Please use this identifier to cite or link to this item: https://idr.l1.nitk.ac.in/jspui/handle/123456789/10846
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMukherjee, S.-
dc.contributor.authorRam Mohana Reddy, Guddeti-
dc.date.accessioned2020-03-31T08:23:11Z-
dc.date.available2020-03-31T08:23:11Z-
dc.date.issued2014-
dc.identifier.citation3D Research, 2014, Vol.5, 3, pp.1-21en_US
dc.identifier.urihttp://idr.nitk.ac.in/jspui/handle/123456789/10846-
dc.description.abstractAbstract: We propose a hybrid method for stereo disparity estimation by combining block and region-based stereo matching approaches. It generates dense depth maps from disparity measurements of only 18 % image pixels (left or right). The methodology involves segmenting pixel lightness values using fast K-Means implementation, refining segment boundaries using morphological filtering and connected components analysis; then determining boundaries disparities using sum of absolute differences (SAD) cost function. Complete disparity maps are reconstructed from boundaries disparities. We consider an application of our method for depth-based selective blurring of non-interest regions of stereo images, using Gaussian blur to de-focus users non-interest regions. Experiments on Middlebury dataset demonstrate that our method outperforms traditional disparity estimation approaches using SAD and normalized cross correlation by up to 33.6 % and some recent methods by up to 6.1 %. Further, our method is highly parallelizable using CPU GPU framework based on Java Thread Pool and APARAPI with speed-up of 5.8 for 250 stereo video frames (4,096 2,304). 2014, 3D Research Center, Kwangwoon University and Springer-Verlag Berlin Heidelberg.en_US
dc.titleDepth-Based Selective Blurring in Stereo Images Using Accelerated Frameworken_US
dc.typeArticleen_US
Appears in Collections:1. Journal Articles

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.