An interplay of phenomenology, psychology and geometrical modeling in terms of visual perception
Naturalizing phenomenology refers to putting the study of mind on con- crete foundations leading to a better understanding of the cognitive dimension of mind via the scientific methodology based on conjecture and refutation, trial and error. In a specific case of visual perception, a modeling task as a part of naturalizing phenomenology can be achieved starting from Husserlian phe- nomenology under the restriction of Gestalt psychology. We will see an intuitive explanation of such modeling approaches starting from their phenomenological and psychological principles by using the model of Citti and Sarti  as an example framework of perceptual models of vision.
 G. Citti and A. Sarti, A cortical based model of perceptual completion in the roto-translation space, Journal of Mathematical Imaging and Vision, 24, (3), pp. 307-326, 2006.
Nicolas Girard (Titane)
Regularized building segmentation by frame field learning
We add a frame field output to an image segmentation neural network to improve segmentation quality and provide additional geometric structure information for a subsequent polygonization step. A frame field allows to characterize two directions at every point of the image. We train a network to align the frame field to the tangent of ground truth contours. In addition to increasing the performance of the segmentation by leveraging the multi-task learning effect, our method produces a more regular segmentation and is more robust due to the additional learning signal.
An introduction to aerial and satellite image processing
Large quantities of aerial and satellite images are captured everyday. These images have varying properties and usages, but they must often be processed into useful products before serving any purpose. What are these properties, usages, and products? We will talk about the different kinds of sensors found on UAVs and satellites, and explain what Orthoimage, Digital Terrain Models, and Urban 3D Models are, and how they are created. Finally, we will explore new processing techniques, both onboard and on the ground, that have recently appeared with the rise of Deep Learning.
The outreach of computer science culture aims for:
- Contributing to citizens' understanding of computer sciences in society
- Raising the awareness of citizens on the scientific, environmental, ethical and socioeconomic stakes related to computer sciences
- Cultivating scientific vocations in children and teenagers
- Involve a greater number of citizens in computer science evolution
After an introduction to Inria mediation, we will show how to introduce in an entertaining manner fundamental concepts in informatics and mathematics(algorithms and graphs).
We will also allude to presenting current research in computer sciences.
This presentation will be interactive and involve the audience.