Method for detecting gestures based on a pulsed radiofrequency signal
AssigneeVitesco Technologies GmbH
InventorsMaxime RATEAU, Mohamed ELKAIROUH, Maxime ROSANO
Life of this patent
Estimating the term…
Abstract
A method for detecting gestures based on a pulsed radiofrequency signal arising from a reflection from a moving target. The method can include obtaining an input datum chosen from at least one of the following types: an in-phase component I of the signal, a quadrature component Q of the signal, a phase of the signal and a derivative of the phase of the signal, corresponding to at least a portion of the signal resulting from a reflection from the target at a distance tapk. The method can further include determining, based on said input datum and using a classifier, a classification of the gesture according to the intentional or unintentional nature of the gesture.
Claims17
A method for detecting gestures based on a pulsed radiofrequency signal arising from a reflection from a moving target, comprising:
- obtaining an input datum chosen from at least one of the following types:
- an in-phase component I of the signal, a quadrature component Q of the signal, a phase of the signal and a derivative of the phase of the signal, corresponding to at least a portion of the signal resulting from a reflection from the target at a distance tapk;
- and
- determining, based on said input datum and using a classifier, a classification of the gesture according to the intentional or unintentional nature of the gesture;
- wherein the classifier is a convolutional neural network comprising at least two convolutional layers, a non-linear activation function, a pooling layer, a flatten layer and in that the input data are “int8”-quantized by signed integers.
A method for controlling an opening element of a motor vehicle, comprising:
- detecting gestures based on a pulsed radiofrequency signal arising from a reflection from a moving target, comprising:
- obtaining an input datum chosen from at least one of the following types:
- an in-phase component I of the signal, a quadrature component Q of the signal, a phase of the signal and a derivative of the phase of the signal, corresponding to at least a portion of the signal resulting from a reflection from the target at a distance tapk;
- and
- determining, based on said input datum and using a classifier, a classification of the gesture according to the intentional or unintentional nature of the gesture;
- wherein the classifier is a convolutional neural network comprising at least two convolutional layers, a non-linear activation function, a pooling layer, a flatten layer and in that the input data are “int8”-quantized by signed integers;
- wherein said target is a limb of a user of the vehicle producing a gesture, the control method further comprising:
- commanding locking or unlocking of the opening element;
- or
- respectively opening or closing of the opening element;
- or
- respectively switching of a handle flush with the opening element from a rest position to a gripping position when the gesture is identified as being intentional.
Dependencies are inferred from the claim text.