Nathan Piasco soutiendra sa thèse « Vision-based localization with discriminative features from heterogeneous visual data » le lundi 25 novembre 2019 à 14h amphi MP de l’IUT du Creusot.
Le jury sera composé de :
- Vincent Lepetit, Ecole des Ponts Paris Tech, Marne-la-Vallée (Rapporteur)
- Nicolas Thome, CEDRIC Lab, CNAM, Paris (Rapporteur)
- Josef Sivic, INRIA IMPACT, Paris & Prague (Examinateur)
- Torsten Sattler, Chalmers University of Technology, Göteborg (Examinateur)
et de ses encadrants Désiré Sidibé (IBISC, Université d’Evry Val d’Essonne), Valérie Gouet-Brunet (LABSTIG, IGN) & Cédric Demonceaux (ViBot ERL CNRS 6000, ImViA, UBFC)
Abstract :
Visual-based Localization (VBL) consists in retrieving the location of a visual image within a known space. VBL is involved in several present-day practical applications, such as indoor and outdoor navigation, 3D reconstruction, etc. The main challenge in VBL comes from the fact that the visual input to localize could have been taken at a different time than the reference database. Visual changes may occur on the observed environment during this period of time, especially for outdoor localization. Recent approaches use complementary information in order to address these visually challenging localization scenarios, like geometric information or semantic information. However geometric or semantic information are not always available or can be costly to obtain. In order to get free of any extra modalities used to solve challenging localization scenarios, we propose to use a modality transfer model capable of reproducing the underlying scene geometry from a monocular image.
At first, we cast the localization problem as a Content-based Image Retrieval (CBIR) problem and we train a CNN image descriptor with radiometry to dense geometry transfer as side training objective. Once trained, our system can be used on monocular images only to construct an expressive descriptor for localization in challenging conditions. Secondly, we introduce a new relocalization pipeline to improve the localization given by our initial localization step. In a same manner as our global image descriptor, the relocalization is aided by the geometric information learned during an offline stage. The extra geometric information is used to constrain the final pose estimation of the query. Through comprehensive experiments, we demonstrate the effectiveness of our proposals for both indoor and outdoor localization.