Detection of the triple riding and speed violation on two-wheelers using deep learning algorithms
- PDF / 5,251,448 Bytes
- 13 Pages / 439.642 x 666.49 pts Page_size
- 46 Downloads / 171 Views
Detection of the triple riding and speed violation on two-wheelers using deep learning algorithms Nikhil Chakravarthy Mallela1
· Rohit Volety2 · Srinivasa Perumal R.1 · Nadesh R. K.1
Received: 15 February 2020 / Revised: 14 August 2020 / Accepted: 19 October 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract To curb the accident rate and traffic levels, strict implementation of the rules and continuous monitoring of the traffic is mandatory. Traffic Rule Violation Monitoring System ensures that the rules are followed strictly and it reduces the human effort. The main objective of this work is to identify the Triple Riding. To detect the triple riders, the deep learning framework darknet is used, which in turn uses a type of convolutional neural networks i.e. Deconvolutional neural network-based YOLO (You Only Look Once) algorithm for detection of the number of persons riding a bike, the system classifies the vehicle as to the rule-breach vehicle or not. The junctions acting as the data collections center, collects the data. The image of the vehicle classified as the rule-breach is stored along with the data such as vehicle manufacturing ID and vehicle speed transferred at the particular frame. The transfer of the data is facilitated using the GSM module and the NodeMCU deployed on the vehicle. The vehicle number will be verified with the transport office. To survive the lack of internet connectivity or low internet connectivity, the system is being equipped with the GSM module; else, the data related to the vehicle can be pulled by the development boards deployed at the junctions, acting them as the central part of the public internetwork deployed. This public internetwork acting the medium to pull the data from the vehicle to the central system. This is carried out using the concept of dynamic network configuration in NodeMCU. The use of Node MCU and the public network system makes the system much more viable, available and reliable. Thereby making the riders follow the rules properly and reducing irresponsible driving. Keywords Triple riding · Object detection · YOLO · Speed violation · Deep learning
Nikhil Chakravarthy Mallela
[email protected] Srinivasa Perumal R. [email protected] 1
School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, India
2
School of Electronics Engineering, Vellore Institute of Technology, Vellore, India
Multimedia Tools and Applications
1 Introduction Road safety is the most important aspect of this automobile driven technological world. Considering the number of people taking road transport as the means to reach their destination, the number of people reaching the heavens instead of their safe home, increasing day-to-day. As per Indian government data, in 2017 alone, 1,47,913 people were killed in road accidents across India. One lakh forty-seven thousand nine hundred and thirteen dead bodies on Indian roads in just one year. This figure is 37.54% more than the total number
Data Loading...
