System for performing distortion correction and calibration using pattern projection, and method using the same

1. A system, comprising:

a projector that projects an original pattern image onto a screen;

at least one camera that captures the original pattern image projected onto the screen and provides the captured image as a photographed pattern image, the photographed pattern image including image distortion caused by camera lens and a calibration state of the at least one camera; and

an image processing device comprising at least one processor and a memory storing instructions configured to instruct the at least one processor to perform:

calculating a calibration parameter by comparing the original pattern image with the photographed pattern image, the calibration parameter for correcting the image distortion in the photographed pattern image,

wherein the calibration parameter is calculated using a plane equation obtained based on a difference between the original pattern image and the photographed pattern image,

wherein the calibration parameter is applied to the photographed pattern image to correct the image distortion, and

wherein the comparing the original pattern image with the photographed pattern image comprises:

setting at least one reference pattern in the original pattern image;

extracting a search region from the photographed pattern image by utilizing x and y coordinates of a center point of the at least one reference pattern; and

performing pattern matching between the at least one reference pattern and a pattern in the search region, the search region corresponding to a region including a periphery of the at least one reference pattern.

2. The system of claim 1 , wherein the projector and the at least one camera are positioned on the same horizontal axis or vertical axis.

3. The system of claim 1 , wherein the setting at least one reference pattern in the original pattern image comprises setting the at least one reference pattern in the original pattern image so that a portion corresponding to the at least one reference pattern exists in the photographed pattern image.

4. The system of claim 1 , wherein the performing pattern matching comprises tracking at least one of positional movement, angle conversion, and size conversion for a pattern included in the search region with respect to a reference pattern included in the original pattern image based on the at least one reference pattern.

5. The system of claim 4 , wherein the calculating a calibration parameter comprises:

obtaining the plane equation using the tracked at least one of positional movement, angle conversion, and size conversion for the pattern included in the search region; and

calculating the calibration parameter based on the plane equation.

6. The system of claim 5 , wherein the instructions are further configured to instruct that at least one processor to perform generating a depth image by applying the calibration parameter to the photographed pattern image that includes the image distortion, the depth image corresponding to the photographed pattern image whose image distortion has been corrected.

7. The system of claim 1 , wherein the original pattern image includes a specific pattern including random dots or lines.

8. An image processing device, comprising:

at least one processor; and

a memory storing instructions configured to instruct the at least one processor to perform:

comparing an original pattern image projected by a projector with a photographed pattern image obtained by a camera, the photographed pattern image including image distortion caused by camera lens and a calibration state of the camera, the comparison being performed by setting at least one reference pattern in the original pattern image, extracting a search region from the photographed pattern image by utilizing x and y coordinates of a center point of the at least one reference pattern, and performing pattern matching between the at least one reference pattern and a pattern in the search region, the search region corresponding to the at least one reference pattern;

calculating a calibration parameter using a plane equation, which is obtained based on a difference between the original pattern image and the photographed pattern image, the difference being obtained by the pattern matching; and

generating a depth image by applying the calibration parameter to the photographed pattern image, the depth image corresponding to the photographed pattern image whose image distortion has been corrected.

9. The image processing device of claim 8 , wherein the comparing an original pattern image projected by a projector comprises:

setting the at least one reference pattern in the original pattern image;

extracting the search region corresponding to a region including a periphery of the at least one reference pattern from the photographed pattern image; and

performing the pattern matching by tracking at least one of positional movement, angle conversion, and size conversion for a pattern included in the search region with respect to a reference pattern included in the original pattern image based on the at least one reference pattern.

10. The image processing device of claim 9 , wherein the calculating a calibration parameter comprises:

obtaining the plane equation using the tracked at least one of positional movement, angle conversion, and size conversion for the pattern included in the search region based on the at least one reference pattern; and

calculating the calibration parameter based on the plane equation.

11. A method, comprising:

projecting an original pattern image onto a screen;

generating a photographed pattern image by capturing the projected original pattern image using at least one camera, the photographed pattern image including image distortion caused by camera lens and a calibration state of the at least one camera; and

calculating a calibration parameter by comparing the original pattern image with the photographed pattern image, the calibration parameter for correcting the image distortion in the photographed pattern image,

wherein the calibration parameter is calculated using a plane equation obtained based on a difference between the original pattern image and the photographed pattern image,

wherein the calibration parameter is applied to the photographed pattern image to correct the image distortion, and

wherein the calculating of the calibration parameter includes:

setting at least one reference pattern in the original pattern image and a search region in the photographed pattern image; and

performing pattern matching between the at least one reference pattern and a pattern in the search region.

12. The method of claim 11 , further comprising:

generating a depth image by applying the calibration parameter to the photographed pattern image that includes the image distortion, the depth image corresponding to the photographed pattern image whose image distortion has been corrected.

13. The method of claim 11 , wherein the original pattern image includes a specific pattern including random dots or lines.

14. The method of claim 11 , wherein the setting of the at least one reference pattern includes setting a corresponding adjacent region with respect to center coordinates of the at least one reference pattern in the original pattern image, as the search region in the photographed pattern image.

15. The method of claim 11 , wherein the performing of the pattern matching includes tracking at least one of positional movement, angle conversion, and size conversion for a pattern included in the search region with respect to a reference pattern included in the original pattern image based on the at least one reference pattern.

16. The method of claim 15 , wherein the calculating of the calibration parameter includes

obtaining the plane equation using the tracked at least one of positional movement, angle conversion, and size conversion for the pattern included in the search region, and

calculating the calibration parameter based on the plane equation.