Detecting user input from multi-modal hand bio-metrics
According to an example aspect of the present invention, there is provided an input device and corresponding method which digitizes and transforms minute hand movements and gestures into user interface commands without interfering with the normal use of one's hands. The device and method may, for example, determine user actions based on detected user action characteristics from a plurality of sensors, where the sensors are preferably of different types.
1 . A multimodal biometric measurement apparatus, the apparatus comprising:
a mounting component configured to be worn by a user,
at least one wrist contour sensor,
at least one bioacoustic sensor comprising a vibration sensor,
at least one inertial measurement unit, IMU, comprising an accelerometer and gyroscope, and
a controller comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to with the at least one processor, to cause the controller at least to:
receive a first sensor data stream from the at least one wrist contour sensor,
receive a second sensor data stream from the at least one bioacoustic sensor, and
receive a third sensor data stream from the at least one inertial measurement unit,
wherein the at least one wrist contour sensor, the at least one bioacoustic sensor, and the at least one inertial measurement unit are arranged within a single housing and wherein the first, the second and the third sensor data stream are received concurrently, and
determine, based on at least one of the first, the second and the third sensor data stream, at least one characteristic of a user action,
determine, based on the determined at least one characteristic of a user action, at least one user action, and
generate at least one user interface, UI, command, based at least in part on the determined at least one user action,
wherein the wrist contour sensor comprises an array of profilometric sensors and wherein said array is arranged with the at least one bioacoustic sensor on the surface of the single housing.
2 . The apparatus of claim 1 , wherein determining the at least one characteristic of a user action comprises providing at least one of the first, the second and the third sensor data stream as an input to at least one neural network trained to determine at least one characteristic of a user action as an output, wherein the output of the at least one neural network comprises a confidence value of the at least one characteristic of a user action.
3 . The apparatus of claim 2 , wherein determining the at least one user action comprises providing the output of the at least one neural network to an event interpreter configured to determine the user action based on the determined user action characteristics and received contextual information.
4 . The apparatus of claim 2 , wherein the controller is configured to perform preprocessing on at least one of the first, the second and the third sensor data stream before providing the at least one preprocessed data stream as an input to the at least one neural network.
5 . The apparatus of claim 1 , wherein the controller is further configured so that the first sensor data stream is provided to a first neural network, the second sensor data stream is provided to a second neural network, and the third sensor data stream is provided to a third neural network or mathematical model.
6 . The apparatus of claim 1 , wherein the controller is further configured so that the first, the second and the third sensor data stream are provided to the same neural network.
7 . The apparatus of claim 1 , wherein the apparatus comprises a smartwatch.
8 . The apparatus of claim 1 , wherein the apparatus comprises an add-on device, wherein the apparatus is configured to be attached to another wearable by at least one of the following arrangements:
wherein the add-on apparatus is configured to be directly attached to the body of another wearable in such a manner that the sensors of the add-on apparatus may measure the user;
wherein the add-on apparatus is configured to be attached to a mounting component of the other wearable; and/or
wherein the add-on apparatus is configured to be part of or connected to a mounting component of the other wearable.
9 . A method to generate UI commands, the method comprising:
receiving a first sensor data stream from at least one wrist contour sensor,
receiving a second sensor data stream from at least one bioacoustic sensor, and
receiving a third sensor data stream from at least one inertial measurement unit,
wherein the at least one wrist contour sensor, the at least one bioacoustic sensor, the at least one inertial measurement unit are arranged within a single housing and wherein the first, the second and the third sensor data stream are received concurrently, and
determining, based on at least one of the first, the second and the third sensor data stream, at least one characteristic of a user action,
determining, based on the determined at least one characteristic of a user action, at least one user action, and
generating at least one user interface, UI, command, based at least in part on the determined at least one user action,
wherein the wrist contour sensor comprises an array of profilometric sensors and wherein said array is arranged with the at least one bioacoustic sensor in an annular form on the surface of the single housing.
10 . The method of claim 9 , wherein determining the at least one characteristic of a user action comprises providing at least one of the first, the second and the third sensor data stream as an input to at least one neural network trained to determine at least one characteristic of an user action as an output, wherein the output of the at least one neural network comprises a confidence value of the at least one characteristic of an user action.
11 . The method of claim 9 , wherein determining the at least one user action comprises providing the output of the at least one neural network to an event interpreter configured to determine the user action based on the determined user action characteristics.
12 . The method of claim 11 , wherein the controller is further configured so that the event interpreter comprises at least one of: an inference engine, a decision tree.
13 . The method of claim 9 , wherein preprocessing is performed on at least one of the first, the second and the third sensor data stream before providing the at least one preprocessed data stream as an input to the at least one neural network.
14 . The method of claim 9 , wherein the first sensor data stream is provided to a first neural network, the second sensor data stream is provided to a second neural network, and the third sensor data stream is provided to a third neural network or mathematical model.
15 . The method of claim 9 , wherein the first, the second and the third sensor data stream are provided to the same neural network.
16 . The method of claim 9 , wherein the single housing comprises a smartwatch.
17 . The method of claim 9 , wherein the apparatus comprises an add-on device, wherein the apparatus is configured to be attached by at least one of the following arrangements:
wherein the add-on apparatus is configured to be directly attached to the body of another wearable in such a manner that the add-on apparatus may measure the user;
wherein the add-on apparatus is configured to be attached to a mounting component; and/or
wherein the add-on apparatus is configured to be part of or connected to a mounting component such as a strap.
18 . A non-transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least:
receive a first sensor data stream from at least one wrist contour sensor,
receive a second sensor data stream from at least one bioacoustic sensor, and
receive a third sensor data stream from at least one inertial measurement unit,
wherein the at least one wrist contour sensor, the at least one bioacoustic sensor, and the at least one inertial measurement unit are arranged within a single housing and wherein the first, the second and the third sensor data stream are received concurrently, and
determine, based on at least one of the first, the second and the third sensor data stream, at least one characteristic of a user action,
determine, based on the determined at least one characteristic of a user action, at least one user action, and
generate at least one user interface, UI, command, based at least in part on the determined at least one user action,
wherein the wrist contour sensor comprises an array of profilometric sensors and wherein said array is arranged with the at least one bioacoustic sensor on the surface of the single housing.