Vous êtes ici : Accueil » Kiosque » Annonce


Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?


14 mars 2018

Robotic vision and machine learning applied to 3D reconstruction of plants

Catégorie : Post-doctorant

The detailed open position for September 2018 can be found at:




Context: Plants constitute complex structure in constant growth. Characterizing these structures in 3D is important for various biological applications such as precise pathogens quantification with compensation of anamorphosis effect, dynamic measurement of architecture despite occlusions, or multi scale characterization of canopy for external shoot analysis.

Topic: In this post-doctoral position we propose to tackle the 3D reconstruction of plants in various conditions of observation including indoor/outdoor, RGB-IR-X-ray, single plants or small cohorts based on UAV. This is addressed with the use of simulated plants and state of the art machine learning approaches.

Profil: The selected candidate will join an active and recognized research group in 3D plant imaging [1,2] and machine learning [3,4]. We offer a large panel of applications of robotics with strong potential for academic or industrial carrier. Advanced skills in robotics, image processing and computer sciences are necessary.

Supervision: David ROUSSEAU (Université d’Angers), Christian WOLF (INSA Lyon),

Place: INRA Angers, France in collaboration with INSA Lyon.

Salary: Standard Fellowship in the framework of an ERC-like project.


[1] M. Garbez, Y. Chene, E. Belin, M. Sigogne, J. Labatte, G. Hunault, R. Symoneaux, D. Rousseau, Galopin, G. "Predicting sensorial attribute scores of ornamental plants assessed in 3D through"; Computers and Electronics in Agriculture, 121, 331-346, 2016.

[2] Y. Chene, D. Rousseau, E. Belin M. Garbez, G. Galopin, F. Chapeau-Blondeau "Shape descriptors to characterize the shoots of entire plants from multiple side views of a motorized depth sensor"; Machine Vision and Applications, DOI: 10.1007/s00138-016-0762-x, 2016.

[3] Damien Fourure, Remi Emonet, Elisa Fromont, Damien Muselet, Alain Trémeau, Christian Wolf. Residual Conv-Deconv Grid Network for Semantic Segmentation. In British Machine Vision Conference (BMVC), 2017. 

[4] Damien Fourure, Remi Emonet, Elisa Fromont, Damien Muselet, Alain Trémeau, Christian Wolf. Semantic Segmentation via Multi-task, Multi-domain Learning In joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016).


For more information, please contact before 31 of may 2018 with motivation letter and resume: 

david.rousseau@univ-angers.fr and christian.wolf@cnrs-liris.fr


Dans cette rubrique

(c) GdR 720 ISIS - CNRS - 2011-2018.