An Efficient and Robust Moving Shadow Removal Algorithm and Its Applications in ITS

Intelligent Transport System (ITS) applications are focused on improving road safety and creating new transport services. To realize the potential of ITS applications, data exchange should be efficiently carried out through direct communication over short distances both between vehicles (V2V) and between vehicles and infrastructure (V2I). High demands are placed on ITS performance indicators. These requirements are increasing especially in the context of the new mobility patterns using autonomous vehicles. The ITS big data processing can be centralized or distributed. The centralized approach utilizes the power of cloud computing. In contrast to cloud computing, intelligent data processing with faster responses and higher quality can be provided by fog computing. Fog computing is a horizontal, system-level architecture that distributes computing, storage, control and networking functions closer to the users along a cloud-to-thing continuum. Implementing fog computing in the dynamic environment of ITS to provide real-time big data analytics is facing many challenges that are not covered by previous research studies. The article analyzes the availability of V2I services in distributed communication network of ITS with fog-based architecture from reliability point of view. The dependability of V2I services for end users of smart vehicle in fog operating ITS is defined. The mathematical model of the reliability of a separate dedicated service in fog-based ITS for end user applications in the real conditions of operation is developed.

Meeting privacy challenges while advancing intelligent transportation systems

The 5.9 GHz band has been earmarked in many countries for Intelligent Transportation Systems (ITS) applications. Cellular V2X (C-V2X)—a recently developed access technology for vehicle-to-everything (V2X) communications—is a candidate technology to provision ITS applications using the 5.9 GHz band. Due to the ever-increasing popularity of Wi-Fi and search for additional unlicensed bands, in the US and Europe, regional regulators have previously considered allowing co-channel Wi-Fi operations in the ITS band on a secondary basis to the incumbent ITS technology. Additionally, there are several Wi-Fi channel configurations, some already in operation while others still under consideration, which place Wi-Fi and C-V2X devices in adjacent bands. It is, therefore, likely that CV2X users may be susceptible to interference from Wi-Fi devices operating both in co-channel scenarios and in adjacent bands. To make an informed decision on future Wi-Fi channelization in and around the ITS band, a detailed study on the impact of these Wi-Fi transmissions on the system performance of C-V2X is extremely essential. In this paper, through a comprehensive and systematic simulation study, we investigate the impact of Wi-Fi transmissions on the performance of C-V2X, both in co-channel and adjacent channel scenarios. Our simulations reveal that if Wi-Fi devices are to coexist with C-V2X in the same spectrum, existing mechanisms either fall short of sufficiently protecting C-V2X performance or render the spectrum unusable for Wi-Fi operations. On the other hand, all Wi-Fi channels that are adjacent to the ITS band can significantly degrade the system-wide C-V2X performance. In such scenarios, to adequately protect the C-V2X network performance, either certain restrictions need to be put in place on Wi-Fi operations, or the operations of Wi-Fi in such channels must be prohibited.

Intelligent Transport Systems consists of applications such as accident warning and avoidance systems. This is an area of interest to us in this research. The accident detection and alert system in the field of ITS (intelligent transportation system) are implemented and analyzed using many statistical methods for proving the accident detection point, GPS Coordinates points search, etc. In this paper, the analysis is performed on how accidents can be prevented using statistical analysis applied to the flow of vehicles in the construction area. This study helps to compare different statistical methods for vehicle detection in accident warning systems. Different statistical methods like Poisson’s probability distribution, Binomial distribution and Negative Binomial probability distributions were evaluated considering the count of vehicles and their distances from the area near or far from the prone area considered in the construction site. The aim of this paper is to evaluate and compare the statistical methods on the real-time datasets collected by hardware configuration of Arduino-Mega, Node-MCU and cloud service thingsspeak.com and shows that Poisson’s statistical distribution performs better than other methods in terms of probability of success. The different statistics like mean, standard deviation, and variance for different statistical methods are evaluated, out of these Poisson performs better.KeywordsAccident avoidanceIntelligent transportation system (ITS)Poisson’s distributionBinomial distributionNegative binomial distribution

Design and implementation of a vehicle interface protocol using an IEEE 1394 network

Current standards for vehicle safety consider only accidental failures; they do not consider failures caused by malicious attackers. The standards implicitly assume that the sensors and Electronic Control Units (ECUs) of each vehicle compose a secure in-vehicle network because no external entity communicates with the nodes of the network. These standards assume that safety and security aspects are independent. Connecting vehicles to external entities, e.g., through Vehicle to Mobile (V2M), Vehicle to Vehicle (V2V), and Vehicle to Infrastructure (V2I), proved to be useful: it enables using Intelligent Transportation Systems (ITS) applications that improve our safety, efficiency, and comfort; but vulnerable to security threats. This paper provides an overview of AGORA framework: a framework generating secure and tested boiler-plate code needed for ITS applications, demonstrates that safety and security aspects in motor vehicles are not independent, and proposes extending safety assurance by considering security aspects. It also discusses a set of research challenges related to extended safety assurance in connected vehicles.

Cellular vehicle-to-everything (C-V2X) is a communication technology that supports various safety, mobility, and environmental applications, given its higher reliability properties compared to other communication technologies. The performance of these C-V2X-enabled intelligent transportation system (ITS) applications is affected by the performance of the C-V2X communication technology (mainly packet loss). Similarly, the performance of the C-V2X communication is dependent on the vehicular traffic density which is affected by the traffic mobility patterns and vehicle routing strategies. Consequently, it is critical to develop a tool that can simulate, analyze, and evaluate the mutual interactions of the transportation and communication systems at the application level to quantify the benefits of C-V2X-enabled ITS applications realistically. In this paper, we demonstrate the benefits gained when using C-V2X Vehicle-to-Infrastructure (V2I) communication technology in an energy-efficient dynamic routing application. Specifically, we develop a Connected Energy-Efficient Dynamic Routing (C-EEDR) application using C-V2X as a communication medium in an integrated vehicular traffic and communication simulator (INTEGRATION). The results demonstrate that the C-EEDR application achieves fuel savings of up to 16.6% and 14.7% in the IDEAL and C-V2X communication cases, respectively, for a peak hour demand on the downtown Los Angeles network considering a 50% level of market penetration of connected vehicles. The results demonstrate that the fuel savings increase with increasing levels of market penetration at lower traffic demand levels (25% and 50% the peak demand). At higher traffic demand levels (75% and 100%), the fuel savings increase with increasing levels of market penetration with maximum benefits at a 50% market penetration rate. Although the communication system is affected by the high density of vehicles at the high traffic demand levels (75% and 100% the peak demand), the C-EEDR application manages to perform reliably, producing system-wide fuel consumption savings.The C-EEDR application achieves fuel savings of 15.2% and 11.7% for the IDEAL communication and 14% and 9% for the C-V2X communication at the 75% and 100% market penetration rates, respectively. Finally, the paper demonstrates that the C-V2X communication constraints only affect the performance of the C-EEDR application at the full demand level when the market penetration of the connected vehicles exceeds 25%. This degradation, however, is minimal (less than a 2.5% reduction in fuel savings).

Many intelligent transportation systems (ITS) applications require accurate prediction of traffic parameters. Previous studies have shown that data driven machine learning methods like support vector regression (SVR) can effectively and accurately perform this task. However, these studies focus on highways, or a few road segments. We propose a robust and scalable method using n-SVR to tackle the problem of speed prediction of a large heterogenous road network. The traditional performance measures such as mean absolute percentage error (MAPE) and root mean square error (RMSE) provide little insight into spatial and temporal characteristics of prediction methods for a large network. This inadequacy can be a serious hurdle in effective implementation of prediction models for route guidance, congestion avoidance, dynamic traffic assignment and other ITS applications. We propose unsupervised learning techniques by employing k-means clustering, principal component analysis (PCA), and self organizing maps (SOM) to overcome this insufficiency. We establish the effectiveness of the developed methods by evaluation of spatial and temporal characteristics of prediction performance of the proposed variable window n-SVR method.

In this paper we present a fastest path algorithm that contains multiple unique destinations, which is a specialization of the Traveling Salesman Problem (TSP) with intermediate cities. This algorithm can be used with Intelligent Transportation System (ITS) applications for determining the fastest route to travel to a set of destinations, such as required by delivery companies. The dynamic behavior of the algorithm is necessary for ITS applications since the amount of time to traverse a roadway in a vehicular network can change constantly. Assuming that all of the potential paths between all nodes in the transportation graph is known, the algorithm will determine the fastest route to a set of nodes in O(n <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> ), where n is the number of nodes to visit. The algorithm was executed on theoretical and actual transportation graphs in FreeSim (http://www.freewaysimulator.com), and an analysis of the running time and a proof of the correctness of the algorithm are included in this paper.

In recent years, with the further adoption of the Internet of Things and sensor technology, all kinds of intelligent transportation system (ITS) applications based on a wide range of traffic sensor data have had rapid development. Traffic sensor data gathered by large amounts of sensors show some new features, such as massiveness, continuity, streaming, and spatio-temporality. ITS applications utilizing traffic sensor data can be divided into three main types: 1) offline processing of historical data; 2) online processing of streaming data; and 3) hybrid processing of both. Current research tends to solve these problems in separate solutions, such as stream computing and batch processing. In this paper, we propose a hybrid processing approach and present corresponding system implementation for both streaming and historical traffic sensor data, which combines spatio-temporal data partitioning, pipelined parallel processing, and stream computing techniques to support hybrid processing of traffic sensor data in real-time. Three types of real-world applications are explained in detail to show the usability and generality of our approach and system. Our experiments show that the system can achieve better performance than a popular open-source streaming system called Storm.

Vehicle-to-anything (V2X) communication is considered worldwide to be an appropriate technology to enable a large number of the intelligent transportation system (ITS) applications for traffic safety and efficiency. However, since there is no completed underlying V2X communication standard in China, it is difficult for Chinese automotive enterprises and research institutions to develop ITS applications in large scale. Therefore, the Society of Automotive Engineers of China (C-SAE) together with China ITS Industry Alliance (C-ITS) decided to develop Application Layer Specification and Data Exchange Standard first to motivate the development of the Chinese cooperative intelligent transport system industry. This paper introduces the details of the Chinese Cooperative Intelligent Transportation System Vehicular Communication Application Layer Specification and Data Exchange Standard. Included in the discussion are the description of the application scenarios and their technique requirements, the summary of the message set in the data exchange standard, and the design of the application layer data interactive interfaces. It is noteworthy that the message set in this standard is complete for the included application scenarios and the designed application layer interfaces are compatible with the underlying V2X communication protocols like DSRC and LTE-V. Finally, several directions worth further consideration are suggested for future standardization.

Dual band rectangular patch antenna array with defected ground structure for ITS application

Nowadays, the Intelligent Transport Systems (ITS) attract many attentions. ITS applications would indeed increase the road safety and the transport efficiency, limit the impact of the vehicles on the environment, improve the overall productivity... However, several important open issues have to be solved before. Among them, the software architecture represents a key issue. Indeed, most of the ITS applications will rely on a distributed frameworks embedded in the vehicles. These applications often require robustness, quality of services or real time management, while the vehicular networks present important constraints in terms of dynamic, variable density, communication reliability, communication duration...

Intelligent Transport System (ITS) provides innovative services to all modes of transportation. It facilitates numerous safety and traffic management applications by providing neighborhood mobility information using wireless communications. To implement this technology, secure wireless communication is a key requirement. As ITS applications involve the safety of vehicles, therefore a lower end-to-end delay is needed. ITS could be subject to security attacks such as man-in-the-middle, denial of service and jamming. A robust cryptographic algorithm is required that can provide defense against data tampering by malicious users. Elliptic Curve Digital Signature Algorithm (ECDSA) is a well-known cryptographic algorithm that provides robust security with a small message overhead. In this paper, we implement ECDSA signature algorithm on a Virtex 6 Field Programmable Gate Array (FPGA), which is capable to validate the real-time constraints of ITS applications. Parallelism is exploited in ECDSA architecture by using parallel processing techniques to reduce the hardware delays, thus reducing the real-time security and end-to-end delay of the ITS messages. The proposed implementation provides faster computational time for signature of ITS messages as compared to other implementations available in the literature.

Intelligent Transportation Systems (ITS) have progressively incorporated machine learning to optimize traffic efficiency, enhance safety, and improve real-time decision-making. However, the traditional centralized machine learning (ML) paradigm faces critical limitations regarding data privacy, scalability, and single-point vulnerabilities. This study explores FL as a decentralized alternative that preserves privacy by training local models without transferring raw data. Based on a systematic literature review encompassing 39 ITS-related studies, this work classifies applications according to their architectural detail—distinguishing systems from models—and identifies three families of federated learning (FL) frameworks: privacy-focused, integrable, and advanced infrastructure. Three representative frameworks—Federated Learning-based Gated Recurrent Unit (FedGRU), Digital Twin + Hierarchical Federated Learning (DT + HFL), and Transfer Learning with Convolutional Neural Networks (TFL-CNN)—were comparatively analyzed against a client–server baseline to assess their suitability for ITS adaptation. Our qualitative, architecture-level comparison suggests that DT + HFL and TFL-CNN, characterized by hierarchical aggregation and edge-level coordination, are conceptually better aligned with scalability and stability requirements in vehicular and traffic deployments than pure client–server baselines. FedGRU, while conceptually relevant as a meta-framework for coordinating multiple organizational models, is primarily intended as a complementary reference rather than as a standalone architecture for large-scale ITS deployment. Through application-level evaluations—including traffic prediction, accident detection, transport-mode identification, and driver profiling—this study demonstrates that FL can be effectively integrated into ITS with moderate architectural adjustments. This work does not introduce new experimental results; instead, it provides a qualitative, architecture-level comparison and adaptation guideline to support the migration of ITS applications toward federated learning. Overall, the results establish a solid methodological foundation for migrating centralized ITS architectures toward federated, privacy-preserving intelligence, in alignment with the evolution of edge and 6G infrastructures.