"26230" . . "Bratislava" . "4"^^ . . "Horv\u00E1th, Zsolt" . . "4"^^ . . . "Proceedings of 29th Spring conference on Computer Graphics" . "RIV/00216305:26230/13:PU106363!RIV14-TA0-26230___" . "Herout, Adam" . "2013-05-01+02:00"^^ . "Univerzita Komensk\u00E9ho v Bratislave" . "[A66047B01E0E]" . "68537" . "8"^^ . . . "Szentandr\u00E1si, Istv\u00E1n" . "Design and Detection of Local Geometric Features for Deformable Marker Fields" . . "Design and Detection of Local Geometric Features for Deformable Marker Fields" . . . "This paper sketched out the concept of the Honeycomb Marker Fields - a highly deformable and occlusion-tolerant marker field. We focused on the design of the Y-junctions, the visual image features which appear between the modules (cells) of the marker field. As the main contribution, we presented an algorithm for real-time and robust detection of the Y-junctions, and its experimental evaluation. The specialized Y-junction detection algorithm outperforms a general interest point detector (FAST) in the detection performance. The measurements thus lead to conclusion that for applications which can accept a marker field as a fiduciary pattern, the reliability and performance can be significantly improved. Based on the presented detector of Y-junctions and the preliminary HMF detector, we plan for the closest future to construct a robust and fast detector of the marker field and showcase it on selected applications. Thanks to the performance of the Y-junction detector, the algorithm is expected" . "Smolenice" . "P(TE01020155), P(TE01020415), Z(MSM0021630528)" . "Design and Detection of Local Geometric Features for Deformable Marker Fields"@en . . "Design and Detection of Local Geometric Features for Deformable Marker Fields"@en . "Horv\u00E1th, Zsolt" . . . . . "This paper sketched out the concept of the Honeycomb Marker Fields - a highly deformable and occlusion-tolerant marker field. We focused on the design of the Y-junctions, the visual image features which appear between the modules (cells) of the marker field. As the main contribution, we presented an algorithm for real-time and robust detection of the Y-junctions, and its experimental evaluation. The specialized Y-junction detection algorithm outperforms a general interest point detector (FAST) in the detection performance. The measurements thus lead to conclusion that for applications which can accept a marker field as a fiduciary pattern, the reliability and performance can be significantly improved. Based on the presented detector of Y-junctions and the preliminary HMF detector, we plan for the closest future to construct a robust and fast detector of the marker field and showcase it on selected applications. Thanks to the performance of the Y-junction detector, the algorithm is expected"@en . . "978-80-223-3377-1" . . . . "Szentandr\u00E1si, Istv\u00E1n" . . . "augmented reality, deformable marker field, local geometric features"@en . "RIV/00216305:26230/13:PU106363" . "Zachari\u00E1\u0161, Michal" .