PamiTC Job Board - Posting Details

Title: Ph.D. Position in computer vision and machine learning applied to AR in industrial environmentsPosted: October 11, 2016
Company/Institution: INRIA
Location: France
Department: INRIA Nancy Grand Est, Magrit group

Description: The Magrit team at Loria – Inria Nancy Grand-Est invites applicants for a postdoctoral position in computer vision and machine learning applied to Augmented Reality in industrial environments.

The successful candidate will work on a project to develop algorithms for location and object recognition in large-scale industrial environments (factories, vessels, …), with the aim to enrich the operator's field of view with digital information and media. The main issues concern the size of the environment, the nature of the objects (often non textured, highly specular, …), the presence of repeated patterns. Meanwhile, contextual information, 3D models of the objects and/or video sequences showing the objects under different view angles can be exploited.

Applicants should have knowledge in machine learning and computer vision. Good programming skills in Matlab is a plus.

The Magrit team is part of the Inria Nancy Grand-Est and the Université de Lorraine in France. The group has wide experience in diverse computer vision problems as 3D reconstruction, pose computation and scene recognition applied to augmented reality and medical imaging.

Research at Inria is organized in “project teams” which bring together researchers with complementary skills to focus on specific scientific projects. With this open, agile model, Inria is able to explore original approaches with its partners in industry and academia and provide an efficient response to the multidisciplinary and application challenges of the digital transformation.

1h30 away from Paris by TGV and at the heart of the Greater Region (Belgium, Luxemburg, Germany), the Lorraine region provides a pleasant setting along with a very rich cultural life.

The position is expected to start on 1st November 2016 and will have a duration of 1 year.

A few references related to the research topic of the proposal:

[1] David Crandall, Pedro Felzenszwalb and Daniel Huttenlocher. Object Recognition by Combining Appearance and Geometry. In Conference on Computer Vision and Pattern Recognition, CVPR, 2005.

[2] C. Desai, D. Ramanan and C. Fowlkes. Discriminative models for multi-class object layout. In IEEE 12th International Conference on Computer Vision, Kyoto, 2009, pp. 229-236.

[3] Aude Oliva and Antonio B. Torralba. Modeling the Shape of the Scene : A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision - IJCV, vol. 42, no. 3, pp. 145-175, 2001.

[4] Pierre Rolin, Marie-Odile Berger and Frederic Sur. Viewpoint simulation for camera pose estimation from an unstructured scene model. International Conference on Robotics and Automation, May 2015, Seattle, United States.

[5] Yukun Zhu, Jun Zhu and Rui Zhang. Contextual Object Detection. In IEEE Transactions on Multimedia, vol. 16, no. 6, pp. 1585-1596, Oct. 2014.

Application Instructions: For the internal selection of the candidate, all applicants are invited to submit detailed curriculum vitae, a summary of research interest and a cover letter at and, with subject: “[PhD AR] Candidate”. Candidates must also provide the name and email address of at least 1 referee.