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 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.

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.

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.

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.