FPGA-based prototyping of drone detection algorithm
In recent years, deep learning, especially convolutional neural network, has received much attention as a method of target detection. And better implementation of neural networks using FPGA is also one of the main research directions. Moreover, the detection of small targets, such as drones, is bein...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/173223 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-173223 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1732232024-01-19T15:44:54Z FPGA-based prototyping of drone detection algorithm 李海鹏 Li, Haipeng Kim Tae Hyoung School of Electrical and Electronic Engineering THKIM@ntu.edu.sg Engineering::Electrical and electronic engineering::Applications of electronics In recent years, deep learning, especially convolutional neural network, has received much attention as a method of target detection. And better implementation of neural networks using FPGA is also one of the main research directions. Moreover, the detection of small targets, such as drones, is being applied in a wider range of industrial scenarios. However, the complexity of different network models and the limitation of resources on FPGA are also limiting factors of the improvement works. In this thesis, the simulation of detection of a dataset containing drone images is implemented on FPGA by using a simplified CNN network structure, while optimizing for the limited storage and computational resources of FPGA and utilizing parallelized pipeline processing. In addition, future trends for similar research are discussed with respect to the shortcomings of the design in this thesis. A performance of approximately 270ms for processing one image is achieved with an accuracy of approximately 96.4% on simulation platform, driven by one 200MHz clock. Master's degree 2024-01-19T01:30:54Z 2024-01-19T01:30:54Z 2023 Thesis-Master by Coursework 李海鹏 Li, H. (2023). FPGA-based prototyping of drone detection algorithm. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/173223 https://hdl.handle.net/10356/173223 en 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::Applications of electronics |
spellingShingle |
Engineering::Electrical and electronic engineering::Applications of electronics 李海鹏 Li, Haipeng FPGA-based prototyping of drone detection algorithm |
description |
In recent years, deep learning, especially convolutional neural network, has received much attention as a method of target detection. And better implementation of neural networks using FPGA is also one of the main research directions. Moreover, the detection of small targets, such as drones, is being applied in a wider range of industrial scenarios. However, the complexity of different network models and the limitation of resources on FPGA are also limiting factors of the improvement works. In this thesis, the simulation of detection of a dataset containing drone images is implemented on FPGA by using a simplified CNN network structure, while optimizing for the limited storage and computational resources of FPGA and utilizing parallelized pipeline processing. In addition, future trends for similar research are discussed with respect to the shortcomings of the design in this thesis. A performance of approximately 270ms for processing one image is achieved with an accuracy of approximately 96.4% on simulation platform, driven by one 200MHz clock. |
author2 |
Kim Tae Hyoung |
author_facet |
Kim Tae Hyoung 李海鹏 Li, Haipeng |
format |
Thesis-Master by Coursework |
author |
李海鹏 Li, Haipeng |
author_sort |
李海鹏 Li, Haipeng |
title |
FPGA-based prototyping of drone detection algorithm |
title_short |
FPGA-based prototyping of drone detection algorithm |
title_full |
FPGA-based prototyping of drone detection algorithm |
title_fullStr |
FPGA-based prototyping of drone detection algorithm |
title_full_unstemmed |
FPGA-based prototyping of drone detection algorithm |
title_sort |
fpga-based prototyping of drone detection algorithm |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/173223 |
_version_ |
1789483072045973504 |