Robot cleaner and method for controlling the same

• US 9,610,691 B2
• Filed: 10/13/2015
• Issued: 04/04/2017
• Est. Priority Date: 10/10/2014
• Status: Active Grant

• Current Assignee: LG Electronics, Inc. (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: An, Kwangho, Noh, Dongki, Baek, Seungmin, Kim, Yeonsoo
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US14/881,738
• Publication Number:
  US 20160101524A1
• Time in Patent Office: 539 Days
• Field of Search: 382103, 382153, 382170, 382171, 382190, 382209, 382224, 382278, 382286, 348113, 348116, 348118, 700245, 700248
• CPC Class Codes: B25J 11/0085 Cleaning
• CPC Class Codes: B25J 9/1676 Avoiding collision or forbidden zones
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/145 Illumination specially adapted for pattern recognition, e.g. using gratings
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: 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
• CPC Class Codes: Y10S 901/01 Mobile robot

Abstract

A robot cleaner and a control method thereof according to the present disclosure select a seed pixel in an image of an area in front of a main body, obtain a brightness difference between an upper region and a lower region obtained by dividing a predetermined detection area including each of neighboring pixels of the seed pixel and select a pixel belonging to a detection area having a largest brightness difference as a pixel constituting the boundary between objects indicated in the image. Accordingly, the boundary between objects present within a cleaning area can be detected rapidly and correctly through an image.

Claims

1. A method for controlling a robot cleaner, comprising:

(a) acquiring an image of an area in front of a main body;

(b) selecting a seed pixel from the image acquired in step (a);

(c) obtaining a brightness difference between an upper region and a lower region obtained by horizontally dividing a predetermined detection area to which each of detection target pixels belongs, the detection target pixels including pixels belonging to the same row as the seed pixel in a column adjoining the seed pixel; and

(d) selecting a pixel belonging to a detection area having a largest brightness difference from the detection target pixels as a pixel constituting the boundary between objects indicated in the image.

2. The method of claim 1, wherein step (b) comprises:

(b-1) obtaining a brightness difference between an upper region and a lower region obtained by horizontally dividing a predetermined detection area including each of pixels constituting a column in the image; and

(b-2) selecting a pixel belonging to a detection area having a largest brightness difference from the pixels constituting the column as the seed pixel.

3. The method of claim 2, wherein step (b-1) is performed on two or more columns constituting the image.

4. The method of claim 1, wherein the seed pixel is selected from pixels within a predetermined specific area in the image.

5. The method of claim 4, wherein the robot cleaner includes a light projection unit for downward projecting patterned light including a horizontal segment to an area in front of the main body,

wherein the specific area is defined as a predetermined area above the position of a horizontal segment indicated in the image according to light projected by the light projection unit to a horizontal floor on which the main body is located.

6. The method of claim 5, further comprising vertically dividing the image into an obstacle presence region in which light projected by the light projection unit is indicated above a predetermined reference height and an obstacle absence region in which the light is indicated at the reference height,

wherein the specific area is defined as a predetermined region below the reference height in the obstacle presence region and as a predetermined region at the reference height in the obstacle absence region.

7. The method of claim 6, wherein the predetermined reference height is a height at which a horizontal segment appears in the image according to light projected by the light projection unit to the horizontal floor on which the main body is located.

8. The method of claim 1, further comprising:

detecting a boundary on the basis of pixels selected in (d); and

controlling movement of the robot cleaner on the basis of the detected boundary.

9. A robot cleaner, comprising:

a movable main body;

an image acquisition unit for acquiring an image of an area in front of the main body; and

a controller configured to select a seed pixel from the image acquired by the image acquisition unit, to obtain a brightness difference between an upper region and a lower region obtained by horizontally dividing a predetermined detection area to which each of detection target pixels belongs, the detection target pixels including pixels belonging to the same low as the seed pixel in a column adjoining the seed pixel, and to select a pixel belonging to a detection area having a largest brightness difference from the detection target pixels as a pixel constituting the boundary between objects indicated in the image.

10. The robot cleaner of claim 9, wherein, for each of pixels constituting a column in the image, the controller obtains a brightness difference between an upper region and a lower region obtained by horizontally dividing a predetermined detection area including each pixel constituting the column in the image and selects a pixel belonging to a detection area having a largest brightness difference from the pixels constituting the column as the seed pixel.

11. The robot cleaner of claim 9, wherein the controller selects the seed pixel in two or more columns constituting the image.

12. The robot cleaner of claim 9, wherein the controller selects the seed pixel from pixels within a predetermined specific area in the image.

13. The robot cleaner of claim 12, further comprising a light projection unit for downward projecting patterned light including a horizontal segment to an area in front of the main body,

wherein the controller defines a predetermined area above the position of a horizontal segment indicated in the image according to light projected by the light projection unit to a horizontal floor on which the main body is located, as the specific area.

14. The robot cleaner of claim 13, wherein the controller vertically divides the image acquired by the image acquisition unit into an obstacle presence region in which light projected by the light projection unit is indicated above a predetermined reference height and an obstacle absence region in which the light is indicated at the reference height, defines a predetermined region below the reference height as the specific area in the obstacle presence region and defines a predetermined region at the reference height as the specific area in the obstacle absence region.

15. The robot cleaner of claim 14, wherein the predetermined reference height is a height at which a horizontal segment appears in the image according to light projected by the light projection unit to the horizontal floor on which the main body is located.

16. The robot cleaner of claim 9, wherein the controller detects a boundary on the basis of the selected pixels and controls movement of the robot cleaner on the basis of the detected boundary.