Linha de Pesquisa: Ciência de Dados

Resumo:

This article presents an innovative automated system for detecting and classifying Brazilian
trafc signs and lights using artifcial intelligence. The main objective of the system is to
contribute to road safety by alerting drivers to potential risks such as speeding, alcohol
consumption, and cell phone use, which could lead to severe accidents and jeopardize lives.
The system’s core contribution lies in its ability to accurately detect and classify various
trafc signs and lights, providing crucial warnings to drivers to prevent potential hazards.
To achieve this, the system utilizes the light version of the Single Shot Multibox Detector
(SSD-Lite) as its detection algorithm and experiments with Mobilenet versions 2 and 3 as
base networks. The optimal Mobilenet version is selected based on performance evaluations
to ensure a Mean Average Precision (mAP) higher than 80%, which guarantees reliable
detection results. The dataset used for training and evaluation comprises images extracted
from YouTube trafc videos, each meticulously annotated to create the necessary labels
for model training. Through this extensive experimentation, the system demonstrates its
efcacy in achieving accurate and efcient trafc sign and light detection. The results of the
experiments are compared with other existing approaches that focus on detecting only one
type of trafc sign or employ different network types. The proposed system outperforms
these comparative works, showcasing its superiority in handling various trafc sign and
light classes by providing a dedicated dataset for Brazilian trafc sign and light

Link para a defesa: 

Clique para ingressar na reunião