Detection of environment for voice control of motion tracking system
A method for allowing or disallowing control of a motion tracking system by means of voice, comprising: digitally processing sound detected by each microphone of the at least one microphone; digitally computing SNR by computing both first energy of a voice signal in the detected sound and second energy of noise in the detected sound; digitally processing electromagnetic waves captured by each antenna of the at least one antenna so as to detect data packets transmitted to the computing apparatus by each sensor of the plurality of sensors, each data packet including RSSI of a respective sensor; digitally computing distance between each sensor and the computing apparatus based on the RSSI of the data packets received from the respective sensor; digitally computing a percentage of sensors of the plurality of sensors having at least one of: a distance exceeding a predetermined maximum distance threshold, and a change in distance exceeding a predetermined maximum changing distance threshold; and digitally setting allowance or disallowance of voice control based on both the SNR computed and the percentage of sensors computed.
1. A method for allowing or disallowing control of a motion tracking system by means of voice, the motion tracking system comprising a plurality of sensors adapted for arrangement on a body of a user and to wirelessly transmit data packets, and a computing apparatus to receive the data packets, wherein each of the sensors includes at least one inertial measurement device and a first communications module with an antenna, and wherein the computing apparatus comprises at least one processor, a second communications module, at least one antenna and at least one microphone, the method comprising:
digitally processing, with the computing apparatus, sound detected by each microphone of the at least one microphone;
digitally computing, with the computing apparatus, a signal-to-noise ratio by computing both first energy of a voice signal in the detected sound and second energy of noise in the detected sound;
digitally processing, with the computing apparatus, electromagnetic waves captured by each antenna of the at least one antenna so as to detect data packets transmitted to the computing apparatus by each sensor of the plurality of sensors, each data packet including both a received signal strength indicator RSSI and one or more measurements of a respective sensor, the RSSI being indicative of strength with which the respective sensor receives a wireless signal from the computing apparatus;
digitally computing, with the computing apparatus, distance between each sensor and the computing apparatus based on the RSSI of the data packets received from the respective sensor;
digitally computing, with the computing apparatus, a percentage of sensors of the plurality of sensors having at least one of: a distance exceeding a predetermined maximum distance threshold, or a change in distance exceeding a predetermined maximum changing distance threshold; and
digitally setting, in the computing apparatus, allowance or disallowance of voice control based on both the SNR computed and the percentage of sensors computed.
2. The method of claim 1 , wherein digitally setting allowance or disallowance comprises: allowing voice control when both the SNR computed exceeds a predetermined minimum SNR threshold and the percentage of sensors computed does not exceed a predetermined maximum distant sensors threshold; and disallowing voice control when the SNR computed does not exceed the predetermined minimum SNR threshold or the percentage of sensors computed exceeds the predetermined maximum distant sensors threshold.
3. The method of claim 1 , wherein the distance between each sensor and the computing apparatus digitally computed is a mean distance between each sensor and the computing apparatus in a time interval having a duration between a predetermined minimum distance time threshold and a predetermined maximum distance time threshold.
4. The method of claim 3 , wherein the percentage of sensors is a ratio of A divided by B, where A is a number of sensors whose computed mean distance has increased more than a predetermined maximum mean distance change threshold in a time interval having a duration between a predetermined minimum mean distance time threshold and a predetermined maximum mean distance time threshold, and B is a total number of sensors in the plurality of sensors.
5. The method of claim 1 , wherein the computed distance between a sensor and the computing apparatus is either equal to or proportional to
10
Pmeasured
-
RSSImean
10
·
K
,
where Pmeasured is a predetermined value corresponding to expected power with which an antenna captures electromagnetic waves of the sensors at a predetermined distance value from the computing apparatus, RSSImean is a mean RSSI of the corresponding sensor, and K is a predetermined value corresponding to a factor of wave propagation in an environment where the motion tracking system is located.
6. The method of claim 1 , wherein digitally computing the SNR comprises: providing a plurality of time windows, each time window comprising a different fragment of sound detected; computing energy of the sound in each time window of the plurality of time windows; setting a maximum energy value with the highest computed energy; discarding the time windows of the plurality of time windows having energy less than a predetermined percentage of the highest computed energy; and computing the first energy based on the non-discarded time windows of the plurality of time windows, and the second energy based on the discarded time windows of the plurality of time windows.
7. The method of claim 6 , wherein each time window has a same time duration.
8. The method of claim 1 , wherein digitally computing the SNR comprises P1 or P2, wherein P1 comprises: transforming the sound detected into a frequency domain; computing the first energy of the sound detected for frequencies within a frequency range associated with human voice; and computing the second energy of the sound detected for frequencies different from the frequency range associated with human voice; and wherein P2 comprises: applying at least a first digital filter to the sound detected thereby providing a first filtered sound, the first digital filter being a bandpass filter for frequencies of the frequency range associated with human voice; applying at least a second digital filter to the sound detected thereby providing a second filtered sound, the second digital filter at least filtering out frequencies of the frequency range associated with human voice; and computing the first energy from the first filtered sound and the second energy from the second filtered sound.
9. The method of claim 1 , further comprising repeating the digital operations of the method with the computing apparatus one or more times for digitally setting allowance or disallowance of voice control in accordance with both most recent sound detection and most recent electromagnetic wave capture.
10. The method of claim 1 , wherein digitally setting allowance or disallowance is further based on a predetermined flag corresponding to a physical exercise to be carried out by the user such that: when the predetermined flag is indicative of the user not being within reach of the computing apparatus during performance of the physical exercise, the computing apparatus digitally sets allowance of voice control irrespective of both the SNR computed and the percentage of sensors computed; and when the predetermined flag is indicative of the user being within reach of the computing apparatus during performance of the physical exercise, the computing apparatus digitally sets allowance or disallowance based on both the SNR computed and the percentage of sensors computed.
11. The method of claim 1 , wherein digitally processing the sound detected further comprises determining, from the sound detected, both existence of a voice command and an instruction of the voice command when it is determined that the voice command exists, and the method further comprising at least one of: digitally changing operation of the motion tracking system with the computing apparatus based on the instruction when the computing apparatus has last set allowance of voice control; or digitally maintaining same operation of the motion tracking system with the computing apparatus when the computing apparatus has last set disallowance of voice control.
12. The method of claim 1 , wherein digitally setting allowance or disallowance further comprises at least one of: digitally providing or commanding provision of at least one perceptible signal indicative of allowance of voice control upon setting allowance of voice control; or digitally providing or commanding provision of at least one perceptible signal indicative of disallowance of voice control upon setting disallowance of voice control.
13. The method of claim 1 , wherein digitally computing distance between each sensor and the computing apparatus based on the RSSI of the data packets received from the respective sensor comprises establishing the distance according to the RSSI of the data packets.
14. A motion tracking system comprising: a plurality of sensors adapted for arrangement on a body of a user and to wirelessly transmit data packets, each of the sensors includes at least one inertial measurement device, and a first communications module with an antenna, each data packet including both a received signal strength indicator RSSI and one or more measurements of a respective sensor, the RSSI being indicative of strength with which the respective sensor receives a wireless signal from a computing apparatus; and the computing apparatus comprising: a second communications module; at least one antenna; at least one microphone; at least one memory; and at least one processor to perform the method of claim 1 .
15. A computer program product comprising a non-transitory computer readable medium storing instructions which, when executed by a computing apparatus, cause the computing apparatus to perform the method of claim 1 .