HUMAN RECOGNITION APPARATUS AND HUMAN RECOGNITION METHOD

• US 20100070187A1
• Filed: 01/30/2009
• Published: 03/18/2010
• Est. Priority Date: 08/04/2008
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: CHOI, Seung Min, Cho, Jae II, Lim, Eul Gyoon, Kim, Do Hyung, Lee, Jae Yeon, Hwang, Dae Hwan, Chang, Ji Ho, Shin, Ho Chul
• Granted Patent: US 8,271,204 B2
• Time in Patent Office: Days
• US Class Current: 702/19
• CPC Class Codes: G01H 17/00 Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups see provisionally also G01H1/00
• CPC Class Codes: G06F 2218/10 by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
• CPC Class Codes: G06V 40/25 Recognition of walking or running movements, e.g. gait recognition

Abstract

Provided are a human recognition apparatus and a human recognition method identifying a user based on a walking pattern. The human recognition apparatus includes a detecting unit detecting a vibration according to a user'"'"'s walking, and outputting an electric signal, a pattern calculating unit acquiring a walker'"'"'s walking pattern from the electric signal, and a user determining unit comparing the walking pattern with a previously measured reference data by user and identifying the user based on the comparison result. The human recognition apparatus and the human recognition method are robust against peripheral noise and can increase an acceptance rate through a simple structure and procedure by using the waling pattern, which is one-dimensional time information requiring no vast data throughput, as the user identification data.

Claims

1. A human recognition apparatus, comprising:

a detecting unit detecting a vibration according to a user'"'"'s walking, and outputting an electric signal;

a pattern calculating unit acquiring a walker'"'"'s walking pattern from the electric signal; and

a user determining unit comparing the walking pattern with a previously measured reference data by user and identifying the user based on the comparison result.

2. The human recognition apparatus of claim 1, further comprising a storing unit storing the previously measured reference data by user.

3. The human recognition apparatus of claim 1, wherein the detecting unit comprises:

a vibration sensor outputting an electric signal corresponding to peripheral vibration; and

a high pass filter eliminating a low frequency noise from the electric signal.

4. The human recognition apparatus of claim 1, wherein the pattern calculating unit outputs a ratio of a time interval between a second vibration signal and a next first vibration signal to a time interval between a first vibration signal and the second vibration signal as the user'"'"'s walking pattern, where the first vibration signal is generated when one foot of the user lands on the ground, and the second vibration signal is generated when the other foot of the user lands on the ground.

5. The human recognition apparatus of claim 4, wherein the pattern calculating unit comprises:

a pulse converting unit converting the first vibration signal into a first pulse, and converting the second vibration signal into a second pulse;

a counting unit counting a period of the first pulse to output a first count value, and counting a period of the second pulse to output a second count value; and

an operation unit dividing the second count value by the first count value.

6. The human recognition apparatus of claim 1, wherein the pattern calculating unit comprises:

a sampling unit detecting peaks of the electric signal;

a selecting unit selecting at least three successive peaks from the detected peaks, and calculating at least two time intervals between the selected peaks; and

an operation unit calculating a ratio of the at least two time intervals.

7. The human recognition apparatus of claim 1, wherein the user determining unit comprises:

a comparing unit calculating similarity between the walking pattern and the at least one reference data; and

a selecting unit selecting a reference data having the highest similarity and extracting user information corresponding to the selected reference data.

8. The human recognition apparatus of claim 7, wherein the user determining unit further comprises a verifying unit comparing the similarity with a preset threshold value and outputting an identification failure signal when the similarity is less than the preset threshold value.

9. The human recognition apparatus of claim 1, wherein the user determining unit comprises:

a subtractor subtracting the walking pattern and the at least one reference data to output an absolute value of the resulting value;

a comparator outputting a true value when the lowest absolute value of the output of the subtractor is less than a preset threshold value; and

an operator selecting the reference data where the lowest absolute value is calculated, when the output of the comparator is a true value.

10. A human recognition method, comprising:

detecting a vibration according to a user'"'"'s walking, and converting the detected vibration into an electric signal;

calculating a walker'"'"'s walking pattern according to the electric signal; and

comparing the calculated walking pattern with a previously measured reference data by user and identifying the user based on the comparison result.

11. The human recognition method of claim 10, wherein the calculating of the walking pattern comprises:

detecting a first vibration signal generated when one foot of the user lands on the ground;

detecting a second vibration signal subsequent to the first vibration signal and generated when the other foot of the user lands on the ground;

detecting the first vibration signal subsequent to the second vibration signal; and

calculating a ratio of a second time interval between the second vibration signal and the next first vibration signal to a first time interval between the first vibration signal and the second vibration signal.

12. The human recognition method of claim 10, wherein the identifying of the user comprises:

calculating at least one similarity by comparing the walking pattern with the at least one reference data;

selecting the reference data corresponding to the highest similarity among the at least one similarity; and

extracting user information corresponding to the selected reference data, and outputting the extracted user information as a walking user.

13. The human recognition method of claim 10, further comprising verifying if the highest similarity is greater than a preset threshold value.

14. The human recognition method of claim 13, further comprising performing the calculating of the walking pattern and the identifying of the user on another section of the electric signal when the highest similarity is less than the preset threshold value.

15. The human recognition method of claim 13, further comprising:

calculating at least one new walling pattern when the highest similarity is less than the preset threshold value, and calculating a mean value of the previous walking pattern and the new walking pattern; and

identifying the user by using the mean value.