Computer Vision Algorithms, Vehicle Navigation and Remote Sensing Technologies, and Smart Traffic Planning and Analytics in Urban Transportation Systems.

• Author: Gordon, Susan

1. Introduction

   Algorithm-driven sensing devices, road environment data, and predictive control and spatial cognition algorithms enable dynamic route optimization. The purpose of my systematic review is to examine the recently published literature on urban transportation systems and integrate the insights it configures on computer vision algorithms, vehicle navigation and remote sensing technologies, and smart traffic planning and analytics. By analyzing the most recent (2021-2022) and significant (Web of Science, Scopus, and ProQuest) sources, my paper has attempted to prove that smart traffic analytics integrates computer vision and spatial simulation algorithms (Andronie et al., 2021; Lazaroiu et al., 2020; Poliak et al., 2021), urban sensor networks, and geospatial data mining tools. The actuality and novelty of this study are articulated by addressing motion planning and data visualization tools (Lazaroiu et al, 2017; Olssen, 2021; Zvarikova et al, 2022), autonomous vehicle perception sensors, and crash avoidance technologies (Blake and Frajtova Michalikova, 2021; Nica, 2017; Vatamanescu et al, 2020), that is an emerging topic involving much interest. My research problem is whether object detection and tracking algorithms, adaptive and dynamic route planning tools, and deep learning-based sensing technologies (Balcerzak et al, 2022; Lazaroiu et al, 2022; Valaskova et al, 2022) decrease motor vehicle collisions.

   In this review, prior findings have been cumulated indicating that sensing and computing technologies (Crowell et al., 2022; Nica et al., 2022; Vatamanescu et al, 2022) integrate location tracking algorithms, simulation modeling and mobility data processing tools, and monitoring and predictive capabilities. The identified gaps advance spatial computing and recognition technologies, tracking control and route planning algorithms, urban cloud data, and predictive modeling techniques. My main objective is to indicate that intelligent traffic monitoring systems require simulation and virtualization technologies (Obada and Dabija, 2022; Watson, 2022), connected car data, and autonomous vehicle planning algorithms. This systematic review contributes to the literature on sustainable urban governance networks by clarifying that sensing and computing technologies, visual perception and path planning algorithms, and geospatial mapping tools can curtail crash recurrence.

2. Theoretical Overview of the Main Concepts

   Predictive urban analytics deploys obstacle avoidance and route planning algorithms, spatial data visualization tools, and vehicular communication technologies. Cooperative navigation can be developed on environmental and vehicle sensors for an optimized autonomous transport through a coherent communication traffic management. The manuscript is organized as following: theoretical overview (section 2), methodology (section 3), urban Internet of Things-sensing tools, connected vehicle data, virtual navigation tools, and spatial cognition algorithms (section 4), computer vision and spatial simulation algorithms, urban sensor networks, and geospatial data mining tools (section 5), simulation and virtualization technologies, connected car data, and autonomous vehicle planning algorithms (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

   I carried out a quantitative literature review of ProQuest, Scopus, and the Web of Science throughout March 2022, with search terms including "urban transportation systems" + "computer vision algorithms," "vehicle navigation and remote sensing technologies," and "smart traffic planning and analytics." The search terms were determined as being the most employed words or phrases across the analyzed literature. As I analyzed research published in 2021 and 2022, only 92 papers met the eligibility criteria. By removing controversial or unclear findings (scanty/unimportant data), results unsupported by replication, undetailed content, or papers having quite similar titles, I decided on 15, chiefly 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, Distiller SR, ROBIS, and SRDR (Figures 1-6).

4. Urban Internet of Things-Sensing Tools, Connected Vehicle Data, Virtual Navigation Tools, and Spatial Cognition Algorithms

   Route detection and environment mapping algorithms, deep reinforcement learning techniques, smart infrastructure sensors, and autonomous vehicle interaction control software (Stilgoe, 2021; Yang et al., 2021) can decrease traffic death toll. Self-driving cars enhance traffic safety by adequately sensing and interpreting the surrounding environment, anticipating the behaviors of other road users, and planning and controlling direction and speed. Edge intelligence can considerably reduce the wireless communication intermission by enabling self-driving cars to upload vehicle conditions and environment data to the edge server.

   Cognitive wireless networks, motion planning and machine learning algorithms, traffic congestion monitoring systems, and urban perception and planning tools (Butler et al., 2021; Kanagaraj et al., 2021) enable vehicle and pedestrian detection. Sensors harnessed in vehicle and lane detection facilitate an input image to be obtained instantaneously and integrated throughout an image processing procedure. Increasing concerns in relation to transport downsides and growing socioeconomic dissimilarities require groundbreaking ways to optimize lack of discrimination and articulate big data-driven transportation systems.

   Urban Internet of Things-sensing tools, connected vehicle data, virtual navigation tools, and spatial cognition algorithms (Hataba et al., 2022; Johnson and Nica, 2021; Zhang et al., 2022) configure smart transportation networks. Connected...