Absolute location of a flying platform for image processing technology

Description de l'offre

Absolute location of a flying platform for image processing technology

Airbus Group Innovations Suresnes

Airbus Group Innovations

Airbus is a global leader in aeronautics, space and related services. In 2016, it generated revenues of € 67 billion and employed a workforce of around 134,000. Airbus offers the most comprehensive range of passenger airliners from 100 to more than 600 seats. Airbus is also a European leader providing tanker, combat, transport and mission aircraft, as well as Europe's number one space enterprise and the world's second largest space business. In helicopters, Airbus provides the most efficient civil and military rotorcraft solutions worldwide.

Our people work with passion and determination to make the world a more connected, safer and smarter place. Taking pride in our work, we draw on each other's expertise and experience to achieve excellence. Our diversity and teamwork culture propel us to accomplish the extraordinary - on the ground, in the sky and in space.

Description of the job

Airbus Group Innovations (Suresnes), is looking for an intern for a 6-month internship.

Within the Image Processing and Computer Vision research team of Airbus Group Innovations, you will develop and test computer vision techniques aimed at extracting a condensed 3D signature of a scene observed by a flying platform encoding its geometric (3D) and radiometric (textures) aspects. The objective is then to use the extracted signature as a scene recognition and absolute localization mean to provide any flying platform observing the modelled scene with a driftless vision based navigation capability, even in cases of GPS signal loss.

This internship will start on the 1st of February 2017 (subject to some flexibility).

Internships at Airbus

Profil recherché

Tasks & accountabilities

Your mission would include:

·  Performing state-of-the-art of 3D reconstruction and scene recognition algorithms and tools to be used during the offline learning phase (scene recognition techniques used for SLAM loop closures will be of particular interest),
·  Generating simulated video sequences from a 3D rendering engine to simulate the offline learning phase and the next missions with the corresponding ground truth,
·  Developing the offline scene modelling tool computing a compact 3D scene signature,
·  Developing a low frequency absolute localization algorithm leveraging the learnt 3D representation,
·  Integrating the absolute localization algorithm in an existing real-time SLAM (Simultaneous Localization and Mapping) framework,
·  Evaluating the developed algorithms and proposal for potential evolutions.

Required skills

You are in last year of engineering school, master or university (5th year) and your specialty is computer vision.

You have specific competencies in:

·  3D computer vision algorithms, especially multiple view geometry, bundle adjustment, vision based localization (SLAM), scene recognition…
·  software development (C++, knowledge of ROS framework would be appreciated)
·  optional: 3D and computer graphics software development (Unity framework for example)

You are a good team player and have excellent interpersonal skills.

English: intermediate level
French: fluent