Thales

Jerome Fournier

Etienne Payot

Alain Simon

Bruno Bustin

Jerome Alric

Jacques Rioland

Yannick Goutille

Gilles Henaff

Stephane Bourgain

Christophe Rannou

Arnaud Allais

A method for formulating a knowledge database of object images acquired by an imaging device furnished with a sensor, including defining N classes each including a set of objects represented by a label and a set of characteristics, learning decision rules associated with these classes, definition of K contextual information cues regarding image background f, with k varying from 1 to K and K&#x3e;1, association of one of these information cues regarding image background fwith each object, allotting of the objects into M new classes, with N&#x3c;M&#x2266;K&#xd7;N, each including a set of objects represented by a new label including an old label and one of said information cues regarding image background fand the set of characteristics of these objects, definition for each background fof a subset Qof these M classes associated with this image background, learning of decision rules for each of these subsets Q.

Method for classifying objects in an imaging surveillance system

The invention relates to a method of stabilizing the images of a scene, acquired by means of an observation device of an imaging system, comprising the step of digital processing of a stream of successive images. It comprises a step of acquiring gyrometric measurements by means of at least one gyrometric sensor secured to the observation device, of using these gyrometric measurements to determine so-called approximate shifts undergone between successive images, and the image processing step comprising a sub-step of using the approximate shifts and the image stream acquired to determine so-called fine shifts undergone between successive images.

Hybrid image stabilization method and apparatus

Growing community of inventors

Montigny le Bretonneux, France

Jerome Fournier