Show simple item record

dc.contributor.authorSteedly, Drewen_US
dc.date.accessioned2005-03-01T19:44:31Z
dc.date.available2005-03-01T19:44:31Z
dc.date.issued2004-12-01en_US
dc.identifier.urihttp://hdl.handle.net/1853/4925
dc.description.abstractThis thesis explores efficient techniques for generating 3D reconstructions from imagery. Non-linear optimization is one of the core techniques used when computing a reconstruction and is a computational bottleneck for large sets of images. Since non-linear optimization requires a good initialization to avoid getting stuck in local minima, robust systems for generating reconstructions from images build up the reconstruction incrementally. A hierarchical approach is to split up the images into small subsets, reconstruct each subset independently and then hierarchically merge the subsets. Rigidly locking together portions of the reconstructions reduces the number of parameters needed to represent them when merging, thereby lowering the computational cost of the optimization. We present two techniques that involve optimizing with parts of the reconstruction rigidly locked together. In the first, we start by rigidly grouping the cameras and scene features from each of the reconstructions being merged into separate groups. Cameras and scene features are then incrementally unlocked and optimized until the reconstruction is close to the minimum energy. This technique is most effective when the influence of the new measurements is restricted to a small set of parameters. Measurements that stitch together weakly coupled portions of the reconstruction, though, tend to cause deformations in the low error modes of the reconstruction and cannot be efficiently incorporated with the previous technique. To address this, we present a spectral technique for clustering the tightly coupled portions of a reconstruction into rigid groups. Reconstructions partitioned in this manner can closely mimic the poorly conditioned, low error modes, and therefore efficiently incorporate measurements that stitch together weakly coupled portions of the reconstruction. We explain how this technique can be used to scalably and efficiently generate reconstructions from large sets of images.en_US
dc.format.extent2791483 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectBundle adjustmenten_US
dc.subjectPhotogrammetry
dc.subjectStructure from motion
dc.subjectComputer vision
dc.subjectSpectral partitioning
dc.subjectSparse matrix
dc.subject.lcshThree-dimensional imagingen_US
dc.subject.lcshPhotogrammetryen_US
dc.subject.lcshImage reconstructionen_US
dc.titleRigid Partitioning Techniques for Efficiently Generating 3D Reconstructions from Imagesen_US
dc.typeDissertationen_US
dc.description.degreePh.D.en_US
dc.contributor.departmentComputingen_US
dc.description.advisorCommittee Chair: Irfan Essa; Committee Member: Aaron Bobick; Committee Member: Anthony Yezzi; Committee Member: Frank Dellaert; Committee Member: Rick Szeliskien_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record