Computing in Intelligent Transportation Systems

Now the entire world community is witnessing the intensive development of scientific and technological progress, indicating a change in the technological order. Industrial automation and research in the field of artificial intelligence (AI) are of great importance in the formation of transport technologies. The dynamics of development can be traced through innovations in transport systems associated with the introduction of digital technologies. The relevance and economic efficiency of the implementation of digital technologies in transport systems determine the need for their design description, analysis, and feasibility study. The study provides a rationale for the benefits of implementing blockchain technologies, customer relationship management (CRM), and Internet of Things (IoT) technologies in the transport sector. The tasks solved by the introduction of certain digital technologies in transport have been systematized; their main function is formulated using the example of railroad transportation. Using the analysis of statistical data for Russia, an assessment is made of the scale of dissemination of the considered digital technologies in the Russian transport sector, including in the field of railway transport. The main directions of the digital transformation strategy of the Russian Railways company (Russian Railways) and their economic consequences are outlined.

Many businesses have been developing self-driving automobiles in recent years. The primary motivation for the development of advanced driver assistance systems is to improve safety and reduce road accidents, therefore saving lives. One of the most difficult problems in an autonomous driving system is detecting the road lane or road limits. Collision avoidance in driving assistance systems may rely heavily on lane and object identification. With the increasing volume of traffic, there is a greater demand for security and comfort, both of which are significant parts of driving; thus, new technologies must focus more on these areas. Computer vision is one of the ways that may be utilized to assist a driver in a variety of situations to improve his safety and comfort. One of the most basic features of self-driving automobiles is lane tracking. Many sensors, including as lasers, radar, and vision sensors, are commonly employed for obstacle detection and lane detection. Computer vision is the primary way for detecting road limits and lanes with a vehicle’s vision system. The system uses a camera installed on the vehicle to capture the front view, which is then subjected to a number of processing steps in order to recognize lanes and objects. To do this, a flexible methodology is utilized. This report focuses on computer vision-based lane detection technique with a camera mounted on the vehicle.

Swarm unmanned aerial vehicles (SUAVs) have grown at an increasingly rapid pace over the last decade. UAV uses range from military warfare, environmental observation, and air transport to the burgeoning public entertainment industry. For the aforementioned use scenarios, the precise position of the target of interest is sometimes requested, which is critical for mission completion. This is a simple assignment for GPS-equipped UAVs. The GPS signal, however, can be occluded, modified by environmental conditions. As a result, location information needs to be improved by additional localization techniques, which is the major focus of this article. Furthermore, when localization, guiding, and communication technologies progress, future swarm UAVs will operate autonomously by distributing duties and coordinating the operation of several UAVs. Thus, UAV-UAV communication is offered since it is a component of the SUAV’s autonomous coordinating capacity. Furthermore, future research paths and open difficulties that must be addressed, such as autonomous swarm UAVs, are discussed.

Visual perception stack is indispensable for present-day autonomous vehicle. It perceives the environment around the ego vehicle in the same way as humans. Stereo cameras are the prominent sensor for visual perception stack. This paper will focus on deep-level understanding of visual perception using stereo camera, image processing, and crucial aspects required for autonomous cars. There are other sensors such as LIDAR, GNSS, and IMU, which are used for environment perception, but the information from stereo cameras are far profitable and utilitarian than other sensor information. First, the image formation phenomenon is discussed followed by the image projection onto different frames such as world frame, camera frame, image coordinates, and pixel coordinate. Then camera calibration will be discussed and intrinsic parameters of stereo camera are obtained from RQ factorization method. Depth perception from stereo camera is done by using identifying epipolar line and by arriving at disparity map, depth map, and finally the cross correlation. Then feature detection, feature description, and feature matching are essential in order to establish a robust image detection. The algorithms involved in each part will be discussed along with outlier rejection using RANSAC algorithm. In order to obtain a fine image detection, CNN will be used along with pooling layer and feature decoder to up sample the image. The output of semantic segmentation will be obliging for drivable space estimation, object detection, and distance-to-collision on environment.

Smart farming is utilizing the unmanned aerial vehicles (UAVs) and Internet of Things (IoT) paradigm to achieve the goal of sustainable agriculture. These “smart farms” are made to be maintained by vehicles and connected devices. The combination of several IoT technologies offers huge possibilities for automated processes that require minimal supervision. The suggested method is more reliable and accurate than current systems in tracking the soil’s contents and the safety of the crops because it employs a variety of sensors, including PIR, pH, and capacitance dielectric soil moisture sensors. It also discusses the use of UAV technology in smart agriculture by looking at how UAVs are used in a variety of conditions, such as irrigation, fertilization, weed control, crop monitoring, and field-level phenotyping.

In the modern computational age, enormous amounts of information are being produced every single second. Once these piece of information in terms of data are properly fed, then this has the potential to expand the boundaries of computers. The current world is gradually transitioning to an automatic era, in which every entity and item are automated to carry out desired activities without requiring human participation. People’s lives are now easier and enjoyable due to this automation. Every aspect of computing, including those outside of it, has been automated. One such automation is smart mobility, which provides users with actual information about traffic patterns as well as advice for alternate routes in the event of traffic jams. Any business’s foundation is thought to be its transportation system. The automated intelligent transportation system (ITS), which has totally changed how products, people, and services are delivered, is crucial for achieving sustainability. This paper gives a general overview of the current ITS system, the idea of smart mobility, and current weaknesses in these systems. Their security worries and potential outcomes are also examined. Additionally, future ITS developments are discussed, as well as the significance and necessity of safeguarding these intelligent systems.