Object recognition and 6D pose estimation using deep learning
Object recognition and 6D pose estimation are imperative for robots to relate to the real world. However, due to occlusion, clutter and the properties of various objects in a scene, it might be challenging and tedious for a robot to recognize and estimate the 6D pose of objects. Various methods have...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/77466 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-77466 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-774662023-07-07T16:44:44Z Object recognition and 6D pose estimation using deep learning Sivadas Thinagar Nanoo Teoh Eam Khwang Wang Kong Wah School of Electrical and Electronic Engineering A*STAR DRNTU::Engineering::Electrical and electronic engineering Object recognition and 6D pose estimation are imperative for robots to relate to the real world. However, due to occlusion, clutter and the properties of various objects in a scene, it might be challenging and tedious for a robot to recognize and estimate the 6D pose of objects. Various methods have been presented throughout the years with concern to this topic. However, many of these methods have its set back and limitations. Due to these reasons, rose the motivation to develop a robust and versatile real time system capable of accurate object recognition and 6D pose estimation with respect to the industrial standards. Over the years, with the advancement in technology, computing power have improved drastically. Algorithms, techniques and methods that were once infeasible to implement due to high computational power requirements could now be done with ease. One such implementation is none other than deep learning. It is now the current state-of-the-art technology. Since, this project is in relation with computer vision, the deep learning architecture proposed would be a convolutional neural network. Hence, the dataset used would consist of images. A deep learning framework known as PoseCNN is explored for object recognition and 6D pose estimation capabilities. In this project, a detailed literature review of PoseCNN, as well as comparisons with current approaches, will be reviewed. Finally, the results obtained using the YCB dataset would be presented. Bachelor of Engineering (Electrical and Electronic Engineering) 2019-05-29T06:55:51Z 2019-05-29T06:55:51Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77466 en Nanyang Technological University 134 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 Sivadas Thinagar Nanoo Object recognition and 6D pose estimation using deep learning |
description |
Object recognition and 6D pose estimation are imperative for robots to relate to the real world. However, due to occlusion, clutter and the properties of various objects in a scene, it might be challenging and tedious for a robot to recognize and estimate the 6D pose of objects. Various methods have been presented throughout the years with concern to this topic. However, many of these methods have its set back and limitations. Due to these reasons, rose the motivation to develop a robust and versatile real time system capable of accurate object recognition and 6D pose estimation with respect to the industrial standards. Over the years, with the advancement in technology, computing power have improved drastically. Algorithms, techniques and methods that were once infeasible to implement due to high computational power requirements could now be done with ease. One such implementation is none other than deep learning. It is now the current state-of-the-art technology. Since, this project is in relation with computer vision, the deep learning architecture proposed would be a convolutional neural network. Hence, the dataset used would consist of images. A deep learning framework known as PoseCNN is explored for object recognition and 6D pose estimation capabilities. In this project, a detailed literature review of PoseCNN, as well as comparisons with current approaches, will be reviewed. Finally, the results obtained using the YCB dataset would be presented. |
author2 |
Teoh Eam Khwang |
author_facet |
Teoh Eam Khwang Sivadas Thinagar Nanoo |
format |
Final Year Project |
author |
Sivadas Thinagar Nanoo |
author_sort |
Sivadas Thinagar Nanoo |
title |
Object recognition and 6D pose estimation using deep learning |
title_short |
Object recognition and 6D pose estimation using deep learning |
title_full |
Object recognition and 6D pose estimation using deep learning |
title_fullStr |
Object recognition and 6D pose estimation using deep learning |
title_full_unstemmed |
Object recognition and 6D pose estimation using deep learning |
title_sort |
object recognition and 6d pose estimation using deep learning |
publishDate |
2019 |
url |
http://hdl.handle.net/10356/77466 |
_version_ |
1772828210512265216 |