Next-generation Intelligent Transportation Systems Research Articles

Optical Flow-Based Stereo Visual Odometry With Dynamic Object Detection

Autonomous vehicles (AVs) play an important role in the next-generation intelligent transportation system (ITS), which requires AVs to have the ability of rapid decision-making and control. As a part of ITS, simultaneous localization and mapping (SLAM) technology is the basis for AVs to operate in a complex and unknown environment. In this article, a stereo vision odometry method in a dynamic environment is proposed, which can not only effectively overcome the influence of dynamic objects but also detect the position of dynamic objects. An optical flow filtering algorithm based on the quantitative histogram (QH) and the optical flow angle histogram (OFAH) of the feature points is proposed to obtain dynamic points. Furthermore, a multifeature fusion mechanism is used to perform binary segmentation and get the bounding box of dynamic object. Experiments show that the proposed method can improve the accuracy of pose estimation and detect moving objects in a dynamic environment.

Towards the next generation intelligent transportation system: A vehicle detection and counting framework for undisciplined traffic conditions

Modern development in deep learning and computer vision techniques, intelligent transportation system (ITS) has emerged as a useful tool for building a traffic infrastructure in smart cities. Previously, several computer vision techniques have been proposed for vehicle recognition, which were limited in handling undisciplined, dense and laneless traffic conditions. Moreover, these frameworks did not incorporate many of the local vehicle configurations common in South Asian countries such as Pakistan, Bangladesh, and India. Considering the limitations of previous frameworks, this paper presents efficient vehicle detection and counting model for undisciplined conditions including dense and laneless traffic, occulusion cases and diverse range of local vehicles. A dataset of more than 2400 images of vehicles has been collected comprising of six new categories of local vehicles, and considering undisciplined traffic conditions to ensure robustness in vehicle detection and counting system. Transfer learning based technique has been used, using faster R-CNN model with Inception V2 as underlying architecture. The experimental results show a precision of 86.14% in terms of mAP. The work finds its application in South Asian contexts as more smart cities are formed in this region. The proposed framework will enable traffic monitoring with higher reliability, accuracy and granularity, contributing in having next-generation ITS.

BDEdge: Blockchain and Deep-Learning for Secure Edge-Envisioned Green CAVs

Green Connected and Autonomous Vehicles (CAVs) are the future of next-generation Intelligent Transportation Systems (ITS) that will help humans to improve road safety and reduce pollution, energy consumption, and travel delays. To increase the performance of green CAV, the data generated by Autonomous Vehicles (AVs) and associated infrastructure needs to be processed in real-time. Mobile Edge Computing (MEC) is a promising paradigm that can be integrated with green CAV to save energy and to improve the network performance in terms of low latency for data processing. However, MEC servers and other communication entities in green CAV environment cannot be fully trusted and may bring vulnerabilities related to data privacy and security. Motivated by the above challenges, we design a blockchain and Deep-Learning (DL)-enabled secure data processing framework for an edge-envisioned green CAV environment (hereafter referred to as BDEdge). In blockchain-based scheme, all communication entities are registered, verified and thereafter validated using smart contract-based Practical Byzantine Fault Tolerance (PBFT) consensus algorithm. The authenticated data is forwarded to DL scheme. In DL-based scheme, an Intrusion Detection System (IDS) based on a hybrid model of Sparse Auto-Encoder-enabled Attention Bidirectional Gated Recurrent Unit (SAE-ABIGRU) is designed by analyzing the link load behaviors of the MEC-enabled Road Side Unit (RSU) server. The security analysis and comparative simulation findings shows that the proposed BDEdge framework can significantly reduce false alarm rate and increase accuracy close to 99%.

Guest Editorial Special Issue on Space-Air-Ground Integrated Networks for Intelligent Transportation Systems

Next-generation intelligent transportation systems (ITS) are envisioned to greatly improve transportation safety and efficiency by incorporating wireless communications and informatics technologies into transportation systems. As the cornerstone for ITS, vehicular communication networks enable vehicles on the go to exchange information with other vehicles and the external environments, which expect to play a significant role in supporting a variety of services such as road safety, traffic management, and infotainment. However, the existing terrestrial networks including dedicated shortrange communications (DSRC)-based networks and cellular networks alone cannot serve the vehicular applications very well in different scenarios, due to the inherent issues of deployment, coverage, and capacity. It is imperative to exploit other communication infrastructures, such as low-earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and high-altitude platforms, to support vehicular applications better, resulting in space-air-ground integrated networks (SAGIN). SAGIN can provide more comprehensive and three-dimensional network connectivity for moving vehicles, anywhere and anytime, by exploiting their respective advantages in terms of coverage, flexibility, reliability, and availability.

Speech Emotion Recognition Enhanced Traffic Efficiency Solution for Autonomous Vehicles in a 5G-Enabled Space–Air–Ground Integrated Intelligent Transportation System

Speech emotion recognition (SER) is becoming the main human–computer interaction logic for autonomous vehicles in the next generation of intelligent transportation systems (ITSs). It can improve not only the safety of autonomous vehicles but also the personalized in-vehicle experience. However, current vehicle-mounted SER systems still suffer from two major shortcomings. One is the insufficient service capacity of the vehicle communication network, which is unable to meet the SER needs of autonomous vehicles in next-generation ITSs in terms of the data transmission rate, power consumption, and latency. Second, the accuracy of SER is poor, and it cannot provide sufficient interactivity and personalization between users and vehicles. To address these issues, we propose an SER-enhanced traffic efficiency solution for autonomous vehicles in a 5G-enabled space–air–ground integrated network (SAGIN)-based ITS. First, we convert the vehicle speech information data into spectrograms and input them into an AlexNet network model to obtain the high-level features of the vehicle speech acoustic model. At the same time, we convert the vehicle speech information data into text information and input it into the Bidirectional Encoder Representations from Transformers (BERT) model to obtain the high-level features of the corresponding text model. Finally, these two sets of high-level features are cascaded together to obtain fused features, which are sent to a softmax classifier for emotion matching and classification. Experiments show that the proposed solution can improve not only the SAGIN’s service capabilities, resulting in a large capacity, high bandwidth, ultralow latency, and high reliability, but also the accuracy of vehicle SER as well as the performance, practicality, and user experience of the ITS

Multiagent Information Fusion for Connected Driving: A Review

This paper reviews the state-of-the-art multi-sensor fusion approaches applicable in the next-generation intelligent transportation systems where connected vehicles are cooperatively driven for maximum safety and efficiency. The review finds out that complementary sensor fusion in a time-varying distributed network is required, and for such applications, the state-of-the-art is sensor fusion in the random finite set filtering framework. The fundamental bases of random finite set filters are reviewed with more elaboration on a particular filter called the Labeled Multi-Bernoulli filter. An information-theoretic approach for data fusion based on minimizing information divergence between statistical densities is presented, along with how different divergence functions can be used for sensor fusion. Different approaches are evaluated for their tracking performance and computational cost in a realistic simulation scenario. Their advantages, and disadvantages in the context of real-time implementation in a connected driving scenario are discussed.

Interference-Aware Transmission Scheduling for Internet of Vehicles

Next-generation Intelligent Transportation Systems (ITS) use wirelessly connected vehicles for safety and non-safety applications such as autonomous driving, cooperative awareness, route guidance and multimedia transmissions. This network known as the Internet of Vehicles (IoVs) suffers from many challenges such as collisions due to hidden terminals, and interference from simultaneously transmitting vehicles. Moreover, the packet reception ratio of transmissions between vehicles is significantly reduced at high vehicle densities and severe fading scenarios. As safety applications require periodic broadcast of safety messages from each vehicle to all other vehicles in the neighborhood, the development of an efficient medium access technique is a key challenge. In this paper, we propose an interference-aware medium access protocol for vehicular networks that allocate time slots to the vehicles such that interference due to hidden nodes is minimized. We first provide an analytical model to compute the interference range of a vehicle in the presence of simultaneously transmitting vehicles. We also propose a scheduling algorithm that uses vehicle GPS positions and reuse the same time slot only at a distance greater than the interference range. Simulation results show that the proposed technique improves the packet reception ratio by 70% as compared to the standard IEEE 802.11p based CSMA/CA protocol.

Velocity Prediction Based on Vehicle Lateral Risk Assessment and Traffic Flow: A Brief Review and Application Examples

Forecasting future driving conditions such as acceleration, velocity, and driver behaviors can greatly contribute to safety, mobility, and sustainability issues in the development of new energy vehicles (NEVs). In this brief, a review of existing velocity prediction techniques is studied from the perspective of traffic flow and vehicle lateral dynamics for the first time. A classification framework for velocity prediction in NEVs is presented where various state-of-the-art approaches are put forward. Firstly, we investigate road traffic flow models, under which a driving-scenario-based assessment is introduced. Secondly, vehicle speed prediction methods for NEVs are given where an extensive discussion on traffic flow model classification based on traffic big data and artificial intelligence is carried out. Thirdly, the influence of vehicle lateral dynamics and correlation control methods for vehicle speed prediction are reviewed. Suitable applications of each approach are presented according to their characteristics. Future trends and questions in the development of NEVs from different angles are discussed. Finally, different from existing review papers, we introduce application examples, demonstrating the potential applications of the highlighted concepts in next-generation intelligent transportation systems. To sum up, this review not only gives the first comprehensive analysis and review of road traffic network, vehicle handling stability, and velocity prediction strategies, but also indicates possible applications of each method to prospective designers, where researchers and scholars can better choose the right method on velocity prediction in the development of NEVs.

Secure V2V and V2I Technologies for the Next-Generation Intelligent Transportation Systems

This installment of Computer’s series highlighting the work published in IEEE Computer Society journals comes from IEEE Transactions on Services Computing. The article focuses on next generation intelligent transportation systems.

Positioning Performance Limits of GNSS Meta-Signals and HO-BOC Signals.

Global Navigation Satellite Systems (GNSS) are the main source of position, navigation, and timing (PNT) information and will be a key player in the next-generation intelligent transportation systems and safety-critical applications, but several limitations need to be overcome to meet the stringent performance requirements. One of the open issues is how to provide precise PNT solutions in harsh propagation environments. Under nominal conditions, the former is typically achieved by exploiting carrier phase information through precise positioning techniques, but these methods are very sensitive to the quality of phase observables. Another option that is gaining interest in the scientific community is the use of large bandwidth signals, which allow obtaining a better baseband resolution, and therefore more precise code-based observables. Two options may be considered: (i) high-order binary offset carrier (HO-BOC) modulations or (ii) the concept of GNSS meta-signals. In this contribution, we assess the time-delay and phase maximum likelihood (ML) estimation performance limits of such signals, together with the performance translation into the position domain, considering single point positioning (SPP) and RTK solutions, being an important missing point in the literature. A comprehensive discussion is provided on the estimators’ behavior, the corresponding ML threshold regions, the impact of good and bad satellite constellation geometries, and final conclusions on the best candidates, which may lead to precise solutions under harsh conditions. It is found that if the receiver is constrained by the receiver bandwidth, the best choices are the L1-M or E6-Public Regulated Service (PRS) signals. If the receiver is able to operate at 60 MHz, it is recommended to exploit the full-bandwidth Galileo E5 signal. In terms of robustness and performance, if the receiver can operate at 135 MHz, the best choice is to use the GNSS meta-signals E5 + E6 or B2 + B3, which provide the best overall performances regardless of the positioning method used, the satellite constellation geometry, or the propagation conditions.

Detecting Sybil Attacks Using Proofs of Work and Location in VANETs

Vehicular Ad Hoc Networks (VANETs) have the potential to enable the next-generation Intelligent Transportation Systems (ITS). In ITS, data contributed by vehicles can build a spatio-temporal view of traffic statistics, which can improve road safety and reduce slow traffic and jams. To preserve drivers’ privacy, vehicles should use multiple pseudonyms instead of only one identity. However, vehicles may exploit this abundance of pseudonyms and launch Sybil attacks by pretending to be multiple vehicles. Then, these Sybil (or fake) vehicles report false data, e.g., to create fake congestion or pollute traffic management data. In this article, we propose a Sybil attack detection scheme using proofs of work and location. The idea is that each road side unit (RSU) issues a signed time-stamped tag as a proof for the vehicle’s anonymous location. Proofs sent from multiple consecutive RSUs are used to create a trajectory which is used as vehicle anonymous identity. Also, contributions from one RSU are not enough to create trajectories, rather the contributions of several RSUs are needed. By this way, attackers need to compromise an infeasible number of RSUs to create fake trajectories. Moreover, upon receiving the proof of location from an RSU, the vehicle should solve a computational puzzle by running proof of work (PoW) algorithm. Then, it should provide a valid solution (proof of work) to the next RSU before it can obtain a proof of location. Using the PoW can prevent the vehicles from creating multiple trajectories in case of low-dense RSUs. To report an event, the vehicle has to send the latest trajectory to an event manager. Then, the event manager uses a matching technique to identify the trajectories sent from Sybil vehicles. The scheme depends on the fact that the Sybil trajectories are bounded physically to one vehicle, and therefore, their trajectories should overlap. Extensive experiments and simulations demonstrate that our scheme achieves high detection rate of Sybil attacks with low false negative and acceptable communication and computation overhead.

Robust Positioning for Road Information Services in Challenging Environments

Next-generation Intelligent Transportation Systems (ITS) of future road traffic monitoring will be required to provide reports on traffic status, road conditions, and driver behaviour. Road surface anomalies contribute to increasing the risk of traffic accidents, reduced driver comfort and increased vehicles’ damage. The conventional integrated Global Navigation Satellite System (GNSS)/Inertial Navigation System (INS) positioning solutions can suffer from errors because of inertial sensor noises and biases, especially when low-cost and commercial grade inertial sensors are used. In this work, we use a reduced inertial sensor system utilizing Micro-Electro-Mechanical-System (MEMS) based inertial sensors, to integrate with the GNSS receiver and provide robust positioning in urban canyons. To provide acceptable performance in challenging urban environments, our method de-noises the MEMS-based inertial sensor measurements using a technique based on a Bi-orthonormal search, which separates the monitored motion dynamics from both the inertial sensor bias errors and high-frequency noises. As a result, the performance of the positioning system is improved, providing reliable positioning accuracy during extended GNSS outages that occur in various areas. To show the significant enhancement achieved by the proposed approach, we examined the system performance over three road test trajectories involving MEMS-based inertial sensors and GNSS receivers mounted on our test vehicle. The superior performance of our proposed INS/GNSS integrated positioning system is demonstrated in this paper during various GNSS outages, in different areas, and under multiple driving scenarios.

Estimating ambient visibility in the presence of fog: a deep convolutional neural network approach

Next-generation intelligent transportation systems are based on the acquisition of ambient data that influence traffic flow and safety. Among these, is the ambient visibility range whose estimation, in the presence of fog, is extremely useful for next-generation intelligent transportation systems. However, existing camera-based approaches are based on “engineered features” extraction methods that use computer algorithms and procedures from the image processing field. In this contribution, a novel approach to estimate visibility range under foggy weather conditions is proposed which is based on “learned features” instead. More precisely, we use AlexNet deep convolutional neural network (DCNN), trained with raw image data, for feature extraction and a support vector machine (SVM) for visibility range estimation. Our quantitative analysis showed that the proposed approach is very promising in estimating the visibility range with very good accuracy. The proposed solution can pave the way towards intelligent driveway assistance systems to enhance awareness of driving weather conditions and hence mitigate the safety risks emanating from fog-induced low visibility conditions.

Deep Intelligent Prediction Network: A Novel Deep Learning Based Prediction Model on Spatiotemporal Characteristics and Location Based Services for Big Data Driven Intelligent Transportation System

The concept of big Data for intelligent transportation system has been employed for traffic management on dealing with dynamic traffic environments. Big data analytics helps to cope with large amount of storage and computing resources required to use mass traffic data effectively. However these traditional solutions brings us unprecedented opportunities to manage transportation data but it is inefficient for building the next-generation intelligent transportation systems as Traffic data exploring in velocity and volume on various characteristics. In this article, a new deep intelligent prediction network has been introduced that is hierarchical and operates with spatiotemporal characteristics and location based service on utilizing the Sensor and GPS data of the vehicle in the real time. The proposed model employs deep learning architecture to predict potential road clusters for passengers. It is injected as recommendation system to passenger in terms of mobile apps and hardware equipment employment on the vehicle incorporating location based services models to seek available parking slots, traffic free roads and shortest path for reach destination and other services in the specified path etc. The underlying the traffic data is classified into clusters with extracting set of features on it. The deep behavioural network processes the traffic data in terms of spatiotemporal characteristics to generate the traffic forecasting information, vehicle detection, autonomous driving and driving behaviours. In addition, markov model is embedded to discover the hidden features .The experimental results demonstrates that proposed approaches achieves better results against state of art approaches on the performance measures named as precision, execution time, feasibility and efficiency.

Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and the Way Forward

Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services. Such a transformation---which will be fuelled by concomitant advances in technologies for machine learning (ML) and wireless communications---will enable a future vehicular ecosystem that is better featured and more efficient. However, there are lurking security problems related to the use of ML in such a critical setting where an incorrect ML decision may not only be a nuisance but can lead to loss of precious lives. In this paper, we present an in-depth overview of the various challenges associated with the application of ML in vehicular networks. In addition, we formulate the ML pipeline of CAVs and present various potential security issues associated with the adoption of ML methods. In particular, we focus on the perspective of adversarial ML attacks on CAVs and outline a solution to defend against adversarial attacks in multiple settings.

Traffic model of machine‐type communication for railway signal equipment based on MMPP

Machine-to-machine communication can realise considerably better information cognition of fixed and mobile equipment during rail transit. To assess the network access performance of the machine-type communication (MTC) of railway signal equipment for next-generation intelligent transportation system, the forecasting model of the machine communication traffic of railway signal equipment was divided into station indoor model, station outdoor model, and section movement model on the basis of cell units, and the traffic quantity and signaling overhead of the three models were calculated respectively. Based on Poisson's distribution and the Markov update process, an improved Markov-modulated Poisson Process (IMMPP) of the source traffic model was designed. Compared with the 3GPP traffic model, the IMMPP model maintains a good balance between the complexity and the relatively high accuracy of the signal equipment in the station outdoor and section scenarios. The simulation experiments showed that the IMMPP consumed 0.44 s more than 3GPP model 2 in the section scenario and 1.99 s in the station outdoor scenario, and the simulation equipment was in accordance with the actual railway signal equipment. The research result can provide a reference for the description of MTC traffic of other specialised equipment in the railway environment.

Centimeter-Grade Metropolitan Positioning for Lane-Level Intelligent Transportation Systems Based on the Internet of Vehicles

This paper presents a centimeter-grade metropolitan positioning (CGMP) framework for achieving lane-level localization through Internet of Vehicles (IoV) communications. The CGMP framework integrates vehicle-to-roadside (V2R) and vehicle-to-vehicle (V2V) communications with installed roadside/intersection cameras to provide positioning information to vehicles on the road. This framework can be used to estimate the precise position of a vehicle and detect the lane of each vehicle. The estimated positions and detected lanes can be broadcast to nearby vehicles through V2R and V2V communications. According to our review of relevant research, CGMP is the first positioning system to provide the following features: centimeter-grade positioning accuracy through IoV communications that can detect a vehicle's current lane; the employment of existing roadside/intersection cameras, thus keeping additional construction costs low; and an innovative infrastructure for the application of next-generation intelligent transportation systems that can enable lane-level traffic control, collision avoidance, and vehicle navigation. A prototype based on wireless access in vehicular environments/dedicated short-range communications is implemented to verify the feasibility and effectiveness of the proposed framework. The experimental results indicate that fully deployed CGMP can achieve centimeter-grade positioning accuracy with the error around 10 cm, and partially deployed CGMP can significantly reduce the positioning errors of existing localization methods.

MAC2: Enabling multicasting and congestion control with multichannel transmission for intelligent vehicle terminal in Internet of Vehicles

Internet of Vehicles has become a promising way to realize the evolution from vehicular ad hoc networks and next-generation intelligent transportation system into future autonomous driving scenarios, clean-energy intelligent vehicles, and Smart Cities. However, multicasting service messages on available service channels and periodic exchanges of beacon messages on control channel cause the problem of efficiently scheduling those messages via multichannel transmission for intelligent vehicle terminal, to support real-world applications in Internet of Vehicles scenario. In this article, we investigate the intelligent vehicle terminal architecture and, particularly, design the wireless communication board by incorporating multicasting and congestion control modules. Especially, we present a multicast data delivery scheme with random-delay lowest-cost constraint to transfer service messages on service channels. Furthermore, a priority-aware congestion control scheme is also proposed by considering differentiated priorities of beacon messages on control channel, to cope with the congestion problem at bottleneck vehicle node. Based on the proposed schemes, we build up the RanLow (Random-delay Lowest-cost) module and the priority-aware congestion control (PARCEL) module by enabling multicasting and congestion control together in wireless communication board of the intelligent vehicle terminal architecture. Finally, the experimental results and comparison show that our devised RanLow module and PARCEL module are feasible and more efficient than existing schemes.

Vehicle-to-barrier communication during real-world vehicle crash tests

Vehicle-to-barrier (V2B) communication is expected to facilitate wireless interactions between vehicles and roadside barriers in next-generation intelligent transportation systems. V2B systems will help mitigate single-vehicle, run-off-road crashes, which account for more than 50% of roadside crash fatalities. In this work, the characteristics of the wireless channel prior to and during a crash are analyzed using orthogonal frequency division multiplexing (OFDM) techniques, which has been used in existing vehicular communication systems. More specifically, the performance of OFDM-based V2B links are measured in real-world crash tests for the first time. Three crash tests conducted at the Midwest Roadside Safety Facility, Lincoln, Nebraska, are reported: a bogie vehicle crashing into a soil-embedded post at 27 mph, a sedan crashing to a concrete curb at 15 mph, and a pickup crashing to a steel barrier at 62 mph. Metrics including signal to interference plus noise ratio received signal strength, error vector magnitude, phase error, channel coherence, and bit error rate, are used to illustrate the impacts of antenna type, antenna deployment, speed, and mobility during the crash tests. The empirical evidence shows that barrier-height (0.7–0.9 m) antennas at the barrier can improve V2B signal quality compared to higher deployments (≥1.5 m) due to the stronger reflection of electromagnetic waves at a larger angle of incidence. Moreover, compared to omni-directional barrier antennas, directional barrier antennas can increase signal quality, connectivity, and coherence time of V2B channel because of reduced multi-path effects, however, the antenna orientation needs to be carefully determined to maintain connectivity.

Instantaneous communication capacities of vehicular ad hoc networks

Wireless communications among vehicles, roadside infrastructures, and traffic management centers can enable the development of next-generation Intelligent Transportation Systems so as to tackle basic traffic problems associated with driving safety, road congestion, and vehicle emissions. This paper analytically investigates the instantaneous communication capacities of vehicular ad hoc networks (VANETs), which measure the upper bounds of the message transmission rates of vehicles. Subject to interference among wireless transmissions, the broadcast capacity is defined by the maximum number of successful receivers, and the unicast capacity by the maximum number of successful senders. With the protocol communication model and uniform vehicular traffic patterns, we derive closed-form formulas for the capacities as functions of transmission range r, interference ratio δ, vehicular density ρ, and channel capacity W. We show that broadcast capacities are approximately W(2+δ)rρ+1 for uni-directional communications, and 2W(2+δ)rρ+1 for bi-directional communications; while unicast capacities are approximately W(1+δ)rρ+1 for uni-directional communications, and W(1+δ)rρ+1 for bi-directional communications. For general vehicular traffic patterns, an optimization model is proposed to calculate the capacities, and a genetic algorithm integrated with the protocol communication model is developed to solve the optimization problem. Finally, the impacts of different transmission ranges, interference ratios, and shock waves on communication capacities are analyzed.