Object tracking in robotic micromanipulation by supervised ensemble learning classifier

Cenev, Zoran; Venäläinen, Janne; Sariola, Veikko; Zhou, Quan

doi:10.1109/marss.2016.7561733

Cited by 4 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trajectories of the objects of interest (gripper tips and manipulated chip) are obtained with the detection algorithms that are described in [8]. The gripper tips were tracked with two vision detectors in the top view and one detector from the side view.…”

Section: B Datamentioning

confidence: 99%

See 1 more Smart Citation

Vision based event classification in robotic micromanipulation

Cenev

Venäläinen

Zhou

2017

2017 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

Self Cite

View full text Add to dashboard Cite

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 %).

show abstract

Section: B Datamentioning

confidence: 99%

“…The hardware configuration of the microrobotic system ( Fig. 1) and the software integration for the vision-based detection of the chips are elaborated in our previous work [8]. The event classification describes whether a manipulated chip has been correctly handled or not.…”

Section: Introductionmentioning

confidence: 99%

Vision based event classification in robotic micromanipulation

Cenev

Venäläinen

Zhou

2017

2017 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…While there are a handful of methods for bright field image processing, most of them require a set of defocused images at varying heights and/or detect objects of one type only [33][34][35][36]. Moreover, some of the methods are not suitable for real-time implementation [37] or only work for specific cell shapes [38].…”

Section: Introductionmentioning

confidence: 99%

An Accurate Perception Method for Low Contrast Bright Field Microscopy in Heterogeneous Microenvironments

et al. 2017

View full text Add to dashboard Cite

Automated optical tweezers-based robotic manipulation of microscale objects requires real-time visual perception for estimating the states, i.e., positions and orientations, of the objects. Such visual perception is particularly challenging in heterogeneous environments comprising mixtures of biological and colloidal objects, such as cells and microspheres, when the popular imaging modality of low contrast bright field microscopy is used. In this paper, we present an accurate method to address this challenge. Our method combines many well-established image processing techniques such as blob detection, histogram equalization, erosion, and dilation with a convolutional neural network in a novel manner. We demonstrate the effectiveness of our processing pipeline in perceiving objects of both regular and irregular shapes in heterogeneous microenvironments of varying compositions. The neural network, in particular, helps in distinguishing the individual microspheres present in dense clusters.

show abstract

“…When the lighting condition changes or there exists occlusion, interference among several objects, optical flow, and template matching methods may fail quickly. Some more advanced algorithms are applied to track cells and other micro-objects, such as cross-correlation analysis [107][108][109], and machine learning methods [110,111]. Although they need to be run with better computational capacity, the better robustness still makes it a popular choice for coping with some complicated problems.…”

Section: Image Processing For Manipulating Biological Cellsmentioning

confidence: 99%

Vision-guided robotic micromanipulation for cell rotation control

Cui

View full text Add to dashboard Cite

Ang Wei Tech, for his invaluable guidance and insightful suggestions throughout my Ph.D. study at Nanyang Technological University. He always encouraged me and provided generous support every time I got lost, not only in my research but also in daily life. His enthusiasm and optimism for research and work keep inspiring me to live a meaningful life, both now and in the future.Secondly, I would like to sincerely express my appreciation to my thesis advisory committee, Prof. Lum Guo Zhan, for his warm help in my exploration of several research projects and valuable sharing of study and life, and Prof. Hu Guoqiang for his kind advice on my research progress.Many thanks also go to my fellow teammates,

show abstract

Object tracking in robotic micromanipulation by supervised ensemble learning classifier

Cited by 4 publications

References 20 publications

Vision based event classification in robotic micromanipulation

Vision based event classification in robotic micromanipulation

An Accurate Perception Method for Low Contrast Bright Field Microscopy in Heterogeneous Microenvironments

Vision-guided robotic micromanipulation for cell rotation control

Contact Info

Product

Resources

About