Combining barcode and computer vision to measure river levels

• Grant number: 23/00017-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2023
• End date: March 31, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Jó Ueyama
• Grantee: Gabriel Montagni Domingues Filho
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Floods affect several cities in the country and cause various material and human damages.For this reason, researchers have been engaged in the process of monitoring and forecasting them, with the aim of reducing these damages. Therefore, this project aims to help in this monitoring, developing and applying solutions to improve flood detection through computer vision.Several water level measurement approaches have already been used in this context, most of which are based on classical image processing techniques applied to known watercourse features to somehow measure the water height of a river or stream.Considering the task of measuring the height of the water course from images from video cameras, it is intended to advance a solution to perform this measurement using a marker (i.e., a metal plate with a zebra bar code fixed perpendicularly to the surface of the water from its edge) and develop a database. Thus, it is proposed to use machine learning to detect a metallic plate with a zebra pattern and infer the level of rivers.