Estimating perception of scene layout properties from global image features. Ross, M. G. & Oliva, A. Journal of Vision, January, 2010. PMID: 21216762Paper doi abstract bibtex The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.
@article{ ross_estimating_2010,
title = {Estimating perception of scene layout properties from global image features},
volume = {10},
issn = {, 1534-7362},
url = {http://www.journalofvision.org/content/10/1/2},
doi = {10.1167/10.1.2},
abstract = {The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.},
language = {en},
number = {1},
urldate = {2013-06-13},
journal = {Journal of Vision},
author = {Ross, Michael G. and Oliva, Aude},
month = {January},
year = {2010},
note = {{PMID:} 21216762},
keywords = {computational modeling, depth, space and scene perception, structure of natural images}
}
Downloads: 0
{"_id":{"_str":"527b54da5e011a4c4b000841"},"__v":0,"authorIDs":[],"author_short":["Ross, M.<nbsp>G.","Oliva, A."],"bibbaseid":"ross-oliva-estimatingperceptionofscenelayoutpropertiesfromglobalimagefeatures-2010","bibdata":{"html":"<div class=\"bibbase_paper\"> \n\n\n<span class=\"bibbase_paper_titleauthoryear\">\n\t<span class=\"bibbase_paper_title\"><a name=\"ross_estimating_2010\"> </a>Estimating perception of scene layout properties from global image features.</span>\n\t<span class=\"bibbase_paper_author\">\nRoss, M. G.; and Oliva, A.</span>\n\t<!-- <span class=\"bibbase_paper_year\">2010</span>. -->\n</span>\n\n\n\n<i>Journal of Vision</i>,\n\n10(1).\n\nJanuary 2010.\n\n\nPMID: 21216762.\n\n<br class=\"bibbase_paper_content\"/>\n\n<span class=\"bibbase_paper_content\">\n \n \n <!-- <i -->\n <!-- onclick=\"javascript:log_download('ross-oliva-estimatingperceptionofscenelayoutpropertiesfromglobalimagefeatures-2010', 'http://www.journalofvision.org/content/10/1/2')\">DEBUG -->\n <!-- </i> -->\n\n <a href=\"http://www.journalofvision.org/content/10/1/2\"\n onclick=\"javascript:log_download('ross-oliva-estimatingperceptionofscenelayoutpropertiesfromglobalimagefeatures-2010', 'http://www.journalofvision.org/content/10/1/2')\">\n <img src=\"http://bibbase.org/img/filetypes/blank.png\"\n\t alt=\"Estimating perception of scene layout properties from global image features [.org/content/10/1/2]\" \n\t class=\"bibbase_icon\"\n\t style=\"width: 24px; height: 24px; border: 0px; vertical-align: text-top\" ><span class=\"bibbase_icon_text\">Paper</span></a> \n \n \n \n <a href=\"javascript:showBib('ross_estimating_2010')\"\n class=\"bibbase link\">\n <!-- <img src=\"http://bibbase.org/img/filetypes/bib.png\" -->\n\t<!-- alt=\"Estimating perception of scene layout properties from global image features [bib]\" -->\n\t<!-- class=\"bibbase_icon\" -->\n\t<!-- style=\"width: 24px; height: 24px; border: 0px; vertical-align: text-top\"><span class=\"bibbase_icon_text\">Bibtex</span> -->\n BibTeX\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n <a class=\"bibbase_abstract_link bibbase link\"\n href=\"javascript:showAbstract('ross_estimating_2010')\">\n Abstract\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n\n \n \n \n</span>\n\n<div class=\"well well-small bibbase\" id=\"bib_ross_estimating_2010\"\n style=\"display:none\">\n <pre>@article{ ross_estimating_2010,\n title = {Estimating perception of scene layout properties from global image features},\n volume = {10},\n issn = {, 1534-7362},\n url = {http://www.journalofvision.org/content/10/1/2},\n doi = {10.1167/10.1.2},\n abstract = {The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.},\n language = {en},\n number = {1},\n urldate = {2013-06-13},\n journal = {Journal of Vision},\n author = {Ross, Michael G. and Oliva, Aude},\n month = {January},\n year = {2010},\n note = {{PMID:} 21216762},\n keywords = {computational modeling, depth, space and scene perception, structure of natural images}\n}</pre>\n</div>\n\n\n<div class=\"well well-small bibbase\" id=\"abstract_ross_estimating_2010\"\n style=\"display:none\">\n The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.\n</div>\n\n\n</div>\n","downloads":0,"bibbaseid":"ross-oliva-estimatingperceptionofscenelayoutpropertiesfromglobalimagefeatures-2010","urls":{"Paper":"http://www.journalofvision.org/content/10/1/2"},"role":"author","year":"2010","volume":"10","urldate":"2013-06-13","url":"http://www.journalofvision.org/content/10/1/2","type":"article","title":"Estimating perception of scene layout properties from global image features","number":"1","note":"PMID: 21216762","month":"January","language":"en","keywords":"computational modeling, depth, space and scene perception, structure of natural images","key":"ross_estimating_2010","journal":"Journal of Vision","issn":", 1534-7362","id":"ross_estimating_2010","doi":"10.1167/10.1.2","bibtype":"article","bibtex":"@article{ ross_estimating_2010,\n title = {Estimating perception of scene layout properties from global image features},\n volume = {10},\n issn = {, 1534-7362},\n url = {http://www.journalofvision.org/content/10/1/2},\n doi = {10.1167/10.1.2},\n abstract = {The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas.},\n language = {en},\n number = {1},\n urldate = {2013-06-13},\n journal = {Journal of Vision},\n author = {Ross, Michael G. and Oliva, Aude},\n month = {January},\n year = {2010},\n note = {{PMID:} 21216762},\n keywords = {computational modeling, depth, space and scene perception, structure of natural images}\n}","author_short":["Ross, M.<nbsp>G.","Oliva, A."],"author":["Ross, Michael G.","Oliva, Aude"],"abstract":"The relationship between image features and scene structure is central to the study of human visual perception and computer vision, but many of the specifics of real-world layout perception remain unknown. We do not know which image features are relevant to perceiving layout properties, or whether those features provide the same information for every type of image. Furthermore, we do not know the spatial resolutions required for perceiving different properties. This paper describes an experiment and a computational model that provides new insights on these issues. Humans perceive the global spatial layout properties such as dominant depth, openness, and perspective, from a single image. This work describes an algorithm that reliably predicts human layout judgments. This model's predictions are general, not specific to the observers it trained on. Analysis reveals that the optimal spatial resolutions for determining layout vary with the content of the space and the property being estimated. Openness is best estimated at high resolution, depth is best estimated at medium resolution, and perspective is best estimated at low resolution. Given the reliability and simplicity of estimating the global layout of real-world environments, this model could help resolve perceptual ambiguities encountered by more detailed scene reconstruction schemas."},"bibtype":"article","biburl":"http://bibbase.org/zotero/nbusch","downloads":0,"search_terms":["estimating","perception","scene","layout","properties","global","image","features","ross","oliva"],"title":"Estimating perception of scene layout properties from global image features","year":2010,"dataSources":["9Wz8i3YBFkeJte2aR"]}