Search

Driver identification has shown sustainable development in recent years in a wide variety of applications including but not limited to security, personalization, fleet management, insurance telematics, or ride-hailing. However, the current progress suffers from several challenges such as costly data collections and the need for a huge amount of data from each individual for both driver identification and impostor detection. Therefore, more novel and efficient solutions are required to mitigate the existing challenges. In this paper, we address driver identification and impostor detection tasks using driving behavior analysis of the drivers. We design a deep learning-based system architecture that analyzes windows of 30 seconds of driving data to capture the unique underlying characteristics of the individuals steering behavior based on which it further distinguishes the drivers. We also develop a novel strategy to tackle driver verification and impostor detection tasks based on the combination of the proposed system architecture and Siamese networks concepts. We map the steering behavior of the drivers into latent representations which can be later used to train a similarity function. The performance of the proposed systems is tested over a real-world dataset of 95 drivers. The evaluation results indicate that our system outperforms well-established benchmarks and baseline methodologies. [ABSTRACT FROM AUTHOR]

The advent of in-vehicle networking systems as well as state-of-the-art sensors and communication technologies have facilitated the collection of large volume and almost real-time data on vehicles and drivers, thus opening up future possibilities. Processing and analyzing this data provides unprecedented opportunities to offer remarkable insights and solutions for driving behavior analysis (DBA). Characterizing driving behavior plays a key role in a variety of research areas such as traffic safety, the development of automated vehicles, energy and fuel management, risk assessment, and driver identification and profiling. Advances in DBA-based driver inattention or drunk driver detection can help reduce fatal car crashes, and understanding the driving style (e.g. eco-friendly or aggressive) of drivers can contribute to fuel management and risk assessment of the drivers. These facts have led to a growing interest in addressing DBA challenges. This paper aims to present the state-of-the-art methodologies for DBA and provide a clear roadmap about the main current and future trends in DBA. To this end, we propose categorizing the current research on driving behavior based on the types of data employed for the analysis, the ultimate goals of the analysis, and the techniques based on which the driving data are modeled. We provide an overview of different data resources and available datasets for DBA. Moreover, we discuss the application of DBA along with the key research challenges in this field and potential future directions. [ABSTRACT FROM AUTHOR]

The increasing availability of vehicular trajectory data is at the core of smart mobility solutions. Such data offer us unprecedented information for the development of trajectory data mining-based applications. An essential task of trajectory analysis is the employment of efficient and accurate methods to compare trajectories. This work presents a systematic survey of vehicular trajectory similarity measures and provides a panorama of the research field. First, we show an overview of vehicle trajectory data, including the models and some preprocessing techniques. Then, we give a comprehensive review of methods to compare trajectories and their intrinsic properties. We classify the methods according to the trajectory representation and features such as metricity, computational complexity, and robustness to noise and local time shift. Last, we discuss the applications of vehicular trajectory similarity measures and some open research problems. [ABSTRACT FROM AUTHOR]

Vehicular network technology is frequently used to provide several services and applications for drivers on road networks. The proposed applications in the environment of road networks are classified into three main categories based on their functions: safety, traffic efficiency, and entertainment. The traffic efficiency services are designed to enhance the moving fluency and smoothness of traveling vehicles over the road network. The grid layout architecture of the downtown areas provides several routes toward any targeted destination. Moreover, since several conflicted traffic flows compete at the road intersections, many vehicles have to stop and wait for safe situations to pass the road intersection without coming into conflict with other vehicles. The traffic efficiency applications in this scenario are designed to select the most efficient path for vehicles traveling toward their targeted destination/destinations. Moreover, other applications aimed to decrease the queuing delay time for vehicles at road intersections. In this article, we review several recently proposed mechanisms that worked to enhance the fluency of traffic over downtown road networks and point to the expected future trends in this field. [ABSTRACT FROM AUTHOR]

In this article, we focus on the usage of MQTT (Message Queuing Telemetry Transport) within Connected Vehicles (CVs). Indeed, in the original version of MQTT protocol, the broker is responsible “only” for sending received data to subscribers; abstracting then the underlying mechanism of data exchange. However, within CVs context, subscribers (i.e., the processing infrastructure) may be overloaded with irrelevant data, in particular when the requirement is real or near real-time processing. To overcome this issue, we propose MQTT-CV; a new variant of MQTT protocol, in which the broker is able to perform local processing in order to reduce the workload at the infrastructure; i.e., filtering data before sending them. In this article, we first validate formally the correctness of MQTT-CV protocol (i.e., the three components of the proposed protocol are correctly interacting), through the use of Promela language and its system verification tool; the model checker SPIN. Secondly, using real-world data provided by our car manufacturer partner, we have conducted real implementation and experiments. The obtained results show the effectiveness of our approach in term of data workload reduction at the processing infrastructure. The mean improvement, besides the fact that it is dependent of the target application, was in general about 10 times less in comparison to native MQTT protocol. [ABSTRACT FROM AUTHOR]

Automated Vehicle Classification (AVC) based on vision sensors has received active attention from researchers, due to heightened security concerns in Intelligent Transportation Systems. In this work, we propose a categorization of AVC studies based on the granularity of classification, namely Vehicle Type Recognition, Vehicle Make Recognition, and Vehicle Make and Model Recognition. For each category of AVC systems, we present a comprehensive review and comparison of features extraction, global representation, and classification techniques. We also present the accuracy and speed-related performance metrics and discuss how they can be used to compare and evaluate different AVC works. The various datasets proposed over the years for AVC are also compared in light of the real-world challenges they represent, and those they do not. The major challenges involved in each category of AVC systems are presented, highlighting open problems in this area of research. Finally, we conclude by providing future directions of research in this area, paving the way toward efficient large-scale AVC systems. This survey shall help researchers interested in the area to analyze works completed so far in each category of AVC, focusing on techniques proposed for each module, and to chalk out strategies to enhance state-of-the-art technology. [ABSTRACT FROM AUTHOR]

Vehicular ad hoc networks (VANETs) experience large-scale high-speed mobility and volatile topology. VANETs may therefore experience intermittent connections and may occasionally be unable to guarantee end-to-end connections. This gives the medium access control (MAC) layer the opportunity to adapt its transmission strategy to the current unstable wireless connections to improve transmission efficiency. In this paper, we propose an adaptive frame length aggregation scheme (AFLAS) for VANETs, which is designed to improve transmission efficiency and increase data throughput. In our scheme, the incoming data packets from higher layers are queued separately in the MAC layer to wait for transmission opportunities. Suitable aggregation frame lengths are calculated according to the current wireless status and applied in the MAC layer at the onset of data transmissions. In this paper, we analyze and apply our AFLAS strategy to two current frame aggregation schemes in IEEE 802.11. We also report on the performance evaluation of our scheme. Our results exhibit significant improvement results in data throughput, retransmissions, overheads, and transmission efficiency in comparison with nonadaptive aggregation schemes. [ABSTRACT FROM PUBLISHER]

In this paper, we propose and evaluate unexplored approaches for real-time automated vehicle make and model recognition (VMMR) based on a bag of speeded-up robust features (BoSURF) and demonstrate the suitability of these approaches for vehicle identification systems. The proposed approaches use SURF features of vehicles' front- or rear-facing images and retain the dominant characteristic features (codewords) in a dictionary. Two schemes of dictionary building are evaluated: “single dictionary” and “modular dictionary.” Based on the optimized dictionaries, the SURF features of vehicles' front- or rear-face images are embedded into BoSURF histograms, which are used to train multiclass support vector machines (SVMs) for classification. Two real-time VMMR classification schemes are proposed and evaluated: a single multiclass SVM and an ensemble of multiclass SVM based on attribute bagging. The processing speed and accuracy of the VMMR system are affected greatly by the size of the dictionary. The tradeoff between speed and accuracy is studied to determine optimal dictionary sizes for the VMMR problem. The effectiveness of our approaches is demonstrated through cross-validation tests on a recent publicly accessible VMMR data set. The experimental results prove the superiority of our work over the state of the art, in terms of both processing speed and accuracy, making it highly applicable to real-time VMMR systems. [ABSTRACT FROM PUBLISHER]

Vehicular networking is an emerging technology that offers the potential of providing a variety of new services. However, extending vehicular networks to include internet protocol (IP) connections is still problematic, due in part to the incompatibility of mobile IP handovers with the increased mobility of vehicles. The handover process, consisting of discovery, registration, and packet forwarding, has a large overhead and disrupts connectivity. With increased handover frequency and smaller access-point (AP) dwell times in vehicular networks, the handover causes a large degradation in performance. This paper proposes a predictive handover protocol, using a combination of a Kalman filter (KF) and an online hidden Markov model (HMM), to minimize the effects of prediction errors and to capitalize on advanced handover registration. Extensive simulated experiments were carried out in the network simulator ns-2 to study the performance of the proposed protocol within a variety of traffic and network topology scenarios. Results show a significant improvement to both prediction accuracy and network performance when compared with recent proposed approaches. [ABSTRACT FROM PUBLISHER]

Detecting large animals on roadways using automated systems such as robots or vehicles is a vital task. This can be achieved using conventional tools such as ultrasonic sensors, or with innovative technology based on smart cameras. In this paper, we investigate a vision-based solution. We begin the paper by performing a comparative study between three detectors: 1) Haar-AdaBoost; 2) histogram of oriented gradient (HOG)-AdaBoost; and 3) local binary pattern (LBP)-AdaBoost, which were initially developed to detect humans and their faces. These detectors are implemented, evaluated, and compared to each other in terms of accuracy and processing time. Based on our evaluation and comparison results, we design a two-stage architecture which outperforms the aforementioned detectors. The proposed architecture detects candidate regions of interest using LBP-AdaBoost in the first stage, which offers robustness to false positives in real-time conditions. The second stage is based on support vector machine classifiers that were trained using HOG features. The training data are generated from our novel dataset called large animal dataset, which contains common and thermographic images of large road-animals. We emphasize that no such public dataset currently exists. [ABSTRACT FROM PUBLISHER]

In this paper, we propose an intelligent traffic light controlling (ITLC) algorithm. ITLC is intended to schedule the phases of each isolated traffic light efficiently. This algorithm considers the real-time traffic characteristics of the competing traffic flows at the signalized road intersection. Moreover, we have adopted the ITLC algorithm to design a traffic scheduling algorithm for an arterial street scenario; we have thus proposed an arterial traffic light (ATL) controlling algorithm. In the ATL controlling algorithm, the intelligent traffic lights installed at each road intersection coordinate with each other to generate an efficient traffic schedule for the entire road network. We report on the performance of ITLC and ATL algorithms for several scenarios using NS-2. From the experimental results, we infer that the ITLC algorithm reduces, at each isolated traffic light, the queuing delay and increases the traffic fluency by 30% compared with the online algorithm (OAF) traffic light scheduling algorithm. The latter algorithm achieved the best performance when compared with the OAF traffic light scheduling algorithm. On the other hand, the ATL controlling algorithm increases the traffic fluency of traveling vehicles at arterial street coordinations by 70% more than the random and separate traffic light scheduling system. Furthermore, compared with the previously introduced traffic scheduling ART-SYS, the ATL controlling algorithm decreases the average delay at each traffic light by 10%. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel vision-based detection system able to extend the detection range of vehicles or mobile robots. The proposed system is used to detect and track moving targets from near-to-far ranges and covers a wide range of more than 130 m without decreasing detection accuracy. Typical examples of targets include traffic signs, vehicles, animals, and pedestrians. In this paper, the detection and tracking of moving pedestrians from near-to-far ranges is investigated. The proposed system is composed of two identical cameras. The first camera is equipped with a short focal length lens to detect and track pedestrians in near-to-mid range, and the second camera with a long focal length lens is used to detect and track pedestrians in mid-to-far range. To synchronize the detection results of both cameras and to eliminate repeated measurements, two synchronization algorithms were developed. The tracking process is applied after the detection, and it is used to track and predict the future motion and direction of pedestrian. To prevent vehicle-target collisions, two algorithms that generate alert and danger warnings are developed. A mathematical model based on the fundamental physics of the camera and lens is developed to illustrate the feasibility of our work. Finally, we conducted many experiments in large open-air parking lots and on Ottawa roads to show the applicability of our system. [ABSTRACT FROM AUTHOR]

Accompanying the increasing interest in vehicle ad hoc networks (VANETs), there is a request for high-quality and real-time video streaming on a VANET, for safety and infotainment applications. Video streaming on a VANET faces extra issues, in comparison with the video streaming on a mobile ad hoc network (MANET), such as the highly dynamic topology. However, there are also benefits to VANETs, such as large buffer and battery capacity, predictable motion of vehicles, and powerful central and graphic processing units (CPU and GPU, respectively). However, the high packet loss ratio of a VANET is a critical issue for high-quality video streaming. In this paper, we propose an error recovery process for high-quality and real-time video streaming in a VANET, which is call multichannel error recovery video streaming (MERVS). MERVS transmits the video through two different channels: a reliable channel and an unreliable channel. Because of the importance of the intraframes (I-frames) in terms of video quality, I-frames will be transmitted through the reliable channel. The interframes will be transmitted through the unreliable channel because of the limited resource of the reliable channel. The priority queue, quick start, and scalable reliable channel (SRC) techniques are also integrated to improve the delay of MERVS. Based on the conducted simulation results, MERVS can provide higher quality video streaming compared with forward error correction (FEC) with similar time delay compared with the real-time transport protocol/user datagram protocol (RTP/UDP) in a VANET. [ABSTRACT FROM PUBLISHER]

The evolution of vehicular network applications, from simple alert message exchange to more elaborate and sophisticated systems, boosts the need for content delivery solutions. A useful technique, in this case, is content replication, in which strategically selected vehicles replicate content and help in the delivery process. However, content replication is particularly challenging in vehicular networks, due to their special characteristics, such as highly dynamic topology, diverse density, and large-scale scenarios. Although there has been progress in routing and dissemination solutions for vehicular networks, few studies have concentrated on the content replication problem. To address this issue, we propose an origin–destination-based content replication (ODCRep) solution that focuses on balancing the number of replicas across the application area. Differently from existing solutions, ODCRep relies only on the origin–destination information and uses computationally efficient algorithms. Results from exhaustive simulations show that ODCRep can achieve high coverage, yet can also consume fewer resources than existing solutions. [ABSTRACT FROM PUBLISHER]

IEEE 802.11 is an economical and efficient standard that has been applied to vehicular networks. However, the long handoff latency of the standard handoff scheme for IEEE 802.11 has become an important issue for seamless roaming in vehicular environments, because more handoffs may be triggered due to the higher mobility of vehicles. This paper presents a new and fast location-based handoff scheme particularly designed for vehicular environments. With the position and movement direction of a vehicle and the location information of the surrounding access points (APs), our protocol is able to accurately predict several APs that the vehicle may possibly visit in the future and to assign these APs different priority levels. APs on higher priority levels will be scanned first. A blacklist scheme is also used to exclude those APs that showed no response to the scanning during previous handoffs. Thus, time spent on scanning APs is supposed to be significantly reduced. The simulation results show that the proposed scheme attains not only a lower prediction error rate but also lower link layer handoff latency and that it has a smaller influence on jitter and throughput. Moreover, these results show that the proposed scheme has a smaller total number of handoffs than other handoff schemes. [ABSTRACT FROM PUBLISHER]

In recent years, we have witnessed a growing interest in Vehicular Networks from both the research community and industry. Several potential applications of Vehicular Networks are envisioned such as road safety and security, streaming services, traffic monitoring and driving comfort, just to mention a few. It is critical that the existence of convenience or driving comfort services do not negatively affect the performance of safety services. In essence, the dissemination of safety services or the discovery of convenience applications require the communication among service providers and service requesters through constrained bandwidth resources. Therefore, service discovery techniques for vehicular networks must efficiently use the available common resources. In this paper, we present a bandwidth-efficient and scalable hybrid adaptive service discovery protocol (VSDP) for Vehicular Networks. VSDP aims at providing high success ratio while guaranteeing low response time and good scalability when the number of requests increases. Our proposed protocol finds the service provider and its routing information simultaneously which results in overall bandwidth savings. It uses diverse channels to exchange discovery and routing packets, thereby decreasing the congestion on single channels and decreasing the delay of service discovery. Our proposed service discovery protocol adapts the advertisement zone size of service providers based on an efficient adaptation mechanism that takes into consideration network condition and application requirements. The adaptation process is based on an adjustment technique and a prediction technique. We discuss the implementation of our protocol, present its proof of correctness as well as the performance evaluation through an extensive set of simulation experiments and using different mobility models. Our results show the scalability of our protocol. They indicate that our techniques can achieve significant success rate (more than 90 percent), while guaranteeing low response time (in the order of milliseconds) and low bandwidth usage when compared to existing service discovery techniques. [ABSTRACT FROM AUTHOR]

Vehicular Ad hoc Networks (VANETs) are emerging as a promising approach to improving traffic safety and providing a wide range of wireless applications for all road users. This paper addresses an improved authentication scheme for Radio frequency identification (RFID) applied in VANETs. As often being considered as a precondition for the realization of IoT, RFID can be utilized in the vehicles, so as to make the vehicles identifiable and inventoriable by computers as long as they are fitted out with radio tags. One of the public concerns is likely to focus on a certain large number of security and privacy issues. A few light symmetric key management schemes have been proposed for RFID scenarios. However, as we mentioned already, the authentication methodologies of those light symmetric key management schemes, especially in the scenarios of RFID, are still at an initial phase and call for enormous research efforts. We propose a certificate revocation status validation scheme called EKA2, using the concept of clustering from data mining to evaluate the trustiness of digital certificates. [ABSTRACT FROM PUBLISHER]

In vehicular ad hoc networks (VANETs), network services and applications (e.g., safety messages) require an exchange of vehicle and event location information. The data are exchanged among vehicles within each vehicle's respective radio communication range through direct communication. In reality, direct communication is susceptible to interference and blocked by physical obstacles, which prevent the proper exchange of information about localization information. Obstacles can create a state of nonline of sight (NLOS) between two vehicles, which restricts direct communication even when corresponding vehicles exist within each other's physical communication range, thus preventing them from exchanging proper data and affecting the localization services' integrity and reliability. Dealing with such obstacles is a challenge in VANETs as moving obstacles such as trucks are parts of the network and have the same characteristics of a VANET node (e.g., high-speed mobility and change of driving behavior). In this paper, we present a location verification protocol among cooperative neighboring vehicles to overcome an NLOS condition and secure the integrity of localization services for VANETs. The simulation results showed improvement in neighborhood awareness under NLOS conditions. A solution such as that we propose will help to maintain localization service integrity and reliability. [ABSTRACT FROM PUBLISHER]

The increasing number of potential applications related to intelligent transportation systems (ITSs) have attracted researchers to the area of vehicular networks (VNs). Two main classes of applications have lately gained popularity, i.e., security and safety, and traffic information and service location applications. However, several open research challenges are delaying the efficient and widespread deployment and management of such applications in VNs. One of these challenges comprises how vehicles and service providers could discover each other in VNs, which are well known for their large scale and high mobility. Most service discovery strategies available present high overhead and poor performance in a VN environment. Existing context-aware and location-based service discovery protocols (LocVSDPs) are either designed without considering the particularities of VNs or are not scalable with the increase in network density and the number of requests. In this paper, we propose a new context-aware and LocVSDP (EB-LocVSDP) for VNs and its variant (Naive-LocVSDP). Our protocols offer a scalable framework for the discovery of time-sensitive and location-based services in VNs. They rely on a cluster-based infrastructure. Furthermore, LocVSDPs are integrated into the network layer and use channel diversity to improve service discovery efficiency. We discuss the implementation of our protocols and techniques, report on performance evaluation experiments, and offer a comparison against an existing location-based discovery protocol [the Vehicular Information Transfer Protocol (VITP)]. Our simulation results indicate that our proposed LocVSDPs show a gain of 20% in terms of success rate. LocVSDPs use at least 90% less bandwidth than VITP, and their average response time is at least 10% lower than VITP for successful query transactions. [ABSTRACT FROM PUBLISHER]

Intelligent transportation systems (ITSs) are gaining momentum among researchers. ITS encompasses several technologies, including wireless communications, sensor networks, voice and data communication, real-time driving-assistant systems, etc. These state-of-the-art technologies are expected to pave the way for a plethora of vehicular network applications. However, ITS faces difficult issues when trying to widely deploy such networks and applications. The interconnection of different networks, even in the case of the Internet, is one of the main difficulties that is delaying the wide spread of vehicular networks. In this paper, we present a novel gateway discovery technique for vehicular ad hoc networks (VANets). Our protocol aims to provide an efficient hybrid adaptive Location-Aided Gateway Advertisement and Discovery (LAGAD) mechanism for VANets. First, it permits gateway clients to discover nearby gateways; then, gateways keep advertising themselves to their clients to permit client information about the route toward the discovered gateway without having to resort to reactive route discovery. We discuss the implementation of our algorithm and present its proof of correctness, in addition to the performance evaluation demonstrated through an extensive set of simulation experiments using a Manhattan mobility model. Our results indicate that our LAGAD scheme is scalable and that a significant success rate could be achieved using our algorithm while guaranteeing low response time (on the order of milliseconds) and low bandwidth usage when compared with other gateway discovery approaches. Moreover, our results indicate that LAGAD achieves a high delivery ratio of data packets, as well as a low end-to-end delay, and permits duplicate and ordered data packet reception at the destination gateway. [ABSTRACT FROM PUBLISHER]