Deep learning for object detection and image segmentation

In recent years, the fast-moving consumer goods (FMCG) industry has shown significant interest in robot warehouse automation technology due to the increasing demand of e-commerce, fast and reliable delivery. However, it is not a simple task to pack a large variety of products according to mass custo...

Full description

Saved in:
Bibliographic Details
Main Author: Tan, Yan Hwa
Other Authors: Dino Accoto
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140433
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140433
record_format dspace
spelling sg-ntu-dr.10356-1404332023-03-04T20:00:57Z Deep learning for object detection and image segmentation Tan, Yan Hwa Dino Accoto School of Mechanical and Aerospace Engineering A*STAR Advanced Remanufacturing and Technology Center (ARTC) daccoto@ntu.edu.sg Engineering::Mechanical engineering In recent years, the fast-moving consumer goods (FMCG) industry has shown significant interest in robot warehouse automation technology due to the increasing demand of e-commerce, fast and reliable delivery. However, it is not a simple task to pack a large variety of products according to mass customized orders. Therefore, a fully autonomous warehouse pick-and-place system is able to complete the job with ease by employing a robust vision system that reliably locates and recognizes objects from cluttered environment, different objects and self-occlusions. The aim of this project is to develop an automated solution to allow the robot to pick up the indicated object accurately from a clustered bin in bin-picking. The robot system setup consists of a UR5 robotic arm attached with a gripper and a vision camera. In the proposed approach, we segmented and labelled multiple perspective of a view using a convolutional neural network. A large amount of training data is required to train a deep neural network for segmentation. Therefore, the proposed solution used a self-supervised method to train a large dataset and at a faster speed. The Mask-R-CNN approach was also implemented to identify each item and their individual masks to achieve a higher accuracy for object detection and image segmentation. Bachelor of Engineering (Mechanical Engineering) 2020-05-29T02:06:05Z 2020-05-29T02:06:05Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/140433 en C086 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::Mechanical engineering
spellingShingle Engineering::Mechanical engineering
Tan, Yan Hwa
Deep learning for object detection and image segmentation
description In recent years, the fast-moving consumer goods (FMCG) industry has shown significant interest in robot warehouse automation technology due to the increasing demand of e-commerce, fast and reliable delivery. However, it is not a simple task to pack a large variety of products according to mass customized orders. Therefore, a fully autonomous warehouse pick-and-place system is able to complete the job with ease by employing a robust vision system that reliably locates and recognizes objects from cluttered environment, different objects and self-occlusions. The aim of this project is to develop an automated solution to allow the robot to pick up the indicated object accurately from a clustered bin in bin-picking. The robot system setup consists of a UR5 robotic arm attached with a gripper and a vision camera. In the proposed approach, we segmented and labelled multiple perspective of a view using a convolutional neural network. A large amount of training data is required to train a deep neural network for segmentation. Therefore, the proposed solution used a self-supervised method to train a large dataset and at a faster speed. The Mask-R-CNN approach was also implemented to identify each item and their individual masks to achieve a higher accuracy for object detection and image segmentation.
author2 Dino Accoto
author_facet Dino Accoto
Tan, Yan Hwa
format Final Year Project
author Tan, Yan Hwa
author_sort Tan, Yan Hwa
title Deep learning for object detection and image segmentation
title_short Deep learning for object detection and image segmentation
title_full Deep learning for object detection and image segmentation
title_fullStr Deep learning for object detection and image segmentation
title_full_unstemmed Deep learning for object detection and image segmentation
title_sort deep learning for object detection and image segmentation
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/140433
_version_ 1759858136785616896