"Okutomi, M." . "Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard fo restablishing correspondences using multi-view geometry. Even more importantly, they violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they fo rm an important distinguishing feature for many places. We describe a representation of repeat ed structures suitable for scalable retrieval. It is based on robust detection of repeated ima ge structures and a simple modification of weights in the bag-of-visual-word model. Place reco gnition results are shown on datasets of street-level imagery from Pittsburgh and San Francisc o demonstrating significant gains in recognition performance compared to the standard bag-of-v isual-words baseline and more recently proposed burstiness weighting." . "CVPR: 2013 IEEE Computer Society Conference on Computer Vision and Pattern Recognition" . "1"^^ . "2013-06-25+02:00"^^ . "10.1109/CVPR.2013.119" . "4"^^ . . . "[879BAF56C91C]" . "RIV/68407700:21230/13:00212578!RIV14-MSM-21230___" . . "Visual Place Recognition with Repetitive Structures"@en . "image based localization; repetitive structures; image retrieval; bag of visual wirds"@en . "IEEE Computer Society Press" . . . "Visual Place Recognition with Repetitive Structures" . "114194" . . "8"^^ . . "R" . "Los Alamitos" . . "OR" . "Visual Place Recognition with Repetitive Structures"@en . "Torii, Akihiko" . "21230" . . . . "1063-6919" . "Visual Place Recognition with Repetitive Structures" . "RIV/68407700:21230/13:00212578" . . . . . . "Pajdla, Tom\u00E1\u0161" . "\u0160ivic, J." . "Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard fo restablishing correspondences using multi-view geometry. Even more importantly, they violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they fo rm an important distinguishing feature for many places. We describe a representation of repeat ed structures suitable for scalable retrieval. It is based on robust detection of repeated ima ge structures and a simple modification of weights in the bag-of-visual-word model. Place reco gnition results are shown on datasets of street-level imagery from Pittsburgh and San Francisc o demonstrating significant gains in recognition performance compared to the standard bag-of-v isual-words baseline and more recently proposed burstiness weighting."@en . .