Title:
Detecting Partially Occluded Objects via Segmentation and Validation
Detecting Partially Occluded Objects via Segmentation and Validation
| dc.contributor.author | Levihn, Martin | |
| dc.contributor.author | Dutton, Matthew | |
| dc.contributor.author | Trevor, Alexander J. B. | |
| dc.contributor.author | Stilman, Mike | |
| dc.contributor.corporatename | Georgia Institute of Technology. Center for Robotics and Intelligent Machines | |
| dc.date.accessioned | 2012-04-03T13:33:00Z | |
| dc.date.available | 2012-04-03T13:33:00Z | |
| dc.date.issued | 2012 | |
| dc.description.abstract | This paper presents a novel algorithm: Verfied Partial Object Detector (VPOD) for accurate detection of partially occluded objects such as furniture in 3D point clouds. VPOD is implemented and validated on real sensor data obtained by our robot. It extends Viewpoint Feature Histograms (VFH) which classify unoccluded objects to also classifying partially occluded objects such as furniture that might be seen in typical office environments. To achieve this result, VPOD employs two strategies. First, object models are segmented and the object database is extended to include partial models. Second, once a matching partial object is detected, the full object model is aligned back into the scene and verified for consistency with the point cloud data. Overall, our approach increases the number of objects found and substantially reduces false positives due to the verification process. | en_US |
| dc.identifier.uri | http://hdl.handle.net/1853/43174 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Georgia Institute of Technology | en_US |
| dc.relation.ispartofseries | GT-GOLEM-2012-001 | en_US |
| dc.subject | Object detection | en_US |
| dc.subject | Point clouds | en_US |
| dc.subject | Robots | en_US |
| dc.subject | Segmentation | en_US |
| dc.subject | Validation | en_US |
| dc.subject | Verfied partial object detector | en_US |
| dc.subject | Viewpoint feature histograms | en_US |
| dc.title | Detecting Partially Occluded Objects via Segmentation and Validation | en_US |
| dc.type | Text | |
| dc.type.genre | Technical Report | |
| dspace.entity.type | Publication | |
| local.contributor.corporatename | Humanoid Robotics Laboratory | |
| local.contributor.corporatename | College of Computing | |
| local.relation.ispartofseries | Humanoid Robotics Laboratory Technical Report Series | |
| relation.isOrgUnitOfPublication | 05bf85fb-965e-425d-af8b-dbf56e0d9797 | |
| relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
| relation.isSeriesOfPublication | e2b4b849-c3fb-4761-b071-c47f921fc942 |