Unsupervised segmentation of stereoscopic video objects

dc.contributor.author	Νταλιάνης, Κλήμης Σ.	el
dc.contributor.author	Δουλάμης, Αναστάσιος Δ.	el
dc.contributor.author	Δουλάμης, Νικόλαος Δ.	el
dc.contributor.author	Μαστοράκης, Νίκος Ε.	el
dc.contributor.author	Δρίγκας, Αθανάσιος Σ.	el
dc.date.accessioned	2015-06-09T21:48:09Z
dc.date.available	2015-06-09T21:48:09Z
dc.date.issued	2015-06-10
dc.identifier.uri	http://hdl.handle.net/11400/15627
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.source	http://link.springer.com/article/10.1007%2Fs11265-014-0921-0	en
dc.subject	Ενεργό περίγραμμα
dc.subject	Ελκυστικό σημείο αιχμής
dc.subject	Βάθος χάρτη
dc.subject	Πεδίο ανισότητας
dc.subject	αξιολόγηση των επιδόσεων
dc.subject	Active contour
dc.subject	Attractive edge point
dc.subject	Depth map
dc.subject	Disparity field
dc.subject	Performance--Evaluation
dc.title	Unsupervised segmentation of stereoscopic video objects	en
heal.type	journalArticle
heal.secondaryTitle	constrained segmentation fusion versus greedy active contours	en
heal.classification	Πληροφορική
heal.classification	Πληροφοριακά συστήματα
heal.classification	Computer science
heal.classification	Information systems
heal.classificationURI	N/A-Πληροφορική
heal.classificationURI	N/A-Πληροφοριακά συστήματα
heal.classificationURI	http://skos.um.es/unescothes/C00750
heal.classificationURI	http://skos.um.es/unescothes/C01993
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh2010105499
heal.identifier.secondary	DOI: 10.1007/s11265-014-0921-0
heal.language	en
heal.access	campus
heal.recordProvider	Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Διοίκησης και Οικονομίας. Τμήμα Εμπορίας και Διαφήμισης	el
heal.publicationDate	2014-07-09
heal.bibliographicCitation	Ntalianis, K.S., Doulamis, A.D., Doulamis, N.D., Mastorakis, N.E. and Drigas, A.S. (2014) Unsupervised Segmentation of Stereoscopic Video Objects: Constrained Segmentation Fusion Versus Greedy Active Contours. Journal of Signal Processing Systems. [Online] Available from: http://link.springer.com [Accessed 09/06/2015]	en
heal.abstract	In this paper two efficient unsupervised video object segmentation approaches are proposed and thoroughly compared. Both methods are based on the exploitation of depth information, estimated from stereoscopic pairs. Depth is a more efficient semantic descriptor of visual content, since usually an object is located on one depth plane. However, depth information fails to accurately represent the contours of an object mainly due to erroneous disparity estimation and occlusion issues. For this reason, the first approach projects color segments onto depth information in order to address the limitations of both depth and color segmentation; color segmentation usually over-partitions an object into several regions, while depth fails to precisely represent object contours. Depth information is produced through an occlusion compensated disparity field and then a depth map is generated. On the contrary, color segmentation is accomplished by incorporating a modified version of the Multiresolution Recursive Shortest Spanning Tree segmentation algorithm (M-RSST). Next considering the first "Constrained Fusion of Color Segments" (CFCS) approach, a color segments map is created, by applying the M-RSST to one of the stereoscopic channels. In this case video objects are extracted by fusing color segments according to depth similarity criteria. The second method also utilizes the depth segments map. In particular an active contour is automatically initialized onto the boundary of each depth segment, which is usually different from a video object's boundary. Initialization is accomplished by a fitness function that considers different color areas and preserves the shapes of depth segments' boundaries. For acceleration purposes each point of the active contour is associated to an "attractive edge" point and a greedy approach is incorporated so that the active contour converges to its final position. Several experiments on real life stereoscopic sequences are performed and extensive comparisons in terms of speed and accuracy indicate the promising performance of both methods.	en
heal.publisher	Springer US	en
heal.journalName	Journal of Signal Processing Systems	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true