Ecole Polytechnique Federale De Lausanne

Epfl Ecole Polytechnique Fédérale De Lausanne

Sabine Süsstrunk

Adrien Birbaumer

Martinus Bosch

Jason Racine

Sami Arpa

Yue Lu

Roger David Hersch

Gabriel Autès

Clément Fredembach

A method of classifying a media includes receiving a media file and extracting therefrom first and second data streams including first and second media content, respectively, the media content being associated with the media item. First and second feature vectors describing the first and second media content, respectively, are generated. At least a first single feature vector representing the first sequence of first feature vectors and the second sequence of second feature vectors is generated, or at least a first single feature vector representing at least the first sequence of first feature vectors is generated. A second feature vector representing at least the second sequence of second feature vectors is generated. A probability vector from the first single feature vector, or from the first and second single feature vectors is generated. A user profile suitability class is assigned to the media item based on the probability vector.

Dynamic media content categorization method

A method of displaying an image on a see-through display comprises: obtaining a first electro-magnetic radiation matrix of radiation intensity values of an object; dividing the first matrix into a second matrix representing a first subset of the radiation intensity values, and a third matrix representing a second subset of the radiation intensity values; generating a first grayscale image with an enhanced contrast representing the first subset of the radiation intensity values from the second matrix; colouring the first grayscale image with a first colourmap to obtain a first colour image; generating a second grayscale image representing the second subset of the radiation intensity values; colouring the second grayscale image with a second colourmap to obtain a second colour image; combining the first colour image and the second colour image; and displaying the combined colour image on the see-through display.

Method of displaying an image on a see-through display

A method of displaying an image on a see-through display comprises: obtaining a first electro-magnetic radiation matrix of radiation intensity values of an object; dividing the first matrix into a second matrix representing a first subset of the radiation intensity values, and a third matrix representing a second subset of the radiation intensity values; generating a first histogram for the second matrix; equalizing the first histogram to obtain an equalised second histogram; generating a first grayscale image representing the first subset of the radiation intensity values; colouring the first grayscale image with a first colourmap to obtain a first colour image; generating a second grayscale image representing the second subset of the radiation intensity values; colouring the second grayscale image with a second colourmap to obtain a second colour image; combining the first colour image and the second colour image; and displaying the combined colour image on the see-through display.

We disclose a method for synthesizing by computer an artwork where 2D and 3D contents are integrated within a same composition. Such an artwork creates plausible effects for the viewers by showing a different relationship between 2D and 3D at each viewing angle. Methods are proposed for ensuring the continuity between the 2D and the 3D parts in terms of mesh geometry and reflected colors. The user selects from a given scene a region of interest (ROI) to be reproduced in 3D. A flat rendering grid is created that matches the topology and tesselation of the ROI. The ROI is attached to the rendering grid. To enhance the continuity between the 2D and the 3D parts of a scene object, the 2D part of the object can be represented as bas-relief. Designers can create 2D-3D sculpture paintings for decoration, exhibitions, and homes.

2D-3D sculpture paintings

The present invention aims to capture two images simultaneously in the visible part of the spectrum and a NIR image. This is achieved through a camera for simultaneously capturing a visible and near-infrared image by at least a sensor producing sensor response data and having at least one color filter array (CFA) comprising at least four different filters, said color filter array having visible and near-infrared light filters, and said camera comprising means to obtain a visible image while using the sensor response data from the visible part of the spectrum and a NIR image using the sensor response data from the near-infrared part of the spectrum.

Growing community of inventors

Lausanne, Switzerland

Sabine Süsstrunk