A local adaptive approach  for dense stereo matching in architectural scene reconstruction

dc.contributor.author	Στεντούμης, Χρήστος	el
dc.contributor.author	Γραμματικόπουλος, Λάζαρος	el
dc.contributor.author	Καλησπεράκης, Ηλίας	el
dc.contributor.author	Πέτσα, Έλλη	el
dc.contributor.author	Καρράς, Γιώργος	el
dc.date.accessioned	2015-01-27T19:16:19Z
dc.date.available	2015-01-27T19:16:19Z
dc.date.issued	2015-01-27
dc.identifier.uri	http://hdl.handle.net/11400/4870
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.subject	Matching theory
dc.subject	Correlation (Statistics)
dc.subject	Surface
dc.subject	Reconstruction
dc.subject	Point Cloud
dc.subject.lcsh	Αρχιτεκτονική
dc.title	A local adaptive approach for dense stereo matching in architectural scene reconstruction	en
heal.type	conferenceItem
heal.classification	Topography
heal.classification	Geodesy
heal.classification	Τοπογραφία
heal.classification	Γεωδαισία
heal.classificationURI	http://skos.um.es/unescothes/C04078
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh85053969
heal.classificationURI	N/A-Τοπογραφία
heal.classificationURI	N/A-Γεωδαισία
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh85082044
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh85033032
heal.language	en
heal.access	free
heal.recordProvider	Τ.Ε.Ι. Αθήνας, Σχολή Τεχνολογικών Εφαρμογών, Τμήμα Μηχανικών Πληροφορικής και Μηχανικών Τοπογραφίας & Γεωπληροφορικής	el
heal.publicationDate	2013-02-25
heal.bibliographicCitation	Stentoumis, C., Grammatikopoulos., L., Kalisperakis., I. Petsa E., and Karras., G. (2013). A local adaptive approach for dense stereo matching in architectural scene reconstruction . 5th International Workshop on 3D Virtual Reconstruction and Visualization of Complex Architectures (3D-ARCH '2013), 25-26/02/ 2013, Trento, Italy. Available from: http://portal.survey.ntua.gr/main/labs/photo/staff/gkarras/Karras_3DArch_2013.pdf	en
heal.abstract	In recent years, a demand for 3D models of various scales and precisions has been growing for a wide range of applications; among them, cultural heritage recording is a particularly important and challenging field. We outline an automatic 3D reconstruction pipe-line, mainly focusing on dense stereo-matching which relies on a hierarchical, local optimization scheme. Our matching framework consists of a combination of robust cost measures, extracted via an intuitive cost aggregation support area and set within a coarse-to-fine strategy. The cost function is formulated by combining three individual costs: a cost computed on an extended census transfor-mation of the images; the absolute difference cost, taking into account information from colour channels; and a cost based on the principal image derivatives. An efficient adaptive method of aggregating matching cost for each pixel is then applied, relying on li-nearly expanded cross skeleton support regions. Aggregated cost is smoothed via a 3D Gaussian function. Finally, a simple ‘winner-takes-all’ approach extracts the disparity value with minimum cost. This keeps algorithmic complexity and system computational re-quirements acceptably low for high resolution images (or real-time applications), when compared to complex matching functions of global formulations. The stereo algorithm adopts a hierarchical scheme to accommodate high-resolution images and complex scenes. In a last step, a robust post-processing work-flow is applied to enhance the disparity map and, consequently, the geometric quality of the reconstructed scene. Successful results from our implementation, which combines pre-existing algorithms and novel considera-tions, are presented and evaluated on the Middlebury platform	en
heal.fullTextAvailability	true
heal.conferenceName	5th International Workshop on 3D Virtual Reconstruction and Visualization of Complex Architectures	en
heal.conferenceItemType	full paper