Softkinetic Software

Mintt

Xavier Baele

Julien Thollot

Javier Martinez Gonzalez

Gilles Pinault

Kevin Simons

Laurent Guigues

David Dal Zot

Jeremie Roy

Juan Carlos Tocino Diaz

Laurent Desmecht

Jérémie Roy

Juan Carlos Tocinos Diaz

The invention relates to a computer-implemented segmentation method of an image comprising a segmentation by watershed applied to an evaluation of a curvature at pixels of the image.

Method for segmenting an image

Described herein is a method of calibrating a three-dimensional imaging system. During calibration, a position and an orientation of the three-dimensional imaging system is determined with respect to a first parameter comprising a real world vertical direction (V) and to a second parameter comprising an origin of a three-dimensional scene captured by the imaging system. The first and second parameters are used to derive a calibration matrix (M) which is used to convert measurements from a virtual coordinate system (M) of the three-dimensional imaging system into a real coordinate system (M) related to the real world. The calibration matrix (M) is used to rectify measurements prior to signal processing. An inverse calibration matrix (M) is also determined. Continuous monitoring and adjustment of the setup of the three-dimensional imaging system is carried out and the calibration matrix (M) and its inverse (M) are adjusted accordingly.

Automatic scene calibration

The present invention relates to a method for stabilizing a series of measurements of a physical variable captured by a digital sensor. This method comprises the steps of: capturing at least a first measurement, a second measurement, and a third measurement of said physical variable and storing each measurement in a digital memory. The first and second measurements are compared and, if a difference between the first measurement and the second measurement is below a predetermined threshold, the second measurement is replaced in the memory by a corrected second measurement where the difference with respect to said first measurement has been reduced using a first filtering strength. The corrected second measurement and the third measurement are compared and, if a difference between the filtered value of the corrected second measurement and said third measurement is also below the threshold, said the third measurement is replaced by a corrected third measurement where a difference with respect to said corrected second measurement has been reduced using a second filtering strength that is lower than the first filtering strength. This method has the advantage of filtering noise while still allowing slow but relevant variations in the series of measurements.

Stabilisation method and computer system

Described herein is a method for recognizing a human head in a source image. The method comprises detecting a contour of at least part of a human body in the source image, calculating a depth of the human body in the source image. From the source image, a major radius size and a minor radius size of an ellipse corresponding to a human head at the depth is calculated, and, for at least several of a set of pixels of the detected contour, generating in an accumulator array at least one segment of an ellipse centered on the position of the contour pixel and having the major and minor radius sizes. Positions of local intensity maxima in the accumulator array are selected as corresponding to positions of the human head candidates in the source image.

Head recognition from depth image

Described herein is a user interface that provides contextual feedback, controls and interface elements on a display screen of an interactive three-dimensional imaging system. A user interacts with the interface to provide control signals in accordance with those recognized by the system to a makes use of at least one POI in a three-dimensional scene that is imaged by the imaging system to provide control signals for the user interface. Control signals are provided by means of gestures which are analyzed in real-time by gesture recognition processes that analyze statistical and geometrical properties of POI motion and trajectories.

Natural gesture based user interface methods and systems

The present invention relates to a method for tracking at least one object in a sequence of frames, each frame comprising a pixel array, wherein a depth value is associated to each pixel. The method comprises grouping at least some of said pixels of each frame into several regions, grouping said regions into clusters (B, . . . , B) of interconnected regions; and determining that a cluster (B, . . . , B) which is adjacent to another cluster (B) in a two-dimensional projection belongs to an object partially occluded by said other cluster (B) if it has a different depth value than said other cluster (B).

Tracking method

The present invention relates to a volume recognition method comprising the steps of:

Growing community of inventors

Brussels, Belgium

Xavier Baele