Geospatial Data Mining, Computer Vision-based Lane Detection and Object Localization Algorithms, and Mapping and Navigation Tools in Smart Urban Mobility Systems.

• Author: Carey, Brian

1. Introduction

   Multi-sensor remote sensing data, spatial data visualization tools, and connected vehicle technologies assist smart transportation networks. The purpose of my systematic review is to examine the recently published literature on smart urban mobility systems and integrate the insights it configures on geospatial data mining, computer vision-based lane detection and object localization algorithms, and mapping and navigation tools. By analyzing the most recent (2019-2022) and significant (Web of Science, Scopus, and ProQuest) sources, my paper has attempted to prove that big geospatial data analytics, mobility simulation tools, and sensor data processing algorithms (Andronie et al., 2021a, b; Lazaroiu et al., 2022) shape vehicular communication technologies. The actuality and novelty of this study are articulated by addressing connected vehicle data, mapping and navigation tools, and deep learning-based sensing technologies (Glogovetan et al., 2022; Lazaroiu et al, 2020; Peters, 2022), that is an emerging topic involving much interest. My research problem is whether crash avoidance technologies integrate motion planning algorithms, data mining tools, and smart environmental sensors.

   In this review, prior findings have been cumulated indicating that networked transport systems, autonomous mobility technologies, and multi-sensor environmental data fusion (Frajtova Michalikova et al, 2022; Kliestik et al., 2022; Obada and Dabija, 2022; Poliak et al., 2021) typify urban driving environments. The identified gaps advance simulation optimization algorithms, monitoring and sensing technologies, sensor data processing and mobile obstacle tracking tools, and self-driving car perception systems. My main objective is to indicate that vehicular networks and smart transportation (Gasparin and Schinckus, 2022; Lazaroiu, 2018; Olssen, 2021; Pop et al, 2021) can assist traffic management and optimize road safety, protecting users from inevitable collisions. This systematic review contributes to the literature on real-time Internet of Things data, autonomous vehicle decision-making algorithms, big geospatial data analytics, and virtual mapping tools (Blazek et al, 2022; Mihaila et al, 2016; Poliak et al, 2021) by clarifying that cognitive sensor networks, mobile data traffic, and computer vision algorithms shape vehicle navigation technologies.

2. Theoretical Overview of the Main Concepts

   Multi-sensor environmental data fusion, spatial cognition algorithms, and sensing and navigation systems decrease traffic congestions and collisions. Urban Internet of Things-sensing tools, spatio-temporal fusion algorithms, and environment mapping algorithms cut down crashes and casualties. Intelligent transportation systems harness 3D virtual simulation technology, vehicle routing and navigation tools, and visual analytics. The manuscript is organized as following: theoretical overview (section 2), methodology (section 3), multi-sensor environmental data fusion, spatial cognition algorithms, and sensing and navigation systems (section 4), autonomous vehicle perception sensor data, algorithmic forecasting systems, and spatial recognition technologies (section 5), spatial simulation algorithms, sustainable urban mobility behaviors, and connected vehicle data (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 April 2022, I performed a quantitative literature review of the Web of Science, Scopus, and ProQuest databases, with search terms including "smart urban mobility systems" + "geospatial data mining," "computer vision-based lane detection and object localization algorithms," and "mapping and navigation tools." The search terms were determined as being the most employed words or phrases across the analyzed literature. As I inspected research published between 2019 and 2022, only 93 articles satisfied the eligibility criteria. By eliminating controversial findings, outcomes unsubstantiated by replication, too imprecise material, or having similar titles, I decided upon 15, generally 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: AXIS, Dedoose, ROBIS, and SRDR (Figures 1-6).

4. Multi-Sensor Environmental Data Fusion, Spatial Cognition Algorithms, and Sensing and Navigation Systems

   Connected vehicle data, mapping and navigation tools, and deep learning-based sensing technologies (Kanagaraj et al., 2021; Li et al., 2021) configure smart sustainable intelligent transportation systems. Machine learning algorithms, by use of real-life vehicle data, can predict the subsequent motions of the other road users across vehicular communication. Real-time traffic data can configure the exemplary path to reach a destination. Crash avoidance technologies integrate motion planning algorithms, data mining tools, and smart environmental sensors.

   Sensor data, environment perception tools, infrastructural support systems, and cognitive artificial intelligence algorithms (Ren et al., 2022; Shannon et al., 2021) articulate smart mobility technologies. Cognitive sensor networks, mobile data traffic, and computer vision algorithms shape vehicle navigation technologies. Developments in vehicle safety will considerably decrease collision incidences and severities as a result of cutting-edge technological equipment that can steer through imminent hazards.

   Data visualization tools, ambient sound recognition software, and remote sensing systems (Mutz et al., 2021; Tennant and Stilgoe, 2021) optimize road user safety. Multi-sensor environmental data fusion, spatial cognition algorithms, and sensing and navigation systems decrease traffic congestions and collisions. Robust sensors, map-based localization algorithms, and proper traffic infrastructure are...