack of human resources, authorities are moving towards the use of smart and auto-traffic control systems to manage an increasing volume of traffic. Mostly, these systems monitor traffic using street cameras and identify illegal traffic behaviors, such as signal violations. However, it is not feasible to employ humans or static cameras everywhere in the city in order to cover all the urban roads. These days, modern automobiles come with cameras to store videos as a black-box in case of an accident. In this paper, we exploited the use of vehicular cameras and proposed a smart traffic control model to report any traffic violation on the road. To this end, the vehicle's camera monitors all front cars on the road and transmits videos to the car's attached fog device. The fog device analyses the captured video for unlawful behavior and reports to traffic authorities in case of any violation. Initially, front vehicles are recognized using Single Shot MultiBox Detector (SSD), whereas road lanes are marked using Hough transform. Later, the violations are identified using the violation-detection algorithm. As a use case, the algorithm is designed for the fog device to identify driving violations, including wrong U-turn and driving on a central divider line or a yellow line. The role of the fog device is implemented on a GTX750-Ti GPU-based machine. Finally, the system's performance is evaluated in terms of accuracy and efficiency. © 2021 Elsevier Ltd
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Business & Economics > Department of Industrial Security > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/62266)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.