Data-driven city model representation and analysis using visual and non-visual information

• Grant number: 16/12667-8
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: December 01, 2016
• End date: February 28, 2017
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Roberto Marcondes Cesar Junior
• Grantee: Gabriel Augusto Bianchi Azevedo Ferreira
• Supervisor: José Cláudio Teixeira e Silva Junior
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Institution abroad: New York University, United States
• Associated to the scholarship: 15/03475-5 - Watching the cities: big data and computer vision for analysis of urban environments, BP.IC

Abstract

Thanks to the advent and widespread of new technologies, data are generated all the time, in many forms and from many sources. In particular, cities daily generate a huge amount of data such as from surveillance cameras, demographic statistics and tax revenues. Such data can be efficiently employed to build a city model, where semantic information can be extracted and future events can be predicted. We propose to develop a data-driven approach for representing important city information. Relevant data will be extracted from visual and non-visual data sources. Visual sources include maps, images, videos from urban areas. Non-visual sources include socio-economics statistics and related data regarding a certain urban environment. Computer Vision and Pattern Recognition algorithms will be applied to analyze the data in order to extract relevant information. This document is based on a common project for Eric Keiji Tokuda (PhD proc. 14/24918-0) and Gabriel Augusto Bianchi Azevedo Ferreira (Scientific Initiation proc. 15/03475-5). (AU)