Anisotropic-Scale Junction Detection and Matching for Indoor Images. Xue, N., Xia, G., Bai, X., Zhang, L., & Shen, W. IEEE Transactions on Image Processing, 27(1):78 - 91, 2018.
![Anisotropic-Scale Junction Detection and Matching for Indoor Images. [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper ![Anisotropic-Scale Junction Detection and Matching for Indoor Images. [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex
Paper Website abstract bibtex Junctions plays an important role in characterizing locally geometrical structures of images, and the detection of which is a longstanding but challenging task. Existing junction detectors usually focus on identifying the location and orien- tations of junction branches while ignoring their scales which however contain rich geometries of images. This paper presents a novel approach for junction detection and characterization, which especially exploits the locally anisotropic geometries of a junction and estimates its scales by relying on an a-contrario model. The output junctions are with anisotropic scales, saying that a scale parameter is associated with each branch of a junction, and are thus named as anisotropic-scale junctions (ASJs). We then apply the new detected ASJs for matching indoor images, where there are dramatic changes of viewpoints and the detected local visual features, e.g. key-points, are usually insufficient and lack distinctive ability. We propose to use the anisotropic geometries of our junctions to improve the matching precision of indoor images. The matching results on sets of indoor images demonstrate that our approach achieves the state-of-the- art performance on indoor image matching.
@article{
title = {Anisotropic-Scale Junction Detection and Matching for Indoor Images.},
type = {article},
year = {2018},
identifiers = {[object Object]},
keywords = {Junction detection and characterization,a-contrario model,an,geometric structures,indoor image matching,non-local description},
pages = {78 - 91},
volume = {27},
websites = {https://cherubicxn.github.io/publication/2017-tip-asj/,http://arxiv.org/abs/1703.05630},
id = {04b82c97-aa74-38fe-927b-04cf5c4db71d},
created = {2017-09-21T12:44:54.970Z},
file_attached = {true},
profile_id = {5a444090-7c14-3511-9ea2-b564829e81d3},
last_modified = {2018-08-21T01:08:56.353Z},
tags = {Low-level vision},
read = {true},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Xue2017},
folder_uuids = {9ecfc150-431e-46be-a324-476004cc24ec},
private_publication = {false},
abstract = {Junctions plays an important role in characterizing locally geometrical structures of images, and the detection of which is a longstanding but challenging task. Existing junction detectors usually focus on identifying the location and orien- tations of junction branches while ignoring their scales which however contain rich geometries of images. This paper presents a novel approach for junction detection and characterization, which especially exploits the locally anisotropic geometries of a junction and estimates its scales by relying on an a-contrario model. The output junctions are with anisotropic scales, saying that a scale parameter is associated with each branch of a junction, and are thus named as anisotropic-scale junctions (ASJs). We then apply the new detected ASJs for matching indoor images, where there are dramatic changes of viewpoints and the detected local visual features, e.g. key-points, are usually insufficient and lack distinctive ability. We propose to use the anisotropic geometries of our junctions to improve the matching precision of indoor images. The matching results on sets of indoor images demonstrate that our approach achieves the state-of-the- art performance on indoor image matching.},
bibtype = {article},
author = {Xue, Nan and Xia, Gui-Song and Bai, Xiang and Zhang, Liangpei and Shen, Weiming},
journal = {IEEE Transactions on Image Processing},
number = {1}
}Downloads: 0
{"_id":"qGH4gi3eAY5Z4GcWB","bibbaseid":"xue-xia-bai-zhang-shen-anisotropicscalejunctiondetectionandmatchingforindoorimages-2018","downloads":0,"creationDate":"2018-09-05T11:11:39.293Z","title":"Anisotropic-Scale Junction Detection and Matching for Indoor Images.","author_short":["Xue, N.","Xia, G.","Bai, X.","Zhang, L.","Shen, W."],"year":2018,"bibtype":"article","biburl":null,"bibdata":{"title":"Anisotropic-Scale Junction Detection and Matching for Indoor Images.","type":"article","year":"2018","identifiers":"[object Object]","keywords":"Junction detection and characterization,a-contrario model,an,geometric structures,indoor image matching,non-local description","pages":"78 - 91","volume":"27","websites":"https://cherubicxn.github.io/publication/2017-tip-asj/,http://arxiv.org/abs/1703.05630","id":"04b82c97-aa74-38fe-927b-04cf5c4db71d","created":"2017-09-21T12:44:54.970Z","file_attached":"true","profile_id":"5a444090-7c14-3511-9ea2-b564829e81d3","last_modified":"2018-08-21T01:08:56.353Z","tags":"Low-level vision","read":"true","starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Xue2017","folder_uuids":"9ecfc150-431e-46be-a324-476004cc24ec","private_publication":false,"abstract":"Junctions plays an important role in characterizing locally geometrical structures of images, and the detection of which is a longstanding but challenging task. Existing junction detectors usually focus on identifying the location and orien- tations of junction branches while ignoring their scales which however contain rich geometries of images. This paper presents a novel approach for junction detection and characterization, which especially exploits the locally anisotropic geometries of a junction and estimates its scales by relying on an a-contrario model. The output junctions are with anisotropic scales, saying that a scale parameter is associated with each branch of a junction, and are thus named as anisotropic-scale junctions (ASJs). We then apply the new detected ASJs for matching indoor images, where there are dramatic changes of viewpoints and the detected local visual features, e.g. key-points, are usually insufficient and lack distinctive ability. We propose to use the anisotropic geometries of our junctions to improve the matching precision of indoor images. The matching results on sets of indoor images demonstrate that our approach achieves the state-of-the- art performance on indoor image matching.","bibtype":"article","author":"Xue, Nan and Xia, Gui-Song and Bai, Xiang and Zhang, Liangpei and Shen, Weiming","journal":"IEEE Transactions on Image Processing","number":"1","bibtex":"@article{\n title = {Anisotropic-Scale Junction Detection and Matching for Indoor Images.},\n type = {article},\n year = {2018},\n identifiers = {[object Object]},\n keywords = {Junction detection and characterization,a-contrario model,an,geometric structures,indoor image matching,non-local description},\n pages = {78 - 91},\n volume = {27},\n websites = {https://cherubicxn.github.io/publication/2017-tip-asj/,http://arxiv.org/abs/1703.05630},\n id = {04b82c97-aa74-38fe-927b-04cf5c4db71d},\n created = {2017-09-21T12:44:54.970Z},\n file_attached = {true},\n profile_id = {5a444090-7c14-3511-9ea2-b564829e81d3},\n last_modified = {2018-08-21T01:08:56.353Z},\n tags = {Low-level vision},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Xue2017},\n folder_uuids = {9ecfc150-431e-46be-a324-476004cc24ec},\n private_publication = {false},\n abstract = {Junctions plays an important role in characterizing locally geometrical structures of images, and the detection of which is a longstanding but challenging task. Existing junction detectors usually focus on identifying the location and orien- tations of junction branches while ignoring their scales which however contain rich geometries of images. This paper presents a novel approach for junction detection and characterization, which especially exploits the locally anisotropic geometries of a junction and estimates its scales by relying on an a-contrario model. The output junctions are with anisotropic scales, saying that a scale parameter is associated with each branch of a junction, and are thus named as anisotropic-scale junctions (ASJs). We then apply the new detected ASJs for matching indoor images, where there are dramatic changes of viewpoints and the detected local visual features, e.g. key-points, are usually insufficient and lack distinctive ability. We propose to use the anisotropic geometries of our junctions to improve the matching precision of indoor images. The matching results on sets of indoor images demonstrate that our approach achieves the state-of-the- art performance on indoor image matching.},\n bibtype = {article},\n author = {Xue, Nan and Xia, Gui-Song and Bai, Xiang and Zhang, Liangpei and Shen, Weiming},\n journal = {IEEE Transactions on Image Processing},\n number = {1}\n}","author_short":["Xue, N.","Xia, G.","Bai, X.","Zhang, L.","Shen, W."],"urls":{"Paper":"https://bibbase.org/service/mendeley/5a444090-7c14-3511-9ea2-b564829e81d3/file/09165ba5-f817-61f5-30c2-2f6d2167bc47/2018-Anisotropic-Scale_Junction_Detection_and_Matching_for_Indoor_Images..pdf.pdf","Website":"https://cherubicxn.github.io/publication/2017-tip-asj/,http://arxiv.org/abs/1703.05630"},"bibbaseid":"xue-xia-bai-zhang-shen-anisotropicscalejunctiondetectionandmatchingforindoorimages-2018","role":"author","keyword":["Junction detection and characterization","a-contrario model","an","geometric structures","indoor image matching","non-local description"],"downloads":0},"search_terms":["anisotropic","scale","junction","detection","matching","indoor","images","xue","xia","bai","zhang","shen"],"keywords":["junction detection and characterization","a-contrario model","an","geometric structures","indoor image matching","non-local description"],"authorIDs":["5a8f777b5ed39fdb36000005"]}