Smart street lighting

The study's preliminary findings regarding using a single board computer to run an object detection software are presented in the report. These findings are later utilized to create smart street lighting applications. The TensorFlow package is used in Python to produce the object recognition so...

Full description

Saved in:
Bibliographic Details
Main Author: Tan, Cleon Guan Yu
Other Authors: Zhang Qing
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/167624
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-167624
record_format dspace
spelling sg-ntu-dr.10356-1676242023-07-07T17:51:55Z Smart street lighting Tan, Cleon Guan Yu Zhang Qing School of Electrical and Electronic Engineering eqzhang@ntu.edu.sg Engineering::Electrical and electronic engineering The study's preliminary findings regarding using a single board computer to run an object detection software are presented in the report. These findings are later utilized to create smart street lighting applications. The TensorFlow package is used in Python to produce the object recognition software. The SSDMobileNet V2 artificial neural network model was successfully carried out by the author to construct and test the object detection module on the Raspberry Pi 4B. The findings presented in this research show how this module has the capability for further improvement. The author demonstrated that a decent performance is obtainable with little research funding for the AI module based on simulation and actual findings. This module can accurately estimate the object's distance in addition to having a high-precision object detecting feature. The study additionally suggests a number of ways to improve the created module's performance, particularly its real-time capability. Bachelor of Engineering (Electrical and Electronic Engineering) 2023-05-31T05:31:46Z 2023-05-31T05:31:46Z 2023 Final Year Project (FYP) Tan, C. G. Y. (2023). Smart street lighting. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167624 https://hdl.handle.net/10356/167624 en A2221-221 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
spellingShingle Engineering::Electrical and electronic engineering
Tan, Cleon Guan Yu
Smart street lighting
description The study's preliminary findings regarding using a single board computer to run an object detection software are presented in the report. These findings are later utilized to create smart street lighting applications. The TensorFlow package is used in Python to produce the object recognition software. The SSDMobileNet V2 artificial neural network model was successfully carried out by the author to construct and test the object detection module on the Raspberry Pi 4B. The findings presented in this research show how this module has the capability for further improvement. The author demonstrated that a decent performance is obtainable with little research funding for the AI module based on simulation and actual findings. This module can accurately estimate the object's distance in addition to having a high-precision object detecting feature. The study additionally suggests a number of ways to improve the created module's performance, particularly its real-time capability.
author2 Zhang Qing
author_facet Zhang Qing
Tan, Cleon Guan Yu
format Final Year Project
author Tan, Cleon Guan Yu
author_sort Tan, Cleon Guan Yu
title Smart street lighting
title_short Smart street lighting
title_full Smart street lighting
title_fullStr Smart street lighting
title_full_unstemmed Smart street lighting
title_sort smart street lighting
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/167624
_version_ 1772825960877391872