Study of object detection using region-based fully convolutional neural networks

With the fast pace of economic development, deep learning has become one of the fastest growing field in recent over ten years. It has been applied and implemented widely such as Intelligent Transportation System (ITS), industrial automation system, data statistic and robotic. Convolutional Neural N...

Full description

Saved in:
Bibliographic Details
Main Author: Liang, Yuehui
Other Authors: Lu Yilong
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/77769
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-77769
record_format dspace
spelling sg-ntu-dr.10356-777692023-07-07T17:56:30Z Study of object detection using region-based fully convolutional neural networks Liang, Yuehui Lu Yilong School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering With the fast pace of economic development, deep learning has become one of the fastest growing field in recent over ten years. It has been applied and implemented widely such as Intelligent Transportation System (ITS), industrial automation system, data statistic and robotic. Convolutional Neural Network (CNN) is one of the most representative network structures in deep learning technology, and has achieved great success in the field of image processing. This paper covers the concept and development of one of the most popular object detection method-region based fully convolutional neural network (R-FCN). And use high-end computer to evaluate the performance of the model in different data set training and compare with the other convolutional neural network method. Bachelor of Engineering (Electrical and Electronic Engineering) 2019-06-06T04:47:33Z 2019-06-06T04:47:33Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77769 en Nanyang Technological University 49 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Liang, Yuehui
Study of object detection using region-based fully convolutional neural networks
description With the fast pace of economic development, deep learning has become one of the fastest growing field in recent over ten years. It has been applied and implemented widely such as Intelligent Transportation System (ITS), industrial automation system, data statistic and robotic. Convolutional Neural Network (CNN) is one of the most representative network structures in deep learning technology, and has achieved great success in the field of image processing. This paper covers the concept and development of one of the most popular object detection method-region based fully convolutional neural network (R-FCN). And use high-end computer to evaluate the performance of the model in different data set training and compare with the other convolutional neural network method.
author2 Lu Yilong
author_facet Lu Yilong
Liang, Yuehui
format Final Year Project
author Liang, Yuehui
author_sort Liang, Yuehui
title Study of object detection using region-based fully convolutional neural networks
title_short Study of object detection using region-based fully convolutional neural networks
title_full Study of object detection using region-based fully convolutional neural networks
title_fullStr Study of object detection using region-based fully convolutional neural networks
title_full_unstemmed Study of object detection using region-based fully convolutional neural networks
title_sort study of object detection using region-based fully convolutional neural networks
publishDate 2019
url http://hdl.handle.net/10356/77769
_version_ 1772827956268236800