Show simple item record

dc.contributor.advisorLeslie Pack Kaelbling and Tomás Lozano-Pérez.en_US
dc.contributor.authorPopović, Sanja, M. Eng. Massachusetts Institute of Technologyen_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2014-03-06T15:44:03Z
dc.date.available2014-03-06T15:44:03Z
dc.date.copyright2013en_US
dc.date.issued2013en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/85466
dc.descriptionThesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2013.en_US
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 40-41).en_US
dc.description.abstractModern graphics hardware (GPUs) are an amazing computational resource, but only for algorithms with suitable structure. Computer vision algorithms have many characteristics in common with computer graphics algorithms, in particular, they repeat some operations, such as feature computations, at many places in the image. However, there are also more global operations, such as finding nearest neighbors in feature space, that present more of a challenge. In this thesis, we showed how a state-of-the-art object detector, based on RGB-D images, could be parallelized for use on GPUs. By using nVidia's CUDA platform we improved the running times of critical sections up to 38 times. We also built a two-stage pipeline that improves multiple object detection in cluttered scenes. The first stage aims to achieve high precision, even at the cost of lower recall, by detecting only the less occluded objects. This results in large fraction of the scene being labeled which enables the algorithm in the second stage to focus on the less visible objects that would otherwise be missed. We analyze the performance of our algorithm and lay grounds for the future work and extensions.en_US
dc.description.statementofresponsibilityby Sanja Popovic.en_US
dc.format.extent41 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleParallelized two-stage object detection in cluttered RGB-D scenesen_US
dc.title.alternativeParallelized 2-stage object detection in cluttered RGB-D scenesen_US
dc.typeThesisen_US
dc.description.degreeM. Eng.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
dc.identifier.oclc870969578en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record