Kernel integral images: A framework for fast non-uniform filtering. Hussein, M., Porikli, F., & Davis, L. In 2008 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8, 2008. doi abstract bibtex Integral images are commonly used in computer vision and computer graphics applications. Evaluation of box filters via integral images can be performed in constant time, regardless of the filter size. Although Heckbert (1986) extended the integral image approach for more complex filters, its usage has been very limited, in practice. In this paper, we present an extension to integral images that allows for application of a wide class of non-uniform filters. Our approach is superior to Heckbertpsilas in terms of precision requirements and suitability for parallelization. We explain the theoretical basis of the approach and instantiate two concrete examples: filtering with bilinear interpolation, and filtering with approximated Gaussian weighting. Our experiments show the significant speedups we achieve, and the higher accuracy of our approach compared to Heckbertpsilas.
@inproceedings{hussein_kernel_2008,
title = {Kernel integral images: A framework for fast non-uniform filtering},
rights = {All rights reserved},
doi = {10.1109/CVPR.2008.4587641},
shorttitle = {Kernel integral images},
abstract = {Integral images are commonly used in computer vision and computer graphics applications. Evaluation of box filters via integral images can be performed in constant time, regardless of the filter size. Although Heckbert (1986) extended the integral image approach for more complex filters, its usage has been very limited, in practice. In this paper, we present an extension to integral images that allows for application of a wide class of non-uniform filters. Our approach is superior to Heckbertpsilas in terms of precision requirements and suitability for parallelization. We explain the theoretical basis of the approach and instantiate two concrete examples: filtering with bilinear interpolation, and filtering with approximated Gaussian weighting. Our experiments show the significant speedups we achieve, and the higher accuracy of our approach compared to Heckbertpsilas.},
eventtitle = {2008 {IEEE} Conference on Computer Vision and Pattern Recognition},
pages = {1--8},
booktitle = {2008 {IEEE} Conference on Computer Vision and Pattern Recognition},
author = {Hussein, M. and Porikli, F. and Davis, L.},
date = {2008-06},
year = {2008},
keywords = {Application software, approximated Gaussian weighting filtering, approximation theory, bilinear interpolation, computer graphics, Computer graphics, Computer science, computer vision, Computer vision, fast nonuniform filtering, Filtering, filtering theory, Filters, Histograms, image processing, integral equations, interpolation, Interpolation, Kernel, kernel integral images, Target tracking},
file = {IEEE Xplore Abstract Record:C\:\\Users\\Mohamed Hussein\\Zotero\\storage\\U77RQ4IY\\4587641.html:text/html}
}
Downloads: 0
{"_id":"LsDKAJY9AgB5p3Sqb","bibbaseid":"hussein-porikli-davis-kernelintegralimagesaframeworkforfastnonuniformfiltering-2008","author_short":["Hussein, M.","Porikli, F.","Davis, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Kernel integral images: A framework for fast non-uniform filtering","rights":"All rights reserved","doi":"10.1109/CVPR.2008.4587641","shorttitle":"Kernel integral images","abstract":"Integral images are commonly used in computer vision and computer graphics applications. Evaluation of box filters via integral images can be performed in constant time, regardless of the filter size. Although Heckbert (1986) extended the integral image approach for more complex filters, its usage has been very limited, in practice. In this paper, we present an extension to integral images that allows for application of a wide class of non-uniform filters. Our approach is superior to Heckbertpsilas in terms of precision requirements and suitability for parallelization. We explain the theoretical basis of the approach and instantiate two concrete examples: filtering with bilinear interpolation, and filtering with approximated Gaussian weighting. Our experiments show the significant speedups we achieve, and the higher accuracy of our approach compared to Heckbertpsilas.","eventtitle":"2008 IEEE Conference on Computer Vision and Pattern Recognition","pages":"1–8","booktitle":"2008 IEEE Conference on Computer Vision and Pattern Recognition","author":[{"propositions":[],"lastnames":["Hussein"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Porikli"],"firstnames":["F."],"suffixes":[]},{"propositions":[],"lastnames":["Davis"],"firstnames":["L."],"suffixes":[]}],"date":"2008-06","year":"2008","keywords":"Application software, approximated Gaussian weighting filtering, approximation theory, bilinear interpolation, computer graphics, Computer graphics, Computer science, computer vision, Computer vision, fast nonuniform filtering, Filtering, filtering theory, Filters, Histograms, image processing, integral equations, interpolation, Interpolation, Kernel, kernel integral images, Target tracking","file":"IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Mohamed Hussein\\\\Zotero\\\\storage\\\\U77RQ4IY\\\\4587641.html:text/html","bibtex":"@inproceedings{hussein_kernel_2008,\n\ttitle = {Kernel integral images: A framework for fast non-uniform filtering},\n\trights = {All rights reserved},\n\tdoi = {10.1109/CVPR.2008.4587641},\n\tshorttitle = {Kernel integral images},\n\tabstract = {Integral images are commonly used in computer vision and computer graphics applications. Evaluation of box filters via integral images can be performed in constant time, regardless of the filter size. Although Heckbert (1986) extended the integral image approach for more complex filters, its usage has been very limited, in practice. In this paper, we present an extension to integral images that allows for application of a wide class of non-uniform filters. Our approach is superior to Heckbertpsilas in terms of precision requirements and suitability for parallelization. We explain the theoretical basis of the approach and instantiate two concrete examples: filtering with bilinear interpolation, and filtering with approximated Gaussian weighting. Our experiments show the significant speedups we achieve, and the higher accuracy of our approach compared to Heckbertpsilas.},\n\teventtitle = {2008 {IEEE} Conference on Computer Vision and Pattern Recognition},\n\tpages = {1--8},\n\tbooktitle = {2008 {IEEE} Conference on Computer Vision and Pattern Recognition},\n\tauthor = {Hussein, M. and Porikli, F. and Davis, L.},\n\tdate = {2008-06},\n\tyear = {2008},\n\tkeywords = {Application software, approximated Gaussian weighting filtering, approximation theory, bilinear interpolation, computer graphics, Computer graphics, Computer science, computer vision, Computer vision, fast nonuniform filtering, Filtering, filtering theory, Filters, Histograms, image processing, integral equations, interpolation, Interpolation, Kernel, kernel integral images, Target tracking},\n\tfile = {IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Mohamed Hussein\\\\Zotero\\\\storage\\\\U77RQ4IY\\\\4587641.html:text/html}\n}\n\n","author_short":["Hussein, M.","Porikli, F.","Davis, L."],"bibbaseid":"hussein-porikli-davis-kernelintegralimagesaframeworkforfastnonuniformfiltering-2008","role":"author","urls":{},"keyword":["Application software","approximated Gaussian weighting filtering","approximation theory","bilinear interpolation","computer graphics","Computer graphics","Computer science","computer vision","Computer vision","fast nonuniform filtering","Filtering","filtering theory","Filters","Histograms","image processing","integral equations","interpolation","Interpolation","Kernel","kernel integral images","Target tracking"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/2bJzYjCLapWTtM86s/mehussein-2023.bib","dataSources":["kYvtZ54PgkXqjbteW","mhdykGczo2jDicE3X","havAjNnaG4BxhYWyb"],"keywords":["application software","approximated gaussian weighting filtering","approximation theory","bilinear interpolation","computer graphics","computer graphics","computer science","computer vision","computer vision","fast nonuniform filtering","filtering","filtering theory","filters","histograms","image processing","integral equations","interpolation","interpolation","kernel","kernel integral images","target tracking"],"search_terms":["kernel","integral","images","framework","fast","non","uniform","filtering","hussein","porikli","davis"],"title":"Kernel integral images: A framework for fast non-uniform filtering","year":2008}