Podrobnosti studentského projektu

Seznam
Téma:Visual image retrieval and geolocalization
Katedra:Katedra kybernetiky
Vedoucí:Georgios Tolias, Ph.D.
Vypsáno jako:Diplomová práce, Bakalářská práce, Semestrální projekt
Popis:Given a large collection of geo-tagged images, e.g. street-view images, the goal is to build an image-based localization system which will predict the location at which outdoor images are taken. The task will be handled as image retrieval where a large collection of images needs to be indexed. Deep learning models will be used for the visual representation of images. Location estimation is provided with kernel density estimation according to the top-ranked geo-tagged images. The project focuses on improvements of the location estimation
Literatura:Vo Jacobs Hays, ICCV 2017, Revisiting IM2GPS in the Deep Learning Era
Radenovic Tolias Chum, PAMI 2019, Fine-tuning CNN Image Retrieval with No Human Annotation
Za obsah zodpovídá: Petr Pošík