Object tracking in robotic micromanipulation by supervised ensemble learning classifier

Zoran Cenev; Janne Venäläinen; Veikko Sariola; Quan Zhou

doi:10.1109/MARSS.2016.7561733

Object tracking in robotic micromanipulation by supervised ensemble learning classifier

Zoran Cenev, Janne Venäläinen, Veikko Sariola, Quan Zhou

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

Autonomous micromanipulation has a great potential to impact every research field concerning objects at a small scale. In this paper, we report our work on detection and tracking of a transparent SU-8 microchip in 3D Cartesian space during micromanipulation. Conditions such as occlusion, variant object orientation and poor edge prominence hinder the implementation of conventional vision algorithms. To enable tracking in such difficult conditions, an object detection classifier that utilizes an ensemble machine learning algorithm has been implemented. The classifier has been trained with 165 and 85 unique positive and negative samples, respectively. Object detection was achieved at a distance of three times the nominal depth of field with maximum tracking error of only 12 % of the object size.

Original language	English
Title of host publication	Proceedings of the 2016 International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS 2016
Publisher	IEEE
ISBN (Electronic)	9781509015108
DOIs	https://doi.org/10.1109/MARSS.2016.7561733
Publication status	Published - 6 Sept 2016
MoE publication type	A4 Article in a conference publication
Event	International Conference on Manipulation, Automation and Robotics at Small Scales - Paris, France Duration: 18 Jul 2016 → 22 Jul 2016 Conference number: 1

Conference

Conference	International Conference on Manipulation, Automation and Robotics at Small Scales
Abbreviated title	MARSS 2016
Country/Territory	France
City	Paris
Period	18/07/2016 → 22/07/2016

Keywords

classification
detection
Ensemble
learning
machine
micro-object
micromanipulation
robotic

Access to Document

10.1109/MARSS.2016.7561733

OpenUrl availability

Full text

Cite this

@inproceedings{7451ecc03bcb43d79083e3c48215d06e,

title = "Object tracking in robotic micromanipulation by supervised ensemble learning classifier",

abstract = "Autonomous micromanipulation has a great potential to impact every research field concerning objects at a small scale. In this paper, we report our work on detection and tracking of a transparent SU-8 microchip in 3D Cartesian space during micromanipulation. Conditions such as occlusion, variant object orientation and poor edge prominence hinder the implementation of conventional vision algorithms. To enable tracking in such difficult conditions, an object detection classifier that utilizes an ensemble machine learning algorithm has been implemented. The classifier has been trained with 165 and 85 unique positive and negative samples, respectively. Object detection was achieved at a distance of three times the nominal depth of field with maximum tracking error of only 12 % of the object size.",

keywords = "classification, detection, Ensemble, learning, machine, micro-object, micromanipulation, robotic",

author = "Zoran Cenev and Janne Ven{\"a}l{\"a}inen and Veikko Sariola and Quan Zhou",

year = "2016",

month = sep,

day = "6",

doi = "10.1109/MARSS.2016.7561733",

language = "English",

booktitle = "Proceedings of the 2016 International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS 2016",

publisher = "IEEE",

address = "United States",

note = "International Conference on Manipulation, Automation and Robotics at Small Scales , MARSS 2016 ; Conference date: 18-07-2016 Through 22-07-2016",

}

Cenev, Z, Venäläinen, J, Sariola, V & Zhou, Q 2016, Object tracking in robotic micromanipulation by supervised ensemble learning classifier. in Proceedings of the 2016 International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS 2016., 7561733, IEEE, International Conference on Manipulation, Automation and Robotics at Small Scales , Paris, France, 18/07/2016. https://doi.org/10.1109/MARSS.2016.7561733

Object tracking in robotic micromanipulation by supervised ensemble learning classifier. / Cenev, Zoran; Venäläinen, Janne; Sariola, Veikko et al.
Proceedings of the 2016 International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS 2016. IEEE, 2016. 7561733.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Object tracking in robotic micromanipulation by supervised ensemble learning classifier

AU - Cenev, Zoran

AU - Venäläinen, Janne

AU - Sariola, Veikko

AU - Zhou, Quan

N1 - Conference code: 1

PY - 2016/9/6

Y1 - 2016/9/6

N2 - Autonomous micromanipulation has a great potential to impact every research field concerning objects at a small scale. In this paper, we report our work on detection and tracking of a transparent SU-8 microchip in 3D Cartesian space during micromanipulation. Conditions such as occlusion, variant object orientation and poor edge prominence hinder the implementation of conventional vision algorithms. To enable tracking in such difficult conditions, an object detection classifier that utilizes an ensemble machine learning algorithm has been implemented. The classifier has been trained with 165 and 85 unique positive and negative samples, respectively. Object detection was achieved at a distance of three times the nominal depth of field with maximum tracking error of only 12 % of the object size.

AB - Autonomous micromanipulation has a great potential to impact every research field concerning objects at a small scale. In this paper, we report our work on detection and tracking of a transparent SU-8 microchip in 3D Cartesian space during micromanipulation. Conditions such as occlusion, variant object orientation and poor edge prominence hinder the implementation of conventional vision algorithms. To enable tracking in such difficult conditions, an object detection classifier that utilizes an ensemble machine learning algorithm has been implemented. The classifier has been trained with 165 and 85 unique positive and negative samples, respectively. Object detection was achieved at a distance of three times the nominal depth of field with maximum tracking error of only 12 % of the object size.

KW - classification

KW - detection

KW - Ensemble

KW - learning

KW - machine

KW - micro-object

KW - micromanipulation

KW - robotic

UR - http://www.scopus.com/inward/record.url?scp=84988980209&partnerID=8YFLogxK

U2 - 10.1109/MARSS.2016.7561733

DO - 10.1109/MARSS.2016.7561733

M3 - Conference contribution

AN - SCOPUS:84988980209

BT - Proceedings of the 2016 International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS 2016

PB - IEEE

T2 - International Conference on Manipulation, Automation and Robotics at Small Scales

Y2 - 18 July 2016 through 22 July 2016

ER -

Object tracking in robotic micromanipulation by supervised ensemble learning classifier

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this