Computer vision-based detection and classification of lane markings

• Grant number: 14/01465-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2014
• End date: March 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Denis Fernando Wolf
• Grantee: Marcos Paulo Batista
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Due to the large number of traffic accidents, the need for intelligent vehicles has become an evidence for the near future in order to, in addition to reducing that number, get a better flow with traffic, promote social inclusion of elderly and disabled who no physical are fit to drive, among other important points. Because of this, one of the essential areas in a project like this is to get information on where the car is located on the track. Thus, the project focuses on detecting and classifying lanes of traffic with the aid of a monocular camera. For this, we will work with current methods, using image processing and statistical filters in order to make the data more reliable and robust as possible, comparing the various methods published in the conferences of great impact in this area. At the end of the project, is expected to integrate and model these methods so that the autonomous vehicle can leverage this data and work with the algorithms in real time.