# US 2013/0155226 A1 · Object tracking system using robot and object tracking method using a robot

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2013/0155226 A1
- Document ID: US20130155226A1
- Status: Published application
- Kind: A1
- Application number: 13/545,558
- Filed: 2012-07-10
- Published: 2013-06-20
- Earliest claimed: 2011-12-19
- Assignees: Electronics and Telecommunications Research Institute
- Inventors: Dae Ha LEE; Min Su JANG; Seo Hyun JEON; Young Jo CHO; Jae Hong KIM
- Web page: https://patentgrep.com/patent/US20130155226A1

## CPC

- G06T 7/215: Motion-based segmentation
- G06V 10/143: Sensing or illuminating at different wavelengths
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59)
- G06T 2207/30201: Face
- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Disclosed are an object tracking system using a robot and an object tracking method using a robot. The present invention provides an object tracking system using a robot and an object tracking method using a robot capable of continuously performing object tracking without missing the corresponding object even when the object deviates from a viewing angle of a camera, in tracking an image based object (person) using a robot.

## Claims

### Claim 1

An object tracking system using a robot, comprising:
an image acquisition unit that acquires images in front of the robot;
an object detector that detects an object from the images acquired by the image acquisition unit;
a motion pattern calculator that calculates a motion pattern including a distance from the robot and a motion direction of the robot with respect to the object detected by the object detector;
a motion pattern storage unit that stores the motion pattern calculated by the motion pattern calculator; and
a current position calculator that calculates a current position of the object based on the motion pattern for the object stored in the motion pattern storage unit when the object disappears from the images currently acquired by the image acquisition unit,
wherein tracking for the object is performed by moving the image acquisition unit based on the current position calculated by the current position calculator.

### Claim 2 (depends on 1)

The object tracking system of claim 1, wherein the object detector includes:
an image frame storage unit that stores an image frame acquired for unit time; and
a motion object extractor that compares the image frame stored in the image frame storage unit with the currently acquired image frame to extract a motion object.

### Claim 3 (depends on 1)

The object tracking system of claim 1, wherein the object detector further includes:
a face region detector that detects a face region for the detected object;
a body region detector that detects a body region for the detected object; and
a tracking region setting unit that sets a tracking region for the detected object based on at least one of the face region detected by the face region detector and the body region detected by the body region detector.

### Claim 4 (depends on 3)

The object tracking system of claim 3, wherein the face region detector uses a Haar model based on a face skin color model.

### Claim 5 (depends on 3)

The object tracking system of claim 3, wherein the body region detector detects the body region based on red (R)-green (G)-blue (B) information or hue (H)-saturation (S)-intensity (I) information according to a color of clothes of the object.

### Claim 6 (depends on 3)

The object tracking system of claim 3, wherein the object detector further includes a leg pattern detector that detects a leg pattern within the tracking region set by the tracking region setting unit; and
the motion pattern calculator calculates the motion pattern based on the leg pattern detected by the leg pattern detector.

### Claim 7 (depends on 6)

The object tracking system of claim 6, wherein the leg pattern detector is implemented by a laser sensor.

### Claim 8 (depends on 1)

The object tracking system of claim 1, wherein the object detector further includes a tracking region setting unit that sets a tracking region for the detected object, and
the motion pattern calculator calculates the motion pattern for the object within the tracking region set by the tracking region setting unit.

### Claim 9 (depends on 8)

The object tracking system of claim 8, wherein the current position calculator calculates the current position of the object based on the motion pattern in the previous tracking region for the object stored in the motion pattern storage unit when the object disappears from the images currently acquired by the image acquisition unit.

### Claim 10

An object tracking method using a robot, comprising:
acquiring images in front of the robot;
detecting an object from the images acquired in the acquiring of the images;
calculating a motion pattern including a distance from the robot and a motion direction of the robot with respect to the object detected in the detecting of the object;
storing the motion pattern calculated in the calculating of the motion pattern;
calculating a current position of the object based on the motion pattern for the object stored in the storing of the motion pattern when the object disappears from the images currently acquired in the acquiring of the images; and;
tracking the object by moving a position for acquiring the images based on the current position calculated in the calculating of the current position.

### Claim 11 (depends on 10)

The object tracking method of claim 10, wherein the detecting of the object includes:
storing an image frame acquired for unit time; and
comparing the image frame stored in the storing of the image frame with the currently acquired image frame to extract a motion object.

### Claim 12 (depends on 10)

The object tracking method of claim 10, further comprising:
detecting a face region for the object detected in the detecting of the object;
detecting a body region for the object detected in the detecting of the object; and
setting a tracking region for the object detected in the detecting of the object based on at least one of the face region detected in the detecting of the face region and the body region detected in the detecting of the body region.

### Claim 13 (depends on 12)

The object tracking method of claim 12, wherein the detecting of the face region uses a Haar model based on a face skin color model.

### Claim 14 (depends on 12)

The object tracking method of claim 12, wherein the detecting of the body region detects the body region based on red (R)-green (G)-blue (B) information or hue (H)-saturation (S)-intensity (I) information according to a color of clothes of the object.

### Claim 15 (depends on 12)

The object tracking method of claim 12, further comprising:
detecting a leg pattern within the tracking region set in the setting of the tracking region,
wherein the calculating of the motion pattern calculates the motion pattern based on the leg pattern detected in the detecting of the leg pattern.

### Claim 16 (depends on 10)

The object tracking method of claim 10, further comprising:
setting the tracking region for the object detected in the detecting of the object,
wherein the calculating of the motion pattern calculates the motion pattern for the object within the tracking region set in the setting of the tracking region.

### Claim 17 (depends on 16)

The object tracking method of claim 16, wherein the calculating of the current position calculates the current position of the object based on the motion pattern in the previous tracking region for the object stored in the storing of the motion pattern when the object disappears from the images currently acquired in the acquiring of the images.
