File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1080/01691864.2016.1197793
- Scopus: eid_2-s2.0-84978955055
- WOS: WOS:000382334900008
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Multi-contour initial pose estimation for 3D registration
Title | Multi-contour initial pose estimation for 3D registration |
---|---|
Authors | |
Keywords | 3D registration Pose estimation |
Issue Date | 2016 |
Citation | Advanced Robotics, 2016, v. 30, n. 17-18, p. 1173-1185 How to Cite? |
Abstract | Reliable manipulation of everyday household objects is essential to the success of service robots. In order to accurately manipulate these objects, robots need to know objects’ full 6-DOF pose, which is challenging due to sensor noise, clutters, and occlusions. In this paper, we present a new approach for effectively guessing the object pose given an observation of just a small patch of the object, by leveraging the fact that many household objects can only keep stable on a planar surface under a small set of poses. In particular, for each stable pose of an object, we slice the object with horizontal planes and extract multiple cross-section 2D contours. The pose estimation is then reduced to find a stable pose whose contour matches best with that of the sensor data, and this can be solved efficiently by cross-correlation. Experiments on the manipulation tasks in the DARPA Robotics Challenge validate our approach. In addition, we also investigate our method’s performance on object recognition tasks raising in the challenge. |
Persistent Identifier | http://hdl.handle.net/10722/308914 |
ISSN | 2023 Impact Factor: 1.4 2023 SCImago Journal Rankings: 0.605 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cheung, Ernest C.H. | - |
dc.contributor.author | Chao, Cao | - |
dc.contributor.author | Pan, Jia | - |
dc.date.accessioned | 2021-12-08T07:50:24Z | - |
dc.date.available | 2021-12-08T07:50:24Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | Advanced Robotics, 2016, v. 30, n. 17-18, p. 1173-1185 | - |
dc.identifier.issn | 0169-1864 | - |
dc.identifier.uri | http://hdl.handle.net/10722/308914 | - |
dc.description.abstract | Reliable manipulation of everyday household objects is essential to the success of service robots. In order to accurately manipulate these objects, robots need to know objects’ full 6-DOF pose, which is challenging due to sensor noise, clutters, and occlusions. In this paper, we present a new approach for effectively guessing the object pose given an observation of just a small patch of the object, by leveraging the fact that many household objects can only keep stable on a planar surface under a small set of poses. In particular, for each stable pose of an object, we slice the object with horizontal planes and extract multiple cross-section 2D contours. The pose estimation is then reduced to find a stable pose whose contour matches best with that of the sensor data, and this can be solved efficiently by cross-correlation. Experiments on the manipulation tasks in the DARPA Robotics Challenge validate our approach. In addition, we also investigate our method’s performance on object recognition tasks raising in the challenge. | - |
dc.language | eng | - |
dc.relation.ispartof | Advanced Robotics | - |
dc.subject | 3D registration | - |
dc.subject | Pose estimation | - |
dc.title | Multi-contour initial pose estimation for 3D registration | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1080/01691864.2016.1197793 | - |
dc.identifier.scopus | eid_2-s2.0-84978955055 | - |
dc.identifier.volume | 30 | - |
dc.identifier.issue | 17-18 | - |
dc.identifier.spage | 1173 | - |
dc.identifier.epage | 1185 | - |
dc.identifier.eissn | 1568-5535 | - |
dc.identifier.isi | WOS:000382334900008 | - |