Syndicate content

New PhD INPhINIT “la Caixa” fellowship on Geometric and Semantic Scene Analysis

Research Project

Visual and auditory information is everywhere. Moreover, the population is no longer a mere spectator nor a consumer of this type of information but has become a producer of digital contents that are frequently captured using mobile devices and shared over the Internet. At this point, audio-visual information, and more specifically video, has become a popular commodity in today's society.

Technology and science are progressing very rapidly and users expect from this advance to have at their disposal automatic tools that extract an analysis of the contents of the video not only at the geometric level but also at the semantic one. This project is aligned with this challenge.

The project aim is the automatic understanding of a 3D dynamic scene from a video sequence of it. In particular, what is the geometric and semantic configuration of the recorded scene. The goal is to semantically segment the dynamic scene into different objects and their trajectories, infer the depth ordering of the scene along time thus the occlusions and disocclusions and complete the occluded objects. This analysis will be enriched with different types of semantic information depending on the envisaged applications. The obtained results in geometric and semantic analysis will be applied to different scenarios such as: the automatization of video postproduction, e.g. the deletion or insertion of dynamic objects in video sequences in a way that the final result looks natural and integrated with the rest of the projected scene; sport analysis; and video augmentation. Other scenarios that may benefit from our contributions are autonomous navigation and advanced driver assistance systems.


Job position description

This research project will be supervised by Dr. Ballester and Dr. Haro, permanent faculty members of the Image Processing Group (IPG) at Universitat Pompeu Fabra, Barcelona. The research of the IPG lies at the intersection of image processing, computer vision, machine learning, applied mathematics, computer science and technology applications.

The PhD position is offered to a highly motivated researcher, to join our team. Prospective applicants should have a strong academic record with solid background in software development, and experience in computer vision, image processing or deep-learning techniques. Good programming skills are expected, preferably in C/C++ and Python. This research is related to several Spanish and European research projects.


More information in: