AI and Computer Vision Approaches for Big Geo-Spatial Data in Smart City

Dear Colleagues,

This Special Issue aims to stimulate discussions on recent trends in Artificial Intelligence and Computer Vision Approaches for Big-Geospatial Data In Smart Cities. In recent years, the concept of smart cities has blossomed, with a multitude of applications addressing various challenges. Some of them, such as traffic or waste management, are historically well-known. Others, such as ecocitizenship, smart economy, or e-health are new and not only from the perspective of the evolution of technology, but also the evolution of societies. While each smart city is a unique city with its own problems, smart cities share the common idea that data produced at large scales can help to better model, understand, and predict city dynamics.

Evolution in sensor technologies, from the massive development of sensors for the Internet of Things, to recent advances in computer vision allowing to produce data not only from the ground, but also from space, is allowing cities to gather and study heterogeneous sources of data at multiple scales. Artificial intelligence can be used to compute these huge volumes of data by autonomously extracting information from computer vision (object detection and tracking, semantic segmentation, etc.). This huge volume of data induces needs a new generation of tools and models to deal with their heterogeneity, spatial distribution, and noisiness.

Agent-based simulation, through its ability to model a city and its various components (including its citizens) at different scales (physical and temporal), is a promising approach to simulate and model smart cities. At a microscopic scale, sensors can produce geolocalized traces of a phenomenon, while at a macroscopic scale, the fusion and exploitation of data produced by the collective of sensors can produce better information about the city dynamics and help stakeholders make better decisions. For example, an autonomous car can act as a mobile visual sensor collecting various real-time information about the city. By interacting with each other, agents can capture better data about the state of the city, providing various local traces that can be used at a macroscopic level by urban planners to improve the quality of life of the citizens.

This Special Issue will gather works, tools, methodologies, and studies devoted to bridging the gap between the geospatial data produced by sensors and actual smart city applications.

Potential topics include but are not limited to the following:

• AI and computer-vision techniques for smart cities
• The use of real-time data to inform agent-based simulations for smart cities
• Bridging the gap between agent-based simulation and computer vision, etc.
• Computer vision in smart cities environment
• Computer-vision at the edge for smart cities
• Multi-scale simulation of a smart city
• Agent-based simulations for big geospatial data
• Remote sensing (satellite imagery) for smart cities
• Tools and methodologies for big-geospatial data management

Dr. Johan Barthélemy
Dr. Nicolas Verstaevel
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Smart Cities is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Computer vision
• Big geospatial data
• Remote sensing
• (Multi) agent-based simulation
• Smart cities
• AI