Filters








370 Hits in 4.7 sec

Perceptual Grouping Based on Iterative Multi-scale Tensor Voting [chapter]

Leandro Loss, George Bebis, Mircea Nicolescu, Alexei Skourikhine
2006 Lecture Notes in Computer Science  
We propose a new approach for perceptual grouping of oriented segments in highly cluttered images based on tensor voting.  ...  An iterative scheme has been devised which removes noise segments in a conservative way using multi-scale analysis and re-voting.  ...  In this paper, we propose a new approach for perceptual grouping of oriented segments in highly cluttered images based on tensor voting.  ... 
doi:10.1007/11919629_87 fatcat:wgrdhviiangbvkwfa4tgmfa7na

An iterative multi-scale tensor voting scheme for perceptual grouping of natural shapes in cluttered backgrounds

Leandro Loss, George Bebis, Mircea Nicolescu, Alexei Skurikhin
2009 Computer Vision and Image Understanding  
In this context, we have developed a general and powerful method based on an iterative, multiscale tensor voting approach.  ...  The key idea of our approach is removing background segments conservatively on an iterative fashion, using multi-scale analysis, and re-voting on the retained segments.  ...  In this paper, we propose a new approach for perceptual grouping of oriented segments in highly cluttered images based on tensor voting.  ... 
doi:10.1016/j.cviu.2008.07.011 fatcat:e2tfk7pqrvfbfnpu6dihupotha

Tunable tensor voting improves grouping of membrane-bound macromolecules

L.A. Loss, G. Bebis, B. Parvin
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
The novelty of our method lies on the idea of iteratively tuning the tensor voting fields, which allows the concentration of the votes only over areas of interest.  ...  Our work builds upon the tensor voting and the iterative voting frameworks to propose an efficient method to detect and refine perceptually interesting curvilinear structures in images.  ...  [6] extended this tensor voting framework to accommodate iterative saliency thresholding and multi-scale analysis. Parvin et al.  ... 
doi:10.1109/cvpr.2009.5204047 fatcat:cuxbolrpknctbjkg6zzyoezary

Tunable tensor voting improves grouping of membrane-bound macromolecules

Leandro A. Loss, George Bebis, Bahram Parvin
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
The novelty of our method lies on the idea of iteratively tuning the tensor voting fields, which allows the concentration of the votes only over areas of interest.  ...  Our work builds upon the tensor voting and the iterative voting frameworks to propose an efficient method to detect and refine perceptually interesting curvilinear structures in images.  ...  [6] extended this tensor voting framework to accommodate iterative saliency thresholding and multi-scale analysis. Parvin et al.  ... 
doi:10.1109/cvprw.2009.5204047 dblp:conf/cvpr/LossBP09 fatcat:gf7p7jmesjhn7eofjkqdrpha4y

Investigating how and when perceptual organization cues improve boundary detection in natural images

Leandro A. Loss, George Bebis, Mircea Nicolescu, Alexei Skurikhin
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In this context, we investigate the idea of integrating with segmentation the Iterative Multi-Scale Tensor Voting (IMSTV), a variant of Tensor Voting (TV) that performs perceptual grouping by analyzing  ...  information at multiple-scales and removing background clutter in an iterative fashion, preserving salient, organized structures.  ...  a.2, b.2) GM and BG PB maps, (a.3, b.3) magnitudes encoded as tensors in IMSTV, (a.4, b.4) tensors after iterative voting using IMSTV.  ... 
doi:10.1109/cvprw.2008.4562974 dblp:conf/cvpr/LossBNS08 fatcat:skfiwfyhobfk7jlipzdf6e7zia

An Automatic Framework for Figure-Ground Segmentation in Cluttered Backgrounds

L. Loss, G. Bebis, M. Nicolescu, A. N. Skurikhin
2007 Procedings of the British Machine Vision Conference 2007  
Our work employs perceptual grouping concepts to characterize image segments by means of their saliency, which is computed via tensor voting.  ...  The main innovation of our work is a case-based thresholding scheme which iteratively eliminates edge segments with low-saliency in multiple scales, preserving those that are more likely to belong to foreground  ...  Conclusions and Future Work We have proposed an automatic framework for figure-ground segmentation based on an iterative, multi-scale tensor voting scheme.  ... 
doi:10.5244/c.21.32 dblp:conf/bmvc/LossBNS07 fatcat:k2xwrmvsfncivjyag23ux5t5bq

A Vision-Based System For Automatic Detection and Extraction Of Road Networks

Charalambos Poullis, Suya You, Ulrich Neumann
2008 2008 IEEE Workshop on Applications of Computer Vision  
Uniquely, the proposed system is an integrated solution that merges the power of perceptual grouping theory(gabor filtering, tensor voting) and optimized segmentation techniques(global optimization using  ...  Secondly, a novel orientation-based segmentation is presented which incorporates the classification of the perceptual grouping, and results in segmentations with better defined boundaries and continuous  ...  Tensor Voting Tensor voting is a perceptual grouping and segmentation framework introduced by [7] . A key data representation based on tensor calculus is used to encode the data.  ... 
doi:10.1109/wacv.2008.4543996 dblp:conf/wacv/PoullisYN08 fatcat:zg33nqmirjhevbq5e46pusuuwm

Coupled segmentation of nuclear and membrane-bound macromolecules through voting and multiphase level set

Hang Chang, Quan Wen, Bahram Parvin
2015 Pattern Recognition  
At the optical scale, one group of membrane proteins expresses themselves as linear structures along the cell surface boundaries, while others are sequestered; and this paper targets the former group.  ...  To tackle these problems, we introduce a three-step process to (i) regularize the membrane signal through iterative tangential voting, (ii) constrain the location of surface proteins by nuclear features  ...  While [23] introduced the concept of iterative tensor voting for simultaneous denoising and perceptual grouping of membrane-bound signals.  ... 
doi:10.1016/j.patcog.2014.10.005 pmid:25530633 pmcid:PMC4269261 fatcat:dkaprkvcyza4nmfsvn6sz2jne4

Steering second-order tensor voting by vote clustering

Daniel Jorgens, Orjan Smedby, Rodrigo Moreno
2016 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)  
We propose an extension of tensor voting in which information from voxels with a single fibre is used to infer orientation distributions in multi fibre voxels.  ...  The method is able to resolve multiple fibre orientations by clustering tensor votes instead of adding them up.  ...  Based on this observation, we propose to group the received votes into clusters of similar orientation.  ... 
doi:10.1109/isbi.2016.7493492 dblp:conf/isbi/JorgensSM16 fatcat:s5huwhlmhvhwdjwot56j7ckhre

Iterative Voting for Inference of Structural Saliency and Characterization of Subcellular Events

Bahram Parvin, Qing Yang, Ju Han, Hang Chang, Bjorn Rydberg, Mary Helen Barcellos-Hoff
2007 IEEE Transactions on Image Processing  
Iterative voting has been implemented in both 2-D and 3-D for multi image analysis.  ...  The technique can cluster and group nonconvex perceptual circular symmetries along the radial line of an object's shape.  ...  This method shares several attributes with tensor-based voting [9] ; however, it differs in that it is iterative and scalar.  ... 
doi:10.1109/tip.2007.891154 pmid:17357723 fatcat:5r6cu5gtcjdw7f6phbl53b2omm

Using Mobile LiDAR Data for Rapidly Updating Road Markings

Haiyan Guan, Jonathan Li, Yongtao Yu, Zheng Ji, Cheng Wang
2015 IEEE transactions on intelligent transportation systems (Print)  
Weighted neighboring difference histogram (WNDH)-based dynamic thresholding and multiscale tensor voting (MSTV) are proposed to segment and extract road markings from the noisy corrupted GRF images.  ...  Index Terms-Mobile light detection and ranging (LiDAR), point cloud, road marking, tensor voting, thresholding.  ...  Tensor voting (TV) was first introduced in computer vision for perceptual grouping purposes [31] .  ... 
doi:10.1109/tits.2015.2409192 fatcat:qkvjd42tgndibgytwsdlmoi27i

Delineation and geometric modeling of road networks

Charalambos Poullis, Suya You
2010 ISPRS journal of photogrammetry and remote sensing (Print)  
Uniquely, the proposed system is an integrated solution that merges the power of perceptual grouping theory (Gabor filtering, tensor voting) and optimized segmentation techniques (global optimization using  ...  Secondly, a novel orientation-based segmentation is presented which incorporates the classification of the perceptual grouping, and results in segmentations with better defined boundaries and continuous  ...  Firstly, we leveraged the local precision and the multi-scale, multi-orientation capability of Gabor filters, combined with the global context of the tensor voting for the extraction and accurate classification  ... 
doi:10.1016/j.isprsjprs.2009.10.004 fatcat:m2bnvceptrhobizt63erj7rcqm

Probabilistic tensor voting for robust perceptual grouping

Dian Gong, Gerard Medioni
2012 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
In the new framework, the representation consists of a 2nd order symmetric tensor, a polarity vector, and a new type 2 polarity vector orthogonal to the first one.  ...  In this paper, we propose probabilistic Tensor Voting, a Bayesian extension of standard tensor voting, taking into consideration both probabilistic and geometric meaning.  ...  Tensor Voting Review Tensor Voting was originally developed in 2D for perceptual grouping, and later extended to 3D and N D space.  ... 
doi:10.1109/cvprw.2012.6238926 dblp:conf/cvpr/GongM12 fatcat:nci67lf2efbrpllgs4my6uvfxi

IMPACT OF GAP FILLING ON QUALITY OF ROAD NETWORKS

M. Maboudi, J. Amini, M. Gerke
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In this paper, using two different VHR satellite datasets and a gap-filling approach which is based on tensor voting, we show that utilizing an effective road gap filling can result in a quite tangible  ...  Many small segments appear on the road surface in VHR images.  ...  Employing mathematical morphology, perceptual grouping, active contours, and multi-scale processing followed by topology transmission (Zeng et al., 2015) are the most frequent techniques which are used  ... 
doi:10.5194/isprs-archives-xlii-4-w18-683-2019 fatcat:eqcmy6rimngafmrf6d6au6nwoq

Analysis and Interpretation of Multiple Motions Through Surface Saliency [chapter]

Mircea Nicolescu, Changki Min, Gérard Medioni
2006 Lecture Notes in Computer Science  
We propose a novel approach that decouples the above operations, allowing for separate handling of matching, outlier rejection, grouping and 3-D interpretation.  ...  Our methodology for extracting motion layers is based on a layered 4-D representation of data, and a voting scheme for token communication.  ...  The method is also computationally robust, being non-iterative, and does not depend on critical thresholds, the only free parameter being the scale of analysis.  ... 
doi:10.1007/11676959_10 fatcat:6ixw6gdx65ampjhqurfy6ue73u
« Previous Showing results 1 — 15 out of 370 results