Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects

Robotic manipulation of objects requires a fast recognition from image stream. For many cylindrical object (e.g., cans, cups, pipes, bottles, etc.) this is possible through detection of ellipse depicting the circular top of the cylinder. Growing industrial and warehouse applications of robots drive...

Full description

Saved in:
Bibliographic Details
Main Authors: Dong, Huixu, Sun, Guangbin, Pang, Wee-Ching, Asadi, Ehsan, Prasad, Dilip Kumar, Chen, I-Ming
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140260
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140260
record_format dspace
spelling sg-ntu-dr.10356-1402602020-05-27T09:17:14Z Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects Dong, Huixu Sun, Guangbin Pang, Wee-Ching Asadi, Ehsan Prasad, Dilip Kumar Chen, I-Ming School of Computer Science and Engineering Robotics Research Centre Engineering::Computer science and engineering Grasping Perception for Grasping and Manipulation Robotic manipulation of objects requires a fast recognition from image stream. For many cylindrical object (e.g., cans, cups, pipes, bottles, etc.) this is possible through detection of ellipse depicting the circular top of the cylinder. Growing industrial and warehouse applications of robots drive the demand for fast and reliable detection of ellipses, while state-of-the-art methods are lacking in either speed or accuracy strength. We present a novel algorithm to perform fast and robust ellipse detection. First, the method utilizes the information of edge curvature to split curves into arcs. Next, the arc convexity-concavity is used to classify arcs into different quadrants of ellipses. Then, based on multiple geometric constraints the arcs can be grouped at low computational cost. Our method is compared with six state-of-the-art methods using three public image datasets. The comparison results show that the proposed algorithm outperforms other methods with high detection accuracy and fast detection speed. Lastly, the algorithm is applied to identifying cylindrical objects in real-time for arranging and tracking purposes. 2020-05-27T09:17:14Z 2020-05-27T09:17:14Z 2018 Journal Article Dong, H., Sun, G., Pang, W.-C., Asadi, E., Prasad, D. K., & Chen, I.-M. (2018). Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects. IEEE Robotics and Automation Letters, 3(4), 2754-2761. doi:10.1109/LRA.2018.2836428 2377-3766 https://hdl.handle.net/10356/140260 10.1109/LRA.2018.2836428 2-s2.0-85053328041 4 3 2754 2761 en IEEE Robotics and Automation Letters © 2018 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Grasping
Perception for Grasping and Manipulation
spellingShingle Engineering::Computer science and engineering
Grasping
Perception for Grasping and Manipulation
Dong, Huixu
Sun, Guangbin
Pang, Wee-Ching
Asadi, Ehsan
Prasad, Dilip Kumar
Chen, I-Ming
Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
description Robotic manipulation of objects requires a fast recognition from image stream. For many cylindrical object (e.g., cans, cups, pipes, bottles, etc.) this is possible through detection of ellipse depicting the circular top of the cylinder. Growing industrial and warehouse applications of robots drive the demand for fast and reliable detection of ellipses, while state-of-the-art methods are lacking in either speed or accuracy strength. We present a novel algorithm to perform fast and robust ellipse detection. First, the method utilizes the information of edge curvature to split curves into arcs. Next, the arc convexity-concavity is used to classify arcs into different quadrants of ellipses. Then, based on multiple geometric constraints the arcs can be grouped at low computational cost. Our method is compared with six state-of-the-art methods using three public image datasets. The comparison results show that the proposed algorithm outperforms other methods with high detection accuracy and fast detection speed. Lastly, the algorithm is applied to identifying cylindrical objects in real-time for arranging and tracking purposes.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Dong, Huixu
Sun, Guangbin
Pang, Wee-Ching
Asadi, Ehsan
Prasad, Dilip Kumar
Chen, I-Ming
format Article
author Dong, Huixu
Sun, Guangbin
Pang, Wee-Ching
Asadi, Ehsan
Prasad, Dilip Kumar
Chen, I-Ming
author_sort Dong, Huixu
title Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
title_short Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
title_full Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
title_fullStr Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
title_full_unstemmed Fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
title_sort fast ellipse detection via gradient information for robotic manipulation of cylindrical objects
publishDate 2020
url https://hdl.handle.net/10356/140260
_version_ 1681059534595948544