Clara Fernández Labrador PhD defense
Clara, currently a Research Engineer and soon a Postdoctoral Researcher at the MTC, has recently defended her PhD on "Indoor Scene Understanding using Non-Conventional Cameras". Watch the presentation!
Abstract
Computer vision for visual scene understanding is highly desirable, so that machines can perform complex tasks by interacting with the real world, to assist or entertain humans. In this regard, we are interested in indoor environments, where humans spend nearly all their lifetime. This thesis specifically addresses the problems that arise during the quest of the hierarchical visual understanding of indoor scenes, and the required sensing mechanism for the same. On the side of sensing the wide 3D world, we propose to use non-conventional cameras, namely 360° imaging and 3D sensors. On the side of understanding, we aim at three key aspects: room layout estimation; object detection, localization and segmentation; and object category shape modelling, for which novel and efficient solutions are provided.