Design and Optimization of a Deep Neural Network Architecture for Traffic Light Detection

Autonomous Driving has recently become a research trend and efficient autonomous driving system is difficult to achieve due to safety concerns, Applying traffic light recognition to autonomous driving system is one of the factors to prevent accidents that occur as a result of traffic light violation...

Full description

Bibliographic Details
Main Authors: Fukuchi Tomohide, Ikechukwu Mark Ogbodo, Ben Abdallah Abderazek
Format: Article
Language:English
Published: EDP Sciences 2020-01-01
Series:SHS Web of Conferences
Online Access:https://www.shs-conferences.org/articles/shsconf/pdf/2020/05/shsconf_etltc2020_01002.pdf
Description
Summary:Autonomous Driving has recently become a research trend and efficient autonomous driving system is difficult to achieve due to safety concerns, Applying traffic light recognition to autonomous driving system is one of the factors to prevent accidents that occur as a result of traffic light violation. To realize safe autonomous driving system, we propose in this work a design and optimization of a traffic light detection system based on deep neural network. We designed a lightweight convolution neural network with parameters less than 10000 and implemented in software. We achieved 98.3% inference accuracy with 2.5 fps response time. Also we optimized the input image pixel values with normalization and optimized convolution layer with pipeline on FPGA with 5% resource consumption.
ISSN:2261-2424