Show simple item record

dc.contributor.authorHema, Chengalvarayan Radhakrishnamurthy
dc.contributor.authorPaulraj, Murugesapandian
dc.contributor.authorNagaran, R.
dc.contributor.authorSazali, Yaacob
dc.date.accessioned2009-08-11T08:45:41Z
dc.date.available2009-08-11T08:45:41Z
dc.date.issued2006
dc.identifier.citationp.1-5en_US
dc.identifier.isbn1-4244-0024-4
dc.identifier.urihttp://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=4018810
dc.identifier.urihttp://dspace.unimap.edu.my/123456789/6835
dc.descriptionLink to publisher's homepage at http://ieeexplore.ieee.orgen_US
dc.description.abstractIn this paper we present a stereo vision system for segmentation of partially occluded objects and computation of object grasping point in bin picking environments. The stereo vision system was interfaced with an Adept SCARA Robot to perform bin picking operations. Most researches on bin picking involve combination of vision and force sensors, however in this research an attempt is made to develop a bin picking system using only vision sensors for bin pick and place operation. An algorithm to segment partially occluded objects is proposed. The proposed stereo vision system was found to be effective for partially occluded objects and in the absence of albedo effects. The results are validated through real time bin picking experiments on the Adept Robot.en_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.relation.ispartofseriesProceedings of IEEE Conference on Robotics, Automation and Mechatronics 2006en_US
dc.subjectBin pickingen_US
dc.subjectNeural networksen_US
dc.subjectObject localizationen_US
dc.subjectSegmentationen_US
dc.subjectStereo visionen_US
dc.subjectControl engineering computingen_US
dc.subjectRobot visionen_US
dc.subjectRoboticsen_US
dc.subjectImage sensorsen_US
dc.titleObject localization using stereo sensors for adept SCARA roboten_US
dc.typeArticleen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record