Real-time monocular object instance 6D pose estimation

Simple item page
dc.contributor.authorDo, T.
dc.contributor.authorPham, T.
dc.contributor.authorCai, M.
dc.contributor.authorReid, I.
dc.contributor.conferenceBritish Machine Vision Conference (BMVC) (3 Sep 2018 - 6 Sep 2018 : Newcastle upon Tyne, UK)
dc.date.issued2019
dc.description.abstractIn this work, we present, LieNet, a novel deep learning framework that simultaneously detects, segments multiple object instances, and estimates their 6D poses from a single RGB image without requiring additional post-processing. Our system is accurate and fast (∼10 fps), which is well suited for real-time applications. In particular, LieNet detects and segments object instances in the image analogous to modern instance segmentation networks such as Mask R-CNN, but contains a novel additional sub-network for 6D pose estimation. LieNet estimates the rotation matrix of an object by regressing a Lie algebra based rotation representation, and estimates the translation vector by predicting the distance of the object to the camera center. The experiments on two standard pose benchmarking datasets show that LieNet greatly outperforms other recent CNN based pose prediction methods when they are used with monocular images and without post-refinements.
dc.description.statementofresponsibilityThanh-Toan Do, Trung Pham, Ming Cai, Ian Reid
dc.identifier.citationProceedings of the 29th British Machine Vision Conference (BMVC 2018), 2019, pp.1-12
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.urihttp://hdl.handle.net/2440/124685
dc.language.isoen
dc.publisherBMVC Press
dc.rights© 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
dc.source.urihttp://bmvc2018.org/programmedetail.html
dc.titleReal-time monocular object instance 6D pose estimation
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_124685.pdf
Size:
7.42 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Computer Science publications