Method for removing object to be processed from image and device for performing method

1. A method of removing a processing-target object from an image, the method comprising:

determining, by an image processing device, the processing-target object in the image; and

performing, by the image processing device, image post-processing with respect to the processing-target object,

wherein the processing-target object is an object which has been unintentionally imaged,

wherein the processing-target object is determined based on at least one condition that the object is imaged when the object is located at a predetermined threshold distance or less from the image processing device,

wherein the processing-target object is determined further based on the at least one condition that the object is in the image for a predetermined time during the image processing device is moved, or the object appears repeatedly in the image during the image processing device is moved,

wherein the processing-target object is removed from the image, and an interpolation-target region including the processing-target object is interpolated on the basis of a frame including the processing-target object and/or a frame adjacent to the frame,

wherein the interpolation-target region is interpolated based on information on pixels located in an outer region of the interpolation-target region, the outer region includes pixels located at a predetermined distance in an opposite direction from a center of the processing-target object, and the information on the pixels of the outer region includes luminance information and chrominance information,

wherein the interpolation-target region is divided as a plurality of interpolation-target sub-regions based on a predetermined threshold degree of change of the luminance information and the chrominance information on the pixels of the outer region.

2. The method of claim 1 , wherein it is determined whether the processing-target object is present in a determination-target region, and

the determination-target region is decided by learning imaging locations of objects which are included in a plurality of images and identical to the processing-target object.

3. The method of claim 2 , wherein the image is an omnidirectional image generated by an omnidirectional image processing device including a plurality of image capturing units, and

the omnidirectional image processing device is a wearable device.

4. The method of claim 3 , wherein the processing-target object is a body part of a user wearing the omnidirectional image processing device.

5. The image processing device of claim 1 , wherein the processing-target object is removed from the image, and

an interpolation-target region including the processing-target object is interpolated on the basis of a frame including the processing-target object and/or a frame adjacent to the frame.

6. The method of claim 1 , wherein the interpolation-target region is further interpolated based on at least one reference frame, the interpolation-target region is included in an interpolation-target frame, the at least one reference frame is generated within a threshold time from a time point of the interpolation-target frame, the at least one reference frame includes the reference region corresponding to the interpolation-target region, and the at least one reference frame is determined based on luminance and chrominance information of the reference region.

7. An image processing device for removing a processing-target object from an image, the image processing device comprising:

a communication unit configured to communicate with an external device; and

a processor configured to be operatively connected to the communication unit,

wherein the processor decides the processing-target object in the image and performs image post-processing with respect to the processing-target object, and

the processing-target object is an object which has been unintentionally imaged,

wherein the processing-target object is determined based on at least one condition that the object is imaged when the object is located at a predetermined threshold distance or less from the image processing device,

wherein the processing-target object is determined further based on the at least one condition that the object is in the image for a predetermined time during the image processing device is moved, or the object appears repeatedly in the image during the image processing device is moved,

wherein the processing-target object is removed from the image, and an interpolation-target region including the processing-target object is interpolated on the basis of a frame including the processing-target object and/or a frame adjacent to the frame,

wherein the interpolation-target region is interpolated based on information on pixels located in an outer region of the interpolation-target region, the outer region includes pixels located at a predetermined distance in an opposite direction from a center of the processing-target object, and the information on the pixels of the outer region includes luminance information and chrominance information,

wherein the interpolation-target region is divided as a plurality of interpolation-target sub-regions based on a predetermined threshold degree of change of the luminance information and the chrominance information on the pixels of the outer region.

8. The image processing device of claim 7 , wherein it is determined whether the processing-target object is present in a determination-target region, and

the determination-target region is decided by learning imaging locations of objects which are included in a plurality of images and identical to the processing-target object.

9. The image processing device of claim 8 , wherein the image is an omnidirectional image generated by an omnidirectional image processing device including a plurality of image capturing units, and

the omnidirectional image processing device is a wearable device.

10. The image processing device of claim 9 , wherein the processing-target object is a body part of a user wearing the omnidirectional image processing device.