Remote Sensing Data Fusion Techniques, Autonomous Vehicle Driving Perception Algorithms, and Mobility Simulation Tools in Smart Transportation Systems.

• Author: Kliestik, Tomas

1. Introduction

   Intelligent speed assistance tools, urban big data analytics, and object detection and tracking algorithms are pivotal in autonomous vehicle routing and navigation. The purpose of our systematic review is to examine the recently published literature on smart transportation systems and integrate the insights it configures on remote sensing data fusion techniques, autonomous vehicle driving perception algorithms, and mobility simulation tools. By analyzing the most recent (2019-2022) and significant (Web of Science, Scopus, and ProQuest) sources, our paper has attempted to prove that sensor data are pivotal in self-driving car mapping and localization. The actuality and novelty of this study are articulated by addressing autonomous vehicle planning algorithms, predictive maintenance tools, and deep convolutional neural networks (Balcerzak et al, 2022; Lazaroiu et al, 2017; Poliak et al, 2021), that is an emerging topic involving much interest. Our research problem is whether visual perception algorithms, sensing and computing technologies, and route planning and control tools configure networked digital infrastructures.

   In this review, prior findings have been cumulated indicating that traffic flow prediction tools (Andronie et al, 2021; de Godoy et al, 2022; Nica et al, 2022a, b) integrate sensor fusion and route detection algorithms, visualization and analytics tools, and data mining techniques. The identified gaps advance motion planning algorithms, interconnected sensor networks, and mapping and navigation tools. Our main objective is to indicate that neural networks, machine learning algorithms, mobile robotics applications, and sensor technologies (Bacalu, 2021; Kral et al, 2020; Peters, 2022; Valaskova et al, 2022) assist autonomous systems and reduce the need for human supervision. This systematic review contributes to the literature on predictive control and path planning algorithms, data visualization tools, deep learning-based sensing technologies, and urban cloud data (Bennett, 2022; Nica, 2018; Popescu, 2018) by clarifying that real-world connected vehicle data, visual recognition tools, and lane detection algorithms (Barbu et al, 2021; Lazaroiu et al, 2022; Pop et al, 2022; Vatamanescu et al, 2022) articulate autonomous driving technologies.

2. Theoretical Overview of the Main Concepts

   Intelligent transportation infrastructures integrate algorithm-driven sensing devices, virtual navigation tools, and real-time data analytics. Routing and spatial computing technologies, virtual simulation algorithms, and real-world connected vehicle data assist smart traffic planning and analytics. Mobility data processing tools, virtual simulation algorithms, and perception and prediction dynamics assist networked urban environments. Object detection technologies and autonomous vehicle perception systems attempt to eliminate traffic deaths. The manuscript is organized as following: theoretical overview (section 2), methodology (section 3), routing and spatial computing technologies, virtual simulation algorithms, and real-world connected vehicle data (section 4), intelligent speed assistance tools, urban big data analytics, and object detection and tracking algorithms (section 5), sensor fusion and route detection algorithms, visualization and analytics tools, and data mining techniques (section 6), discussion (section 7), synopsis of the main research outcomes (section 8), conclusions (section 9), limitations, implications, and further directions of research (section 10).

3. Methodology

   Throughout March 2022, a quantitative literature review of the Web of Science, Scopus, and ProQuest databases was performed, with search terms including "smart transportation systems" + "remote sensing data fusion techniques," "autonomous vehicle driving perception algorithms," and "mobility simulation tools." The search terms were determined as being the most employed words or phrases across the analyzed literature. As research published between 2019 and 2022 was inspected, only 92 articles satisfied the eligibility criteria. By taking out controversial or ambiguous findings (insufficient/irrelevant data), outcomes unsubstantiated by replication, too general material, or studies with nearly identical titles, we selected 15 mainly empirical sources (Tables 1 and 2). Extracting and inspecting publicly accessible files (scholarly sources) as evidence, before the research began no institutional ethics approval was required. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: AMSTAR, Dedoose, Distiller SR, and SRDR (Figures 1-6).

4. Routing and Spatial Computing Technologies, Virtual Simulation Algorithms, and Real-World Connected Vehicle Data

   Intelligent routing systems (Harb et al., 2022; Li et al., 2021) develop on motion planning algorithms, interconnected sensor networks, and mapping and navigation tools. Object detection technologies and autonomous vehicle perception systems attempt to eliminate traffic deaths. Autonomous transport management and adequate monitoring can improve traffic safety and efficiency. Computational object instantiation and recognition tools, predictive control algorithms, and remote sensor networks optimize intelligent transportation systems.

   Route planning and collision avoidance algorithms, sensor data fusion tools, and image recognition technologies (Mutz et al., 2021; Shannon et al., 2021) can lead to self-driving car acceptance and adoption. Vehicle ownership rates, advanced road configurations, and adjusted driving behaviors will alter the nature of crashes. Sensor data are pivotal in self-driving car mapping and localization. Intelligent transportation infrastructures integrate algorithm-driven sensing devices, virtual navigation tools, and real-time data analytics.

   Cloud computing algorithms, data tracking apps, and mobility simulation tools (Kanagaraj et al., 2021; Zhang et al., 2022) shape transportation analytics. Routing and spatial computing technologies, virtual simulation algorithms, and real-world connected vehicle data assist smart traffic planning and analytics. Image classification algorithms in terms of detection, recognition, and segmentation can deploy real-time collected data, sensor fusion, and computer vision software to optimize path planning and lane and traffic sign detection. (Table 3)

5. ...