RADAR SENSOR AND METHOD OF DETECTING OBJECT USING THE SAME

• US 20130093616A1
• Filed: 10/12/2012
• Published: 04/18/2013
• Est. Priority Date: 10/14/2011
• Status: Active Grant

• Current Assignee: Hanwha Vision Company Limited (Hanwha Corporation)
• Original Assignee: Samsung Techwin Co., Ltd. (Hanwha Corporation)
• Inventors: JEON, Ki-Yong
• Granted Patent: US 9,041,592 B2
• Time in Patent Office: Days
• US Class Current: 342/118
• CPC Class Codes: G01S 13/003 Bistatic radar systems; Multistatic radar systems
• CPC Class Codes: G01S 13/56 for presence detection presence detection using near field arrangements G01V3/00, e.g. G01V3/08, G01V3/12; burglar, theft or intruder alarms with electrical actuation G08B13/22 - G08B13/26
• CPC Class Codes: G01S 13/582 adapted for simultaneous range and velocity measurements
• CPC Class Codes: G01S 13/66 Radar-tracking systems; Analogous systems
• CPC Class Codes: G01S 13/886 for alarm systems alarms with electrical actuation G08B13/22
• CPC Class Codes: G01S 7/412 based on a comparison between measured values and known or stored values
• CPC Class Codes: G01S 7/414 Discriminating targets with respect to background clutter
• CPC Class Codes: G01S 7/415 Identification of targets based on measurements of movement associated with the target

Abstract

A radar sensor and a method of detecting an object by using the same are provided. The method includes: receiving at least one radar signal reflected from the object; converting the received at least one radar signal to at least one signal in a frequency domain; accumulating the converted at least one signal for a predetermined time and extracting at least one feature from the accumulated at least one signal; and identifying the object by comparing the extracted at least one feature with at least one reference value stored in a database.

Claims

1. A method of detecting an object using a radar sensor, the method comprising:

receiving at least one radar signal reflected from the object;

converting the received at least one radar signal to at least one signal in a frequency domain;

accumulating the converted at least one signal for a predetermined time and extracting at least one feature from the accumulated at least one signal; and

identifying the object by comparing the extracted at least one feature with at least one reference value stored in a database.

2. The method of claim 1, wherein the extracting the at least one feature comprises:

generating a frequency spectrogram based on the accumulated at least one signal; and

extracting the at least one feature vector from the frequency spectrogram.

3. The method of claim 2, wherein the at least one feature vector comprises at least one of a signal periodicity, a frequency bandwidth, and an energy intensity.

4. The method of claim 1, wherein the at least one feature vector comprises at least one of a signal periodicity, a frequency bandwidth, and an energy intensity.

5. The method of claim 1, wherein the at least one reference value stored in the database comprises a minimum value and a maximum value of each of at least one feature vector for a target object or a minimum value and a maximum value of a combination of the at least one feature vector for the target object, and

wherein the identifying the object comprises identifying whether the object is the target object on the basis of whether the extracted at least one feature vector is included between the minimum value and the maximum value of each of the at least one feature vector for the target object or the minimum value and the maximum value of the combination of the at least one feature vector for the target object.

6. The method of claim 5, wherein the minimum value and the maximum value of each of the at least one feature vector for the target object, and the minimum value and the maximum value of the combination of the at least one feature vector for the target object are adjusted according to an environment condition.

7. The method of claim 1, wherein the at least one reference value stored in the database comprises at least one reference pattern generated on the basis of at least one feature vector determined for a target object, and

wherein the identifying the object comprises identifying the object by comparing the extracted at least one feature vector with the at least one reference pattern stored in the database.

8. The method of claim 1, further comprising:

estimating a distance to the object based on the at least one radar signal; and

detecting a motion of the object from a distance change of the object over time.

9. The method of claim 1, further comprising determining a minimum value and a maximum value of each of at least one feature vector for a target object or a minimum value and a maximum value of a combination of the at least one feature vector for the target object based on a displacement between each of at least one feature vector of a radar signal reflected from a background when the target object does not exist in the background and at least one feature vector of a radar signal reflected from the target object when the target object exists in the background.

10. The method of claim 9, wherein the identifying the object comprises determining the object as the target object when the extracted at least one feature vector of the object is included between the minimum value and the maximum value of each of the at least one feature vector for the target object or the minimum value and the maximum value of the combination of the at least one feature vector for the target object.

11. The method of claim 1, further comprising:

determining a minimum value and a maximum value of at least one feature vector for a target object or a minimum value and a maximum value of a combination of the at least one feature vector for the target object based on a displacement between each of at least one background feature vector of a radar signal reflected from a background when the target object does not exist in the background and at least one feature vector of a radar signal reflected from the target object when the target object exists in the background, in different environment conditions;

storing in the database each of the at least one background feature vector and the minimum value and the maximum value of the at least one feature vector for the target object or the minimum value and the maximum value of the combination of the at least one feature vector for the target object in the different environment conditions;

selecting the most similar environment condition by comparing at least one feature vector of a radar signal reflected from a background of a monitoring area with the stored at least one background feature vector when the radar sensor is installed; and

selecting a minimum value and a maximum value of at least one feature vector for the target object corresponding to the selected environment condition or a minimum value and a maximum value of a combination of the at least one feature vector for the target object corresponding to the selected environment condition.

12. The method of claim 11, wherein the identifying the object comprises determining the object as the target object when the at least one extracted feature vector is included between the minimum value and the maximum value of the at least one feature vector for the target object corresponding to the selected environment condition or the minimum value and the maximum value of the combination of the at least one feature vector for the target object corresponding to the selected environment condition.

13. A radar sensor comprising:

a signal converter which converts at least one radar signal reflected from an object to at least one signal in a frequency domain;

a feature extractor which accumulates the converted at least one signal in the frequency domain for a predetermined time and extracts at least one feature of the object from the accumulated at least one signal;

a database which stores at least one reference value for identifying the object; and

a determiner which identifies the object by comparing the extracted at least one feature with the at least one reference value stored in the database.

14. The radar sensor of claim 13, wherein the feature extractor generates a frequency spectrogram based on the accumulated at least one signal and extracts the at least one feature vector from the frequency spectrogram.

15. The radar sensor of claim 13, wherein the at least one feature vector comprises at least one of a signal periodicity, a frequency bandwidth, and an energy intensity.

16. The radar sensor of claim 13, wherein the at least one reference value stored in the database comprises a minimum value and a maximum value of each of at least one feature vector for a target object or a minimum value and a maximum value of a combination of the at least one feature vector for the target object, and the determiner identifies whether the object is the target object on the basis of whether the extracted at least one feature vector is included between the minimum value and the maximum value of each of the at least one feature vector for the target object or the minimum value and the maximum value of the combination of the at least one feature vector for the target object.

17. The radar sensor of claim 16, wherein the minimum value and the maximum value of each of the at least one feature vector for the target object, and the minimum value and the maximum value of the combination of the at least one feature vector for the target object are adjusted according to an environment condition.

18. The radar sensor of claim 15, wherein the at least one reference value stored in the database comprises at least one reference pattern generated on the basis of at least one feature vector determined for a target object, and wherein the determiner identifies the object by comparing the extracted at least one feature vector with the at least one reference pattern stored in the database.

19. The radar sensor of claim 13, wherein the feature extractor extracts at least one background feature vector of a radar signal reflected from a background when a target object does not exist in the background and at least one feature vector of a radar signal reflected from the target object when the target object exists in the background, in different environment conditions, and

the database stores each of the at least one background feature vector and a minimum value and a maximum value of the at least one feature vector for the target object or a minimum value and a maximum value of a combination of the at least one feature vector for the target object which are determined based on a displacement between each of the at least one background feature vector of the radar signal reflected from the background when the target object does not exist in the background and the at least one feature vector of the radar signal reflected from the background when the target object exists in the background, in the different environment conditions.

20. The radar sensor of claim 13, further comprising:

a distance estimator which estimates a distance to the object based on the at least one radar signal; and

a motion detector which detects a motion of the object from a distance change of the object over time.