Zdeněk Lokaj

Urban traffic management increasingly relies on accurate, timely and robust traffic detection to support safe, efficient and sustainable mobility in complex urban environments. While a wide range of traffic detection technologies is currently available, many limitations persist due to fragmented data utilization, limited interoperability and sensor-centric system architectures. This paper provides a structured review of commonly used urban traffic detection technologies and analyses their technical and system-level limitations. Based on this analysis, a data-centric reference architecture is proposed, which decouples traffic detection capabilities from individual sensing technologies and enables the integration of heterogeneous infrastructure-based sensors, mobile data and C-ITS sources through harmonization and AI-based multi-source fusion. Rather than presenting a concrete system implementation, the proposed architecture serves as a conceptual framework supporting resilient, scalable and future-ready traffic detection. Its relevance is illustrated using representative use cases focusing on vulnerable road user detection, predictive traffic management and incident handling. The paper argues that use case-driven, data-centric architectural design represents a key enabler for next-generation urban traffic management in smart city environments.

This paper reviews current approaches to cybersecurity risk analysis in critical transport infrastructure, with particular focus on their applicability to complex cyber-physical environments such as tunnel control systems. Modern transport infrastructures are characterised by strong interdependencies between digital control technologies and physical operational processes, which increase cybersecurity risks and the potential for cascading failures. The review shows that existing methodologies are based on standards-driven and governance-oriented frameworks. While these approaches provide structured procedures for risk identification and regulatory compliance, they remain largely qualitative, static, and limited in their ability to represent uncertainty, system interdependencies, and dynamic cyber-physical interactions. To address these limitations, the paper discusses the potential of probabilistic modelling approaches capable of supporting decision-making under uncertainty. Probabilistic graphical models offer mechanisms for modelling complex dependencies, integrating expert knowledge with available data, and improving analytical support for cybersecurity risk management. The findings highlight the need to complement compliance-oriented methodologies with probabilistic and decision-oriented approaches to enhance cybersecurity resilience in critical transport infrastructure.

In recent years, object detection has significantly advanced by using deep learning, especially convolutional neural networks. Most of the existing methods have focused on detecting objects under favorable weather conditions and achieved impressive results. However, object detection in the presence of rain remains a crucial challenge owing to the visibility limitation. In this article, we introduce an amalgamating knowledge network (AK-Net) to deal with the problem of detecting objects hampered by rain. The proposed AK-Net obtains performance improvement by associating object detection with visibility enhancement, and it is composed of five subnetworks: rain streak removal (RSR) subnetwork, raindrop removal (RDR) subnetwork, foggy rain removal (FRR) subnetwork, feature transmission (FT) subnetwork, and object detection (OD) subnetwork. Our approach is flexible; it can adopt different object detection models to construct the OD subnetwork for the final inference of objects. The RSR, RDR, and FRR subnetworks are responsible for producing clean features from rain streak, raindrop, and foggy rain images, respectively, and offer them to the OD subnetwork through the FT subnetwork for efficient object prediction. Experimental results indicate that the mean average precision (mAP) achieved by our proposed AK-Net was up to 19.58% and 26.91% higher than those produced using competitive methods on published iRain and RID datasets, respectively, while preserving the fast-running time of the baseline detector.

In the field of Cooperative Intelligent Transport Systems (C-ITSs), the traditional approach to testing often emphasizes technological parameters, leaving the validation of message content insufficiently addressed. Since the content of these messages is crucial for the correct functioning of C-ITS, this article demonstrates the potential for automated evaluation of C-ITS message content against relevant standards. It leverages our novel tools, Karlos and C-ITS SIM, to facilitate this process. Through detailed laboratory testing and data analysis, the study showcases the effectiveness of these automated solutions in enhancing the accuracy and reliability of message content validation.

In recent years, the concept of smart cities, along with autonomous transportation, has emerged as a significant focal point for researchers, urban planners, and technological innovators. This growing interest is driven not only by technological advancements but also by the pressing need to address current urban mobility challenges such as congestion, air pollution, and the necessity to enhance road safety. Autonomous trams, as a pivotal element of intelligent urban transportation systems, offer a promising pathway towards more efficient, safer, and sustainable urban mobility. With their ability to integrate with a wide range of technologies, from advanced traffic management systems to sensors and artificial intelligence, autonomous trams represent a revolutionary step towards achieving smooth and secure movement in urbanized areas. However, the development and integration of autonomous trams into urban transport systems require not only advanced technologies but also comprehensive testing and validation of their communication with urban infrastructure and the functions of relevant devices. HD maps and digital twins play a crucial role in this process, enabling precise navigation and interaction with the urban environment. These technologies not only enhance the efficiency and safety of autonomous trams but also contribute to a better understanding and management of the urban space. This article focuses on the significance of comprehensive testing of the communication between autonomous trams and urban infrastructure, as well as the functionality of relevant devices, with an emphasis on the use of HD maps and digital twins. Highlighting the theoretical framework and methodologies that are essential for conducting such tests, the paper discusses the anticipated approach and potential challenges. By addressing the broader implications for the development of intelligent urban transportation systems, the article aims to shed light on how these technologies can help overcome the current and future challenges of urban mobility.

The article presents a novel algorithm for merging Bayesian networks generated by different methods, such as expert knowledge and data-driven approaches, while leveraging a symmetry-based approach. The algorithm combines the strengths of each input network to create a more comprehensive and accurate network. Evaluations on traffic accident data from Prague in the Czech Republic and accidents on railway crossings demonstrate superior predictive performance, as measured by prediction error metric. The algorithm identifies and incorporates symmetric nodes into the final network, ensuring consistent representations across different methods. The merged network, incorporating nodes selected from both the expert and algorithm networks, provides a more comprehensive and accurate representation of the relationships among variables in the dataset. Future research could focus on extending the algorithm to deal with cycles and improving the handling of conditional probability tables. Overall, the proposed algorithm demonstrates the effectiveness of combining different sources of knowledge in Bayesian network modeling.

Autoři se zabývají problematikou ochrany osobních údajů v systémech autonomního řízení představujících celé ekosystémy dílčích vzájemně komunikujících prvků a různorodých spolupracujících entit. Při provozu těchto systémů dochází k přenosu a zpracování obrovského množství dat, mezi kterými lze nalézt i řadu významných osobních údajů, které lze zpracovávat pouze v souladu s právními předpisy. V první části článku jsou tak obecně popsány systémy autonomního řízení, specifikace jejich prvků a představení klíčových hráčů, kteří se podílejí na vytváření nebo dalším zpracování těchto dat. Dále jsou rozpracovány jednotlivé kategorie osobních údajů, se kterými budou předmětné systémy autonomního řízení pracovat nebo v nichž se budou nalézat. Stěžejní částí je pak návrh řešení přístupu k ochraně osobních údajů napříč celým ekosystémem s využitím principů privacy by design a privacy by default. V neposlední řadě se autoři zabývají dílčími právními oblastmi jako je kybernetická bezpečnost a ochrana soukromí v elektronických komunikacích, které v souvislosti s problematikou autonomního řízení nemohou být opomenuty.

In the area of smart cities, great emphasis is placed on many different fields such as energetics, information systems, and transportation. All of these should lead to a simplification of life thanks to smart technologies. If we talk about the transportation field, the main issues related to this area are safety, traffic efficiency, or the environment. Another condition is the successful acceptance of any new technology by its users. Cooperative systems prove to be a suitable solution for these issues, especially in urban areas. Today, pilot implementations of cooperative systems in European countries are being carried out. However, before they are put into full operation, they need to be tested, evaluated, and assessed. This article focuses on the latter two points, i.e., evaluation and assessment of the cooperative systems. For this purpose, a methodology was created, which describes the procedure chosen in the evaluation and assessment of cooperative systems in the Czech Republic and a demonstration of its use by example. The methodology is focused on three main areas, which in this case are functional evaluation, user acceptance, and impact assessment. For the area of user acceptance, the main source was questionnaires, impact assessment relied on measured data while functional evaluation was based on discussions with the drivers, evaluating the cooperative systems, the measured data, and the expert observations. All collected and measured data were then processed and some of the results of the evaluation of the selected service are presented at the end of this article.

Smart mobility based on cooperative systems (C-ITS) represents one of the Smart Cities topics. Guaranteed quality of data exchange both between VANET (Vehicular Ad hoc Network) members (V2V) as well as between VANET and Infrastructure (V2I) represents critical condition for suitable functions of the cooperative systems. We proposed hybrid routing protocol for VANET networking based on application of two most widely accepted mobile technologies and theirs combination. Finally, we compared in VANET communication simulation proposed protocol performance with performance of mostly discussed routing protocols designed for VANET conditions.