Intelligent Transport System: Classification of Traffic Signs Using Deep Neural Networks in Real Time

2021 ◽  
pp. 207-219
Author(s):  
Anukriti Kumar ◽  
Tanmay Singh ◽  
Dinesh Kumar Vishwakarma
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Transport System ◽  
Deep Neural Networks ◽  
Intelligent Transport System ◽  
Traffic Signs ◽  
Intelligent Transport

scholarly journals Blockchain Based Intelligent Transport System

2021 ◽  
Vol 1 (3) ◽  
pp. 70-88
Author(s):  
Muhammad Waseem ◽  
Khawaja Arslan Ahmed ◽  
Muhammad Talha Azeem
Keyword(s):  
Real Time ◽  
Transport System ◽  
Private Information ◽  
Large Scale ◽  
Single Point ◽  
Vehicular Network ◽  
Security And Privacy ◽  
Intelligent Transport System ◽  
False Information ◽  
Intelligent Transport

Blockchain technology is widely studied in these days and has vital role in the ITS and Vehicular network. Intelligent Transport System (ITS) have resolved several issues of transportation like congestion, electronic toll collection, traffic light cameras, traffic updates, and environment forecasting. The vehicular network is the ever-increasing network it is not only facilitates us but also brings new challenges with it. The mobile nature of vehicular networks it is very important to collect and broadcast information of traffic events in real-time. A little delay to broadcast important information or deciding on this information can cause a serious situation in the mobile vehicular network. Moreover, malicious vehicles in the network broadcasting false information about these traffic events cause a disturbance in the network. In large-scale scenarios, the transmission of malicious messages offers a lot of danger to the system. They can wrongly claim the roads and provide false information about the incident. These traffic events can be life-threatening and cause unwanted situations like accidents, wastage of time and other resources. Therefore, it is very much important to provide real-time information on recent traffic events and real-time authentication of vehicles that broadcast information in the network. Traditional studies are unable to solve these security issues and contain a single point of failure issue. These studies are centralized and dependent on a single higher authority. Moreover, they have serious security concerns that are harmful for vehicular network. Moreover, any vehicles are unwilling to share their private information while broadcasting information about traffic events because they are strangers to each other. And if a vehicle does not want to share its private information like name, id, etc. It is not possible to authenticate this vehicle and manage trust in the network. It means that it is very crucial to prevent vehicles to broadcast wrong information in the network while preserving their privacy at the same time. Therefore, there is a need to authenticate vehicles and manage trust in the network while preserving their privacy simultaneously. Blockchain can offer better solution to solve these issues due to its secure distributed environment and features that ensure immutability about actions. The purpose of this report is to provide real-time security and privacy in the network. It is also ensured that vehicles get real-time authenticated information about traffic incidents from legitimate vehicles while simultaneously preserving their privacy. It means that only authenticated and legitimate entities (vehicles) can participate in vehicular network and privacy of both sender and receiver is secured in the network. Details of conducted experiments are given, and shreds of evidence are provided to evaluate the performance of architectures for authentication and trust management. The shreds of evidence show that these blockchain-based systems can solve security and trust issues more effectively.

scholarly journals A Crowdsensing-Based Real-Time System for Finger Interactions in Intelligent Transport System

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Chengqun Song ◽  
Jun Cheng ◽  
Wei Feng
Keyword(s):  
Real Time ◽  
Transport System ◽  
Video Frame ◽  
Intelligent Transport System ◽  
Real Time System ◽  
Scanning Method ◽  
Average Percentage ◽  
Intelligent Transport ◽  
Complex Information ◽  
3D Information

Crowdsensing leverages human intelligence/experience from the general public and social interactions to create participatory sensor networks, where context-aware and semantically complex information is gathered, processed, and shared to collaboratively solve specific problems. This paper proposes a real-time projector-camera finger system based on the crowdsensing, in which user can interact with a computer by bare hand touching on arbitrary surfaces. The interaction process of the system can be completely carried out automatically, and it can be used as an intelligent device in intelligent transport system where the driver can watch and interact with the display information while driving, without causing visual distractions. A single camera is used in the system to recover 3D information of fingertip for hand touch detection. A linear-scanning method is used in the system to determine the touch for increasing the users’ collaboration and operationality. Experiments are performed to show the feasibility of the proposed system. The system is robust to different lighting conditions. The average percentage of correct hand touch detection of the system is 92.0% and the average time of processing one video frame is 30 milliseconds.

scholarly journals Moroccan Video Intelligent Transport System: Vehicle Type Classification Based on Three-Dimensional and Two-Dimensional Features

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 72528-72537 ◽  
Author(s):  
Hatim Derrouz ◽  
Abderrahim Elbouziady ◽  
Hamd Ait Abdelali ◽  
Rachid Oulad Haj Thami ◽  
Sanaa El Fkihi ◽  
...  
Keyword(s):  
Transport System ◽  
Three Dimensional ◽  
Intelligent Transport System ◽  
Two Dimensional ◽  
Intelligent Transport ◽  
Vehicle Type ◽  
Vehicle Type Classification ◽  
Type Classification

scholarly journals Assurance monitoring of learning-enabled cyber-physical systems using inductive conformal prediction based on distance learning

2021 ◽  
Vol 35 (2) ◽  
pp. 251-264
Author(s):  
Dimitrios Boursinos ◽  
Xenofon Koutsoukos
Keyword(s):  
Neural Networks ◽  
Distance Learning ◽  
Real Time ◽  
Speaker Recognition ◽  
Deep Neural Networks ◽  
Cyber Physical Systems ◽  
Error Rates ◽  
Traffic Sign ◽  
Conformal Prediction ◽  
Physical Systems

AbstractMachine learning components such as deep neural networks are used extensively in cyber-physical systems (CPS). However, such components may introduce new types of hazards that can have disastrous consequences and need to be addressed for engineering trustworthy systems. Although deep neural networks offer advanced capabilities, they must be complemented by engineering methods and practices that allow effective integration in CPS. In this paper, we proposed an approach for assurance monitoring of learning-enabled CPS based on the conformal prediction framework. In order to allow real-time assurance monitoring, the approach employs distance learning to transform high-dimensional inputs into lower size embedding representations. By leveraging conformal prediction, the approach provides well-calibrated confidence and ensures a bounded small error rate while limiting the number of inputs for which an accurate prediction cannot be made. We demonstrate the approach using three datasets of mobile robot following a wall, speaker recognition, and traffic sign recognition. The experimental results demonstrate that the error rates are well-calibrated while the number of alarms is very small. Furthermore, the method is computationally efficient and allows real-time assurance monitoring of CPS.

Multi-Constrained Real-Time Entry Guidance Using Deep Neural Networks

2021 ◽  
pp. 1-1 ◽  
Author(s):  
Lin Cheng ◽  
Fanghua Jiang ◽  
Zhenbo Wang ◽  
Junfeng Li
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Deep Neural Networks ◽  
Entry Guidance
Sign in / Sign up

Export Citation Format

Share Document