Real - Time Traffic Light Recognition With Deep Learning

Fransiska, Fransiska and Rusyadi, Rusman (2019) Real - Time Traffic Light Recognition With Deep Learning. Bachelor thesis, Swiss German University.

[img]
Preview
Text
Fransiska 11501010 TOC.pdf

Download (262kB) | Preview
[img] Text
Fransiska 11501010 1.pdf
Restricted to Registered users only

Download (763kB)
[img] Text
Fransiska 11501010 2.pdf
Restricted to Registered users only

Download (473kB)
[img] Text
Fransiska 11501010 3.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
Fransiska 11501010 4.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
Fransiska 11501010 5.pdf
Restricted to Registered users only

Download (148kB)
[img]
Preview
Text
Fransiska 11501010 Ref.pdf

Download (127kB) | Preview

Abstract

Due to the high number of car accidents caused by human error, the development of Automated Driver Assistance System (ADAS) has become an integral part in road safety. By improving the driver’s awareness of road conditions, a lower car accidents number is expected. This thesis purpose is to contribute to the ADAS development by implementing traffic light and traffic sign recognition based on vision and Deep Learning. This purpose is achieved by implementing Convolutional Neural Network (CNN) model for the detection and classification job. The library that is used is TensorFlow. A dataset based on Indonesian traffic light and traffic sign is made for training the model, and training is conducted for the model. Testing is conducted with three methods, images, video, and live testing. The training and testing process is also conducted in CPU and GPU environment.

Item Type: Thesis (Bachelor)
Uncontrolled Keywords: ADAS ; Object Detection ; Convolutional Neural Network ; Tensorflow ; SSD
Subjects: T Technology > TJ Mechanical engineering and machinery
T Technology > TJ Mechanical engineering and machinery > TJ163.12 Mechatronics
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL242 Traffic signs and signals
Divisions: Faculty of Engineering and Information Technology > Department of Mechatronics Engineering
Depositing User: Adityatama Ratangga
Date Deposited: 20 May 2020 06:41
Last Modified: 21 May 2020 15:56
URI: http://repository.sgu.ac.id/id/eprint/679

Actions (login required)

View Item View Item