Abstract
Autonomous positioning of small objects to create heterogeneous structures has great potential to advance the current micromanipulation procedures. To achieve autonomous micromanipulation, it is required to recognize the manipulation events. In this work, different classification algorithms including five common supervised learning methods are assessed for identifying states of manipulation. The classifiers are trained with data that consists of 3056 video frames and validated on 2545 videos frames. The best machine learning classifiers classified the events with 92.9 % accuracy, higher than the result of logic-based classification (88.9 %).
Original language | English |
---|---|
Title of host publication | Proceedings of the 2017 International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS 2017 |
Publisher | IEEE |
Number of pages | 6 |
ISBN (Electronic) | 978-1-5386-0346-8 |
DOIs | |
Publication status | Published - 2017 |
MoE publication type | A4 Article in a conference publication |
Event | International Conference on Manipulation, Automation and Robotics at Small Scales - University of Montreal, Montreal, Canada Duration: 17 Jul 2017 → 21 Jul 2017 http://marss-conference.org/ |
Conference
Conference | International Conference on Manipulation, Automation and Robotics at Small Scales |
---|---|
Abbreviated title | MARSS |
Country/Territory | Canada |
City | Montreal |
Period | 17/07/2017 → 21/07/2017 |
Internet address |
Keywords
- event classification
- micromanipulation
- machine vision
- supervised learning