Section: Bilateral Contracts and Grants with Industry
Bilateral Contracts with Industry
Contract with Innopsys: Tissue microarrays (TMA) image analysis
Participants: Charles Kervrann.
Collaborators: Vincent Paveau and Cyril Cauchois (Innopys company).
A three-year contract has been established with Innopsys in 2013 to support the PhD thesis of Hoai-Nam Nguyen. The objective was to investigate and develop methods and algorithms dedicated to fluorescence images acquired by scanners and devices designed by the company. In this project, we focused on localization and segmentation of fluorescence tissue microarrays (TMA) cores in very large 2D images, de-arraying of digital images and correction of grid deformation adapted to devices, correction of scanning artifacts to improve image reconstruction and deconvolution of fluorescence TMA images. The algorithms are currently embedded into software and hardware products designed by Innopsys.
Contract (CIFRE) with Technicolor: Semantically meaningful motion descriptors for video understanding
Participants: Juan Manuel Perez Rua, Patrick Bouthemy.
Collaborators: Tomas Crivelli and Patrick Pérez (Technicolor).
A three-year contract has been established with Technicolor in January 2015 for a CIFRE grant supporting the PhD thesis of Juan Manuel Pérez Rúa. The purpose was to investigate new methods for extracting meaningful mid-level motion-related descriptors that may help for the semantic discovery of the content. First, we addressed the occlusion detection problem and proposed a novel approach where occlusion is formulated in terms of visual reconstruction. Contrary to the usual approaches, the proposed alternative does not critically depend on a pre-computed, dense displacement field, while being shown to be more effective. Second, we developed two hierarchical motion segmentation methods involving a compositional motion representation. The first one follows a frame-based labeling approach which amounts to minimizing a global energy function. The second one is trajectory-based and relies on tree-structured learning and sparse coding.
Contract with OBSYS: microscope set-up control and inverse problems in microscopy
Participants: Giovanni Petrazzuoli, Charles Kervrann.
Collaborators: Charles Gudeudry (OBSYS).
A two-year contract was established with OBSYS in 2016 for hiring an expert-engineer (12 months). The objective is to investigate and develop software for the control of a microscope set-up and the analysis of fluorescence images. Fast and robust algorithms have been especially developed to improve image reconstruction of 3D-TIRF microscope images. The algorithms will be embedded into platforms and devices designed by OBSYS. Giovanni Petrazzuoli has been hired in August 2017 on a full-time R&D engineer position in OBSYS (CDI). The collaboration with Inria will be pursued in 2018.