Data acquisition method and device for motion recognition, motion recognition system and computer readable storage medium

• US 8,989,441 B2
• Filed: 03/18/2013
• Issued: 03/24/2015
• Est. Priority Date: 02/07/2013
• Status: Active Grant

• Current Assignee: Beijing Shunyuan Kaihua Technology Limited, Samsung Electro-Mechanics Co., Ltd. (Samsung Group)
• Original Assignee: Zepp Labs, Inc. (Zepp Health Corporation)
• Inventors: Han, Zheng, Dai, Xiaowei, Chen, Mi
• Primary Examiner(s): Liew, Alex
• Application Number:
  US13/846,700
• Publication Number:
  US 20140219498A1
• Time in Patent Office: 736 Days
• Field of Search: 382/103, 382181-231
• US Class Current: 382/103
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06F 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures

Abstract

A data acquisition method and device for motion recognition, a motion recognition system and a computer readable storage medium are disclosed. The data acquisition device for motion recognition comprises: an initial motion recognition module adapted to perform an initial recognition with respect to motion data collected by a sensor and provide motion data describing a predefined range around a motion trigger point to a data storage module for storage; a data storage module adapted to store motion data provided from the initial motion recognition module; and a communications module adapted to forward the motion data stored in the data storage module to a motion computing device for motion recognition. The present invention makes an initial selection to the motion data to be transmitted to the motion computing device under the same sampling rate. Consequently, the present invention reduces pressures on wireless channel transmission and wireless power consumption, and provides high accuracy in motion recognition while providing motion data at the same sampling rate.

Claims

1. A data acquisition method for motion recognition for use in a data acquisition device comprising an initial motion recognition module, a data storage module and a communications module, the method comprising:

Step S1) the initial motion recognition module performing an initial recognition with respect to motion data acquired by a sensor, and providing m*Fs frames of motion data prior to the motion trigger point, motion data regarding the motion trigger point, and n*Fs−

1 frames of motion data after the motion trigger point to the data storage module for storage, m and n denoting a predefined positive integer, and Fs denoting a sampling rate, and wherein one frame of motion data is a collection of data collected by various sensors at the same sampling moment; and

Step S2) the communications module forwarding the motion data stored at the data storage module to a motion computing device for motion recognition.

2. The method according to claim 1, wherein said Step S1) comprises:

Step S11) the initial motion recognition module storing the motion data acquired from the sensor and detecting a motion trigger point, wherein the m*Fs frames of motion data prior to the motion trigger point are stored in a first buffer, and frames of motion data starting from the motion trigger point are stored in a second buffer; and

Step S12) providing one set of motion data consisting of the m*Fs frames in the first buffer and the n*Fs frames in the second buffer to the data storage module for storage when the second buffer contains up to n*Fs frames of data.

3. The method according to claim 2, wherein said Step S11 comprises:

Step S111) the initial motion recognition module acquiring a frame of motion data from a sensor;

Step S112) determining whether a motion trigger point status is idle, and performing Step S114) if the motion trigger point status is not idle or performing Step S113) if the motion trigger point status is idle;

Step S113) detecting a motion trigger point with respect to the current frame of motion data, and, if no motion trigger point is detected, storing the current frame of motion data in the first buffer and returning to Step S111) to acquire a next frame of motion data;

if motion trigger point is detected, setting the motion trigger point status to non-idle and performing Step

     114);

Step S114) storing the current frame of motion data into the second buffer; and

Step S115) determining whether the second buffer contains up to n*Fs frames of data, and, if negative, returning to Step

     111) to acquire a next frame of motion data;

if positive, performing said Step S12),

wherein the motion trigger point status is initially set to idle, and is initialized to idle after executing said Step S12).

4. The method according to claim 2, wherein the first buffer is sized to store m*Fs frames, and uses a circulating queue.

5. The method according to claim 1, wherein motion trigger point detection in the process of initial recognition comprises at least one of a stroke detection and a large-dimension motion detection;

and

wherein if a stroke or a large-dimension motion is detected, a motion trigger point is determined to have occurred;

if no stroke or large-dimension motion is detected, no motion trigger point is determined to have occurred.

6. The method according to claim 5, wherein the stroke is detected by determining one of the following:

1);

whether the difference between an acceleration of the current frame of motion data and an acceleration of the last frame of motion data reaches a threshold value predefined for a sudden change in the acceleration;

if positive, a stroke is deemed to have occurred,

2) whether the difference between an angular speed of the current frame of motion data and the angular speed of the last frame of motion data reaches a threshold value predefined for a sudden change in the angular speed;

if positive, a stroke is deemed to have occurred; and

3) whether the difference between an acceleration of the current frame of motion data and an acceleration of the last frame of motion data reaches a threshold value predefined for a sudden change in the acceleration, and meanwhile whether the difference between an angular speed of the current frame of motion data and an angular speed of the last frame of motion data reaches a threshold value predefined for a sudden change in the angular speed;

if positive, a stroke is deemed to have occurred.

7. The method according to claim 5, wherein the large-dimension motion detection comprises:

determining whether the acceleration of the current frame of motion data is large enough to reach a predefined threshold, and meanwhile the angular speed is also large enough to reach a predefined threshold, and if positive, a large-dimension motion is determined to have occurred.

8. The method according to claim 1, wherein said Step S2) comprises:

the communications module voluntarily forwarding the motion data stored in the data storage module to the motion computing device after completion of initial recognition and storage of one set of motion data or periodically or in response to a user trigger, or

the communications module forwarding one or more sets of motion data requested by the motion computing device to the motion computing device in response to a request from the motion computing device.

18. A computer readable storage medium, which stores programs for executing the method according to claim 1.

9. A data acquisition device for motion recognition, comprising:

an initial motion recognition module adapted to perform an initial recognition with respect to motion data collected by a sensor and provide m*Fs frames of motion data prior to the motion trigger point, motion data regarding the motion trigger point, and n*Fs−

1 frames of motion data after the motion trigger point to a data storage module for storage, m and n denoting a predefined positive integer, and Fs denoting a sampling rate, and wherein one frame of motion data is a collection of data collected by various sensors at the same sampling moment;

a data storage module adapted to store motion data provided from the initial motion recognition module; and

a communications module adapted to transmit the motion data stored in the data storage module to a motion computing device for motion recognition.

10. The device according to claim 9, wherein the initial motion recognition module comprises:

a buffer and detection module adapted to store the motion data acquired from the sensor and detect a motion trigger point, wherein the m*Fs frames of motion data prior to the motion trigger point are stored in a first buffer, while frames of motion data starting from the motion trigger point are stored in a second buffer; and

a storage interactive module adapted to, when the second buffer contains up to n*Fs frames of data, provide one set of motion data consisting of the m*Fs frames in the first buffer and the n*Fs frames in the second buffer to the data storage module for storage.

11. The device according to claim 10, wherein the buffer and storage module comprises:

a data acquisition module adapted to acquire a frame of motion data from a sensor;

a first determination module adapted to determine whether a motion trigger point status is idle, and trigger a data buffering module if the motion trigger point status is not idle or trigger a motion detection module if the motion trigger point status is idle;

a motion detection module adapted to, when triggered by the first determination module, detect a motion trigger point with respect to the current frame of motion data and, if no motion trigger point is detected, trigger a data buffering module;

if motion trigger point is detected, set the motion trigger point status to non-idle;

a data buffering module adapted to, when triggered by the motion detection module, store the current frame of motion data into the first buffer, and when triggered by the first determination module, store the current frame of motion data into the second buffer and trigger a second determination module; and

a second determination module adapted to, when triggered, determine whether the second buffer contains up to n*Fs frames of data,

wherein the motion trigger point status is initialized to idle after the storage interactive module completes operations.

12. The device according to claim 10, wherein the first buffer is sized to store m*Fs frames, and uses a circulating queue.

13. The device according to claim 9, wherein motion trigger point detection performed by the initial motion recognition module in the process of initial recognition comprises at least one of a stroke detection and a large-dimension motion detection;

and

wherein if a stroke or a large-dimension motion is detected, a motion trigger point is determined to have occurred;

if no stroke or large-dimension motion is detected, no motion trigger point is determined to have occurred.

14. The device according to claim 13, wherein the stroke is detected by determining one of the following:

1);

whether the difference between an acceleration of the current frame of motion data and an acceleration of the last frame of motion data reaches a threshold value predefined for a sudden change in the acceleration;

if positive, a stroke is deemed to have occurred,

2) whether the difference between an angular speed of the current frame of motion data and the angular speed of the last frame of motion data reaches a threshold value predefined for a sudden change in the angular speed;

if positive, a stroke is deemed to have occurred; and

3) whether the difference between an acceleration of the current frame of motion data and an acceleration of the last frame of motion data reaches a threshold value predefined for a sudden change in the acceleration, and meanwhile whether the difference between an angular speed of the current frame of motion data and an angular speed of the last frame of motion data reaches a threshold value predefined for a sudden change in the angular speed;

if positive, a stroke is deemed to have occurred.

15. The device according to claim 13, wherein the initial motion recognition module detects occurrence of a large-dimension motion by determining:

whether the acceleration of the current frame of motion data is large enough to reach a predefined threshold, and meanwhile the angular speed is also large enough to reach a predefined threshold, and if positive, determines that a large-dimension motion has occurred.

16. The device according to claim 9, wherein the communications module voluntarily forwards the motion data stored in the data storage module to the motion computing device after completion of initial recognition and storage of one set of motion data or periodically or in response to a user trigger;

or

the communications module forwards one or more sets of motion data requested by the motion computing device to the motion computing device in response to a request from the motion computing device.

17. A motion recognition system, comprising:

a motion computing device; and

a data acquisition device according to claim 9,

wherein the motion computing device is adapted to perform motion recognition based on motion data transmitted from the data acquisition device.