TY - JOUR
T1 - Material classification with laser thermography and machine learning
AU - Aujeszky, Tamas
AU - Korres, Georgios
AU - Eid, Mohamad
N1 - Publisher Copyright:
© 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2019/4/3
Y1 - 2019/4/3
N2 - Robotic devices that can perform teleoperation work in complex and unstructured environments (e.g. healthcare, education, automotive, telepresence, defence, etc.) rely mainly on visual and/or auditory feedback to interact with a remote operator. There is a vital need for measuring the physical properties of ambient environments when performing precise manipulation tasks over a distance, to improve the quality of performance. In this paper, we propose an approach to combine infrared thermography with machine learning for a fast, accurate way to classify objects of different material. A laser source stimulates the surface of the object while an infrared camera captures its thermal signature, extracts features about these signatures and feeds them into a machine learning-based algorithm for classification. Results demonstrated that a classification accuracy of around 97% can be achieved with majority vote Decision Tree classifier, even in the presence of data from multiple data acquisition sessions.
AB - Robotic devices that can perform teleoperation work in complex and unstructured environments (e.g. healthcare, education, automotive, telepresence, defence, etc.) rely mainly on visual and/or auditory feedback to interact with a remote operator. There is a vital need for measuring the physical properties of ambient environments when performing precise manipulation tasks over a distance, to improve the quality of performance. In this paper, we propose an approach to combine infrared thermography with machine learning for a fast, accurate way to classify objects of different material. A laser source stimulates the surface of the object while an infrared camera captures its thermal signature, extracts features about these signatures and feeds them into a machine learning-based algorithm for classification. Results demonstrated that a classification accuracy of around 97% can be achieved with majority vote Decision Tree classifier, even in the presence of data from multiple data acquisition sessions.
KW - Infrared imaging
KW - haptic interfaces
KW - image classification
KW - machine learning
KW - measurement by laser beam
UR - http://www.scopus.com/inward/record.url?scp=85058981654&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058981654&partnerID=8YFLogxK
U2 - 10.1080/17686733.2018.1539895
DO - 10.1080/17686733.2018.1539895
M3 - Article
AN - SCOPUS:85058981654
SN - 1768-6733
VL - 16
SP - 181
EP - 202
JO - Quantitative InfraRed Thermography Journal
JF - Quantitative InfraRed Thermography Journal
IS - 2
ER -