File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3390/s150921054
- Scopus: eid_2-s2.0-84940707754
- WOS: WOS:000362512200006
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Saliency-Guided Detection of Unknown Objects in RGB-D Indoor Scenes
Title | Saliency-Guided Detection of Unknown Objects in RGB-D Indoor Scenes |
---|---|
Authors | |
Keywords | RGB-D object segmentation Saliency detection Unknown object detection |
Issue Date | 2015 |
Publisher | Molecular Diversity Preservation International. The Journal's web site is located at http://www.mdpi.net/sensors |
Citation | Sensors, 2015, v. 15 n. 9, p. 21054-21074 How to Cite? |
Abstract | This paper studies the problem of detecting unknown objects within indoor environments in an active and natural manner. The visual saliency scheme utilizing both color and depth cues is proposed to arouse the interests of the machine system for detecting unknown objects at salient positions in a 3D scene. The 3D points at the salient positions are selected as seed points for generating object hypotheses using the 3D shape. We perform multi-class labeling on a Markov random field (MRF) over the voxels of the 3D scene, combining cues from object hypotheses and 3D shape. The results from MRF are further refined by merging the labeled objects, which are spatially connected and have high correlation between color histograms. Quantitative and qualitative evaluations on two benchmark RGB-D datasets illustrate the advantages of the proposed method. The experiments of object detection and manipulation performed on a mobile manipulator validate its effectiveness and practicability in robotic applications. |
Persistent Identifier | http://hdl.handle.net/10722/234604 |
ISSN | 2023 Impact Factor: 3.4 2023 SCImago Journal Rankings: 0.786 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | BAO, J | - |
dc.contributor.author | JIA, Y | - |
dc.contributor.author | CHENG, Y | - |
dc.contributor.author | Xi, N | - |
dc.date.accessioned | 2016-10-14T13:47:59Z | - |
dc.date.available | 2016-10-14T13:47:59Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Sensors, 2015, v. 15 n. 9, p. 21054-21074 | - |
dc.identifier.issn | 1424-8220 | - |
dc.identifier.uri | http://hdl.handle.net/10722/234604 | - |
dc.description.abstract | This paper studies the problem of detecting unknown objects within indoor environments in an active and natural manner. The visual saliency scheme utilizing both color and depth cues is proposed to arouse the interests of the machine system for detecting unknown objects at salient positions in a 3D scene. The 3D points at the salient positions are selected as seed points for generating object hypotheses using the 3D shape. We perform multi-class labeling on a Markov random field (MRF) over the voxels of the 3D scene, combining cues from object hypotheses and 3D shape. The results from MRF are further refined by merging the labeled objects, which are spatially connected and have high correlation between color histograms. Quantitative and qualitative evaluations on two benchmark RGB-D datasets illustrate the advantages of the proposed method. The experiments of object detection and manipulation performed on a mobile manipulator validate its effectiveness and practicability in robotic applications. | - |
dc.language | eng | - |
dc.publisher | Molecular Diversity Preservation International. The Journal's web site is located at http://www.mdpi.net/sensors | - |
dc.relation.ispartof | Sensors | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | RGB-D object segmentation | - |
dc.subject | Saliency detection | - |
dc.subject | Unknown object detection | - |
dc.title | Saliency-Guided Detection of Unknown Objects in RGB-D Indoor Scenes | - |
dc.type | Article | - |
dc.identifier.email | Xi, N: xining@hku.hk | - |
dc.identifier.authority | Xi, N=rp02044 | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.3390/s150921054 | - |
dc.identifier.scopus | eid_2-s2.0-84940707754 | - |
dc.identifier.hkuros | 269251 | - |
dc.identifier.volume | 15 | - |
dc.identifier.issue | 9 | - |
dc.identifier.spage | 21054 | - |
dc.identifier.epage | 21074 | - |
dc.identifier.isi | WOS:000362512200006 | - |
dc.publisher.place | Switzerland | - |
dc.identifier.issnl | 1424-8220 | - |