Abstract:
The method for processing signals originating for example from several proximity sensors for the recognition of a movement of an object, comprises first respective samplings of the said signals delivered by the sensors so as to obtain a first set of first date-stamped samples, the generation, from the first set of first date-stamped samples, of new sampling times comprising a start of movement time, an end of movement time, and times regularly spaced between the start of movement time and the end of movement time, a re-sampling of the signal delivered by each sensor between the start of movement time and the end of movement time at the said new sampling times using the first samples, in such a manner as to generate a second set of second date-stamped samples, and a processing of the said second set of date-stamped samples by a movement recognition algorithm.
Abstract:
A method for extracting characteristic points from an image, includes extracting characteristic points from a first image, generating for each characteristic point a descriptor with several components describing an image region around the characteristic point, and comparing two by two the descriptors of the first image, the characteristic points whose descriptors have a proximity between them greater than an ambiguity threshold, being considered ambiguous.
Abstract:
The method for processing signals originating for example from several proximity sensors for the recognition of a movement of an object, comprises first respective samplings of the said signals delivered by the sensors so as to obtain a first set of first date-stamped samples, the generation, from the first set of first date-stamped samples, of new sampling times comprising a start of movement time, an end of movement time, and times regularly spaced between the start of movement time and the end of movement time, a re-sampling of the signal delivered by each sensor between the start of movement time and the end of movement time at the said new sampling times using the first samples, in such a manner as to generate a second set of second date-stamped samples, and a processing of the said second set of date-stamped samples by a movement recognition algorithm.
Abstract:
A method for extracting characteristic points from an image, includes extracting characteristic points from a first image, generating for each characteristic point a descriptor with several components describing an image region around the characteristic point, and comparing two by two the descriptors of the first image, the characteristic points whose descriptors have a proximity between them greater than an ambiguity threshold, being considered ambiguous.