METHOD AND DEVICE FOR MOTION COUNT DETECTION

• US 20160116498A1
• Filed: 10/20/2015
• Published: 04/28/2016
• Est. Priority Date: 10/23/2014
• Status: Abandoned Application

• Current Assignee: Anhui Huami Information Technology Co., Ltd. (Zepp Health Corporation)
• Original Assignee: Anhui Huami Information Technology Co., Ltd. (Zepp Health Corporation)
• Inventors: WU, Haocheng
• Application Number:
  US14/887,821
• Publication Number:
  US 20160116498A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 22/006 Pedometers
• CPC Class Codes: G01P 13/00 Indicating or recording presence, absence, or direction, of movement electric switches H01H; counting moving objects G06M7/00

Abstract

A method and apparatus for detecting motion counts include: identifying one or more motion modes upon detection of acceleration; recording one or more motion modes to the list of motion modes limited with a maximum length and recording an occurrence number for each motion mode within the list of motion modes; upon detection of a motion mode, determining whether the detected motion mode is one of the motion modes within the list of motion modes; if the detected motion mode is one of the motion modes within the list of motion modes, increasing the occurrence number associated with the detected motion mode by one; if otherwise, appending the detected motion mode as a new motion mode to the list of motion modes and recording the occurrence number associated with the new motion mode as one. The method and apparatus effectively reduce misidentification rate, and have high extendibility.

Claims

1. A method for detecting motion counts, comprising:

identifying one or more motion modes upon detection of acceleration;

recording one or more motion modes into a list of motion modes, and recording an occurrence number for each motion mode in the list of motion modes;

upon identification of a motion mode;

determining whether the detected motion mode is one of the motion modes within the list of motion modes limited with a maximum length;

based on a determination that the detected motion mode is one of the motion modes within the list of motion modes, increasing the occurrence number associated with the detected motion mode by one;

based on a determination that the detected motion mode is none of the motion modes within the list of motion modes, appending the detected motion mode as a new motion mode to the list of motion modes, and recording the occurrence number associated with the new motion mode as one in the list of motion modes; and

using a recorded maximum occurrence number in the list of motion modes as an output of motion counts.

2. The method of claim 1, wherein the identifying one or more motion modes upon detection of acceleration, further comprises:

upon detection of acceleration, identifying one or more motion modes in accordance with one or more pre-set identification rules, which further comprises;

identifying a motion which has acceleration with pre-set variation characteristics as a motion mode, wherein the pre-set variation characteristics include variation characteristics of turning from zero to a positive value, turning from a positive value to zero, turning from zero to a negative value, and turning from a negative value to zero;

or the pre-set variation characteristics include variation characteristics of turning from zero to a negative value, turning from a negative value to zero, turning from zero to a positive value, and turning from a positive value to zero.

3. The method of claim 1, wherein the recording one or more motion modes into the list of motion modes and the recording the occurrence number for each motion mode in the list of motion modes, further comprise:

by a descending order of the occurrence numbers, assigning a node for each motion mode of one or more motion modes within the list of motion modes, and recording the motion mode and the occurrence number of the motion mode in the node, wherein the motion mode with the largest occurrence number associates with a head node, and the motion mode with the second largest occurrence number associates with a second node, and the rest may be deduced by analogy.

4. The method of claim 1, wherein the determining whether the detected motion mode is one of the motion modes within the list of motion modes, further comprises:

comparing the detected motion mode to the motion mode recorded in each node within the list of motion modes by a successive order starting from the head node, and determining whether the detected motion mode is one of the motion modes within the list of motion mode.

5. The method of claim 3, wherein based on a determination that the detected motion mode is none of the motion modes within the list of motion modes, the appending the detected motion mode as a new motion mode to the list of motion modes, and the recording the occurrence number associated with the new motion mode as one in the list of motion modes, further comprise:

based on a determination that the detected motion mode is none of the motion modes within the list of motion modes, determining whether the length of the list of motion modes exceeds a set maximum length;

upon a determination that the length of the list of motion modes does not exceed a set maximum length, directly appending the detected motion mode as a new motion mode to the end of the list of motion modes, and recording the occurrence number associated with the new motion mode as one in the list of motion modes;

upon a determination that the length of the list of motion modes exceeds a set maximum length, firstly removing the motion mode with the least occurrence number from the list of motion modes, and secondly appending the detected motion mode as a new motion mode to the end of the list of motion modes and recording the occurrence number associated with the new motion mode as one in the end node.

6. The method of claim 1, wherein the determining whether the detected motion mode is one of the motion modes within the list of motion modes, further comprises:

determining the degree of similarity between the detected motion mode and each motion mode within the list of motion modes;

upon a determination that the degree of similarity between the detected motion mode and one of the motion modes within the list of motion modes is equal or greater than a pre-set value, deciding that the detected motion mode is said motion mode; and

upon a determination that the degree of similarity between the detected motion mode and any of the motion modes within the list of motion modes is less than the pre-set value, deciding that the detected motion mode is none of the motion modes within the list of motion modes.

7. The method of claim 6, wherein the using a recorded maximum occurrence number in the list of motion modes as an output of motion counts, further comprises:

recording a characteristic value associated with the detected motion mode with a maximum occurrence number to a library of historical characteristic values of the same motion mode, and determining a mean value for the characteristic values of the same motion mode from the historical characteristic values of the same motion mode as the characteristic value associated with the node within the list of the motion modes for use in next detection; and

when next detection starts, upon a determination that a difference between the characteristic value of the detected motion mode and the mean value of the characteristic values of the same motion mode is less than a pre-set difference value, recording the occurrence number associated with the detected motion mode as one.

8. An apparatus for detecting motion counts, comprising:

an identification module, wherein the identification module identifies one or more motion modes upon detection of acceleration;

a first record module, wherein the first record module records one or more motion modes to a list of motion modes and records an occurrence number for each motion mode within the list of motion modes;

a determination module, wherein upon detecting a motion mode, the determination module determines whether the detected motion mode is one of the motion modes within the list of motion modes;

upon a determination that the detected motion mode is one of the motion modes within the list of motion modes, the determination module increases the occurrence number associated with the detected motion mode by one; and

upon a determination that the detected motion mode is none of the motion modes within the list of motion modes, the determination module appends the detected motion mode as a new motion mode to the list of motion modes and records the occurrence number associated with the new motion mode as one in the list of motion modes; and

an output module, wherein the output module uses a recorded maximum occurrence number in the list of motion modes as an output of motion counts.

9. The apparatus in claim 8, wherein the identification module comprises:

an identification sub-module, wherein upon detection of acceleration, the identification sub-module identifies one or more motion modes in accordance with one or more pre-set identification rules;

wherein the pre-set identification rules comprises;

identifying a motion which has acceleration with pre-set variation characteristics as a motion mode, wherein the pre-set variation characteristics include variation characteristics of turning from zero to a positive value, turning from a positive value to zero, turning from zero to a negative value, and turning from a negative value to zero;

or the pre-set variation characteristics include variation characteristics of turning from zero to a negative value, turning from a negative value to zero, turning from zero to a positive value, and turning from a positive value to zero.

10. The apparatus in claim 8, wherein the first record module comprises:

a first record sub-module, wherein the first record sub-module assigns a node for each motion mode of one or more motion modes within the list of motion modes by a descending order of the occurrence numbers, and records the motion mode and the occurrence number associated with each node, wherein the motion mode with the largest occurrence number associates with a head node, and the motion mode with the second largest occurrence number associates with a second node, and the rest may be deduced by analogy.

11. The apparatus in claim 8, wherein the determination module comprises:

a first determination sub-module, wherein the first determination sub-module compares the detected motion mode to the motion mode recorded in each node within the list of motion modes by a successive order starting from the head node, and determines whether the detected motion mode is one of the motion modes within the list of motion mode.

12. The apparatus in claim 11, wherein the determination module further comprises:

a second determination sub-module, wherein based on a determination that the detected motion mode is none of the motion modes within the list of motion modes, the second determination sub-module determines whether the length of the list of motion modes exceeds a set maximum length;

upon a determination that the length of the list of motion modes does not exceed the set maximum length, the second determination sub-module directly appends the detected motion mode as a new motion mode to the end of the list of motion modes, and records the occurrence number associated with the new motion mode as one in the list of motion modes;

upon a determination that the length of the list of motion modes exceeds the set maximum length, the second determination sub-module firstly removes the motion mode with the least occurrence number from the list of motion modes, and secondly appends the detected motion mode as a new motion mode to the end of the list of motion modes and records the occurrence number associated with the new motion mode as one in the end node.

13. The apparatus in claim 8, wherein the determination module comprises:

a third determination sub-module, wherein the third determination sub-module determines the degree of similarity between the detected motion mode and each motion mode within the list of motion modes;

a first decision sub-module, wherein upon a determination that the degree of similarity between the detected motion mode and one of the motion modes within the list of motion modes is equal or greater than a pre-set value, the first decision sub-module decides that the detected motion mode is said motion mode; and

a second decision sub-module, wherein upon a determination that the degree of similarity between the detected motion mode and any of the motion modes within the list of motion modes is less than the pre-set value, the second decision sub-module decides that the detected motion mode is none of the motion modes within the list of motion modes.

14. The apparatus in claim 13, further comprising:

a second record module, wherein the second record module records a characteristic value associated with the detected motion mode with a maximum occurrence number to a library of historical characteristic values of the same motion mode;

a determination module, wherein the determination module determines a mean value of the characteristic values of the same motion mode from the historical characteristic values of the same motion mode as the characteristic value associated with the node within the list of the motion modes for use in next detection; and

a third record module, wherein when next detection starts, upon a determination that a difference between the characteristic value of the detected motion mode and the mean value of the characteristic values of the same motion mode is less than a pre-set difference value, the third record module records the occurrence number associated with the detected motion mode as one.