Title:
Material Classification with Active Thermography on Multiple Household Objects
Material Classification with Active Thermography on Multiple Household Objects
| dc.contributor.advisor | Kemp, Charles C. | |
| dc.contributor.author | Chen, Haofeng | |
| dc.contributor.committeeMember | Hays, James | |
| dc.contributor.department | Computer Science | |
| dc.date.accessioned | 2020-11-09T16:58:34Z | |
| dc.date.available | 2020-11-09T16:58:34Z | |
| dc.date.created | 2019-05 | |
| dc.date.issued | 2019-05 | |
| dc.date.submitted | May 2019 | |
| dc.date.updated | 2020-11-09T16:58:35Z | |
| dc.description.abstract | Active thermography is a technique to inject heat into a target sample and observe the temperature change along time. Such a technique enables a robot to perform material classification with machine learning algorithms and infer material properties of its surroundings. We present a study of material classification on 20 household objects of 5 material classes using active thermography, and analyze factors that impact on material classifiers’ performance on generalizing to heating distances and object instances not present during training. By performing a 20-way classification of the object instances, we show that there is potential for classifiers to generalize to unseen objects made from known material classes. The best-performing algorithm trained on 15 object instances at 5 heating distances (20cm, 25cm, 30cm, 35cm, 40cm) gives an accuracy of 71.7% when generalizing to 5 objects that are not in the training set. | |
| dc.description.degree | Undergraduate | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/1853/63832 | |
| dc.language.iso | en_US | |
| dc.publisher | Georgia Institute of Technology | |
| dc.subject | Material Classification | |
| dc.subject | Active Thermography | |
| dc.subject | Robotic Manipulation | |
| dc.title | Material Classification with Active Thermography on Multiple Household Objects | |
| dc.type | Text | |
| dc.type.genre | Undergraduate Thesis | |
| dspace.entity.type | Publication | |
| local.contributor.advisor | Kemp, Charles C. | |
| local.contributor.corporatename | College of Computing | |
| local.contributor.corporatename | School of Computer Science | |
| local.contributor.corporatename | Undergraduate Research Opportunities Program | |
| local.relation.ispartofseries | Undergraduate Research Option Theses | |
| relation.isAdvisorOfPublication | e4f743b9-0557-4889-a16e-00afe0715f4c | |
| relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
| relation.isOrgUnitOfPublication | 6b42174a-e0e1-40e3-a581-47bed0470a1e | |
| relation.isOrgUnitOfPublication | 0db885f5-939b-4de1-807b-f2ec73714200 | |
| relation.isSeriesOfPublication | e1a827bd-cf25-4b83-ba24-70848b7036ac | |
| thesis.degree.level | Undergraduate |