Abstract: A device identifying a cyclic movement type of a physical system from a set of possible cyclic movements types includes: a movement sensor providing an observation data sequence concerning the physical system; a storage storing at least one statistical hidden-state Markov model; and a computer programmed to analyze the observation data sequence and select one cyclic movement type based on the stored statistical model. The storage includes least one statistical hidden-state Markov model for each possible cyclic movement type and the computer is programmed to analyze compatibility of the observation data sequence with each possible cyclic movement type based on the statistical model associated with this cyclic movement type. The computer is further programmed to provide a sequence of hidden states of the statistical model associated with the selected cyclic movement type, based on the observation data sequence and the statistical model associated with the selected cyclic movement type.

Abstract: A remote control, such as a 3D air mouse, includes motion sensors used to measure position/orientation in space to alternatively control a cursor on a display, recognize gestures by the user so that data/commands can be entered into an electronic system being controlled or the like. Timed sequences of pressing a single trigger button and the quantity of motion during said sequences are both timed in relation to thresholds to switch between modes.

Abstract: A device (DISP) for gestural control of a system (SYST) includes a grippable mobile control element (TC), a movement sensor assembly (EC) for measuring movements of the mobile control element (TC), and a processing circuit (DET) for detection the rotation or translation of the mobile control element in relation to an axis that is substantially invariant over a time window. The device (DISP) also includes a circuit (REG) for adjusting the value of at least one parameter of the system, and a circuit (CMD) for controlling activation/deactivation of the adjustment upon a detection by the detection circuit (DET) of a rotation and/or translation of the mobile control element in relation to an axis that is substantially invariant over a time window.

Abstract: A pointing device includes accelerometers and rotational sensors that are coupled to a processor. The processor samples the accelerometers and rotational sensors to detect gravity and pointing device motion and uses algebraic algorithms to calculate roll compensated cursor control signals. The processor transmits the cursor control signals to a receiver that is coupled to an electronic device that moves the cursor on the visual display.

Abstract: A user to machine interface emulates a touch interface on a screen. The interface is configured for operating in a touch emulation mode based on a triggering event. A triggering event may be a rotation around a first axis of an angle higher than a first threshold. Analysis of the amount of rotation around a second axis may be used to determine the number of fingers defining a specific touch gesture. An infinite variety of touch gestures may therefore be emulated by a remote control based on application context thus allowing for multiple uses of the touch screen machine from a distance.

Abstract: This method for detecting activity (A) of a physical system carrying a motion sensor comprises the following steps: extracting (100) a sequence (M) of measurements provided by the motion sensor; deducing (102) therefrom an observation sequence (O) calculated on the basis of the measurement sequence (M); determining (104) the activity (A) of the physical system in the form of a sequence of states corresponding to the observation sequence, using a statistical model of components of the observation sequence in view of a plurality of possible predetermined states of the physical system. At least one component of the observation sequence (O) is calculated on the basis of a reference value ({circumflex over (?)}) of a vector representing a reference axis.

Abstract: The invention relates to a processing logic for determining a position of a virtual object on a display configured to: receive from one or more motion sensors motion signals representative of an orientation of a first device and/or a derivative thereof; obtain a first set of data representative of the orientation of the first device based on the motion signals; obtain a second set of data representative of the orientation of the first device based on the motion signals, said second set of data being different from the first set of data; calculate a first candidate position of the virtual object on a display based on the first set of data; calculate a second candidate position of the virtual object on the display based on the second set of data; select one of the first candidate position and the second candidate position as a position of the virtual object on the display.

Abstract: The invention discloses an improved method and device for sensing orientation of an object in space in a Working Reference Frame. The device of the invention includes an angular velocity sensor with at least two sensing axes and a linear acceleration sensor with at least three sensing axes. The method used for sensing orientation of the object in space in the Working Reference Frame uses synthetic values of the gravity component of the acceleration of the object. It depends upon the number of sensing axes of the angular velocity sensor and upon the dynamicity of the movement of the object. The dynamicity of the movement of the object is tested to compute the synthetic values which are used. The method and device of the invention allow control of a cursor on a display, independently of the roll imparted to the device by a user, in a seamless manner which is greatly improved over the devices and methods of the prior art.

Abstract: A method for the continuous recognition of gestures of a user of a handheld mobile terminal fitted with a motion sensor assembly, includes the steps of, for at least one motion sensor measuring signal of the motion sensor assembly, over a time window: detecting (2) a candidate gesture; and comparing (3) said candidate gesture with a set of predetermined gestures. The candidate gesture detection step (2) includes substeps of: calculating the value of a parameter representative of the symmetry of the gesture with respect to at least one axis; and calculating the value of a parameter representative of the energy of the gesture along at least one axis.

Abstract: A system for observing a swimming activity of a person includes a waterproof housing (BET) having a motion sensor (MS), and is furnished with fixing means (BEL) for securely fastening the housing (BET) to a part of the body of a user. The system has analysis means (AN) for analyzing the signals transmitted by the motion sensor (MS) to at least one measurement axis and which are adapted for determining the type of swimming of the user as a function of time by using a hidden Markov model with N states corresponding respectively to N types of swimming.

Abstract: A method estimating orientation of a path followed by a carrier of a movement sensor includes: determining an orientation of the movement sensor with respect to the path; estimating an orientation of the movement sensor with respect to a fixed reference; estimating an orientation of the path with respect to the fixed reference by the determined orientation of the movement sensor and the estimated orientation of the movement sensor; detecting start and end of a phase of disorientation of the movement sensor with respect to the path; updating, after the detected end of the disorientation phase, determined orientation of the movement sensor with respect to the path by orientation of the path with respect to the fixed reference as estimated at the detected start of the disorientation phase and orientation of the movement sensor with respect to the fixed reference as estimated after the detected end of the disorientation phase.

Abstract: A system for analyzing a user's strides has a first sensor assembly (EC1) furnished within a housing, with a triaxial magnetometer (3M) fixed to the housing (BT), which is associated with a moving frame (LF). First fixing means (MF1) fixes the first sensor assembly (EC1) to a leg segment of the user. Processing means (MT) calculates the angle of yaw (YawGF) and/or of pitch (PitchGF) and/or of roll (RollGF) of the first sensor assembly (EC1), and calculates the corresponding angular temporal variation or variations ( ? Yaw GF ? t , ? Pitch GF ? t , ? Roll GF ? t ) , in a fixed global frame (GF) relative to the terrestrial frame, on the basis of the measurements of the triaxial magnetometer (3M) delivered in the moving frame (LF).

Abstract: A method for configuring a device for detecting a situation from a set of situations where a physical system comprises the following steps: reception of a learning sequence corresponding to a given situation of the physical system; determination of parameters of a hidden-state Markov statistical model recorded in the detection device and relating to the given situation, on the basis of a prior initialization of these parameters.

Abstract: A system for determining activity of a mobile element, includes at least one motion sensor having a measurement axis, and which is securely connected to the mobile element. A filter for selects, for each measurement axis of the motion sensor, high frequencies above a first threshold, and processing equipment for determines a unidimensional high-frequency component (y(n)) equal to the square of the Euclidean norm of the high frequencies along the measurement axes of the motion sensor. A calculator calculates, for each state, probability density functions (Py,i) of the high-frequency component, the probability density function corresponding to each state according to a Chi-square law with a degree of freedom equal to the number of measurement axes of the motion sensor. An analyzer defines states of the mobile element, utilizing the probability density function of the high-frequency component for each state, together with the probabilities of transitions between two successive states.

Abstract: The magnetic field measurement system comprises a triaxial main sensor (1) for measuring magnetic field that can move jointly with a carrier element (2) capable of generating at least one additional magnetic field disturbing the measurements of said triaxial main sensor (1), said triaxial sensor (1) being adapted for providing orthonormal measurements for a reference magnetic field in the absence of magnetic disturbances due to said carrier element (2). The system comprises means of adjustment (5, 6, 7, 9, 4a, 4b) of said triaxial main sensor (1) comprising a removable additional sensor for magnetic field measurement, that can move jointly with said carrier element (2), and disposed outside said carrier element (2) away from the additional magnetic field or fields.

Abstract: A system for determining the posture of a person has a motion sensor (CM) with at least one axis of measurement, which is provided with fixing means (MF) for rigidly connecting said motion sensor (CM) to a user. Analysis means (AN) are also included for determining a posture of the user. The analysis means (AN) utilize: (A) joint densities of probabilities of a low-frequency component and a high-frequency component, these densities of probabilities being defined for each posture; and (B) probabilities of transition between two successive postures.

Abstract: A system for inputting graphical elements Includes a substantially pen-shaped peripheral device (PD); means (DIG) for digitizing graphical elements produced by a first end (END1) of the peripheral device (PD); and display means (DISP) suitable for displaying the said graphical elements produced. The system also includes means (MSR) for measuring signals representative of the movement executed by the peripheral device (PD), which includes a gyrometer (G) with at least two measurement axes providing angular speeds according to the said axes, linked in a fixed manner to the said peripheral device (PD). Means (POS) for positioning, on the display means (DISP), a pointing element (PT), based on the said angular speeds, is also provided, together with means (ACT) for activating/deactivating the positioning means (POS).

Abstract: The invention discloses a device and a method to control an object on a surface using motion sensor measurements and relative and absolute pointing algorithms. Relative pointing is preferred at low speeds and absolute pointing is preferred at high speeds. Transition between the results of the two algorithms has to be smoothed, using a weighted combination of the two results. The weights may be made dependent over time or over speed of the device. Maximum and minimum values of different parameters may have to be set to avoid jumps or changes in direction which may affect the user's experience negatively. The goal is that the user has consistent perceptions what he or she sees on the screen and the movements he or she imparts on the device, while still keeping the position of the object as close as possible to the position calculated by an absolute pointing algorithm.

Abstract: A method determining values of parameters representing a movement of an entity represented by an articulated chain, by a sensor assembly including at least one sensor for a parameter representing an orientation of a first segment of the articulated chain, the method including: reception of an orientation value measured and supplied by the orientation sensor; estimation of a value of at least one first parameter representing a movement of the first segment by processing the orientation value; and, based on a predetermined movement model of the articulated chain, as a time change model, including at least one relationship of time dependency between the at least one first parameter and at least one other parameter representing a movement of another segment of the articulated chain: estimation of a value of the at least one other parameter by application of the time change model to the estimated value of the at least one first parameter.

Abstract: A system for real-time determination of a parameter of a movement having a repetitive form includes first estimating means for estimating an approximation of the period of the repetitive movement, before the end of the current movement, on the basis of representative signals indicative of the movement. A determining means determines a size of a sliding window on the basis of the period estimated by the first estimating means. Finally, a second estimating means precisely estimates, using the sliding window, the movement parameter, on the basis of the representative signals indicative of the movement and of the size of the sliding window delivered by the first estimating means.