摘要:
An image processing apparatus may detect an occlusion boundary between objects within an input depth image by applying an edge detection algorithm to the input depth image. The image processing apparatus may classify the occlusion boundary into a foreground region boundary and a background region boundary using a depth gradient vector direction of the occlusion boundary, and may extract an occlusion region of the input depth image using the foreground region boundary.
摘要:
An image generating apparatus may include a first reflector and a second reflector. When a light emitter emits an infrared light, the infrared light may be reflected from a first reflector and be omni-directionally reflected. The reflected infrared light that is the infrared light reflected from the object may be reflected from a second reflector and be transferred to a sensor. The sensor may receive the reflected infrared light and generate a depth image of the object.
摘要:
A method and apparatus for temporally interpolating a three-dimensional (3D) depth image are provided to generate an intermediate depth image in a desired time. The apparatus may interpolate depth images generated by a depth camera, using a temporal interpolation procedure, may generate an intermediate depth image in a new time using the interpolated depth images, and may combine the generated intermediate depth image with color images, to generate a high-precision 3D image.
摘要:
A first calculator of an image processing apparatus may trace a view transform vector between color images of different frames. A second calculator may trace a view transform vector between depth images of different frames. In this example, a third calculator may calculate a view transform vector between the color camera and the depth camera using the view transform vector between the color images and the view transform vector between the depth images.
摘要:
The present invention relates to a method of matching a color image and depth image using feature points corresponding to each other. An image processing method, including: selecting a first pixel group including at least one pixel from an input color image; selecting a second pixel group including at least one pixel corresponding to each of the at least one pixel included in the first pixel group from an input depth image; calculating a transformation function of the first pixel group and second pixel group based on a coordinate value of each of the at least one pixel included in the first pixel group and a coordinate value of each of the at least one pixel included in the second pixel group; and matching each pixel of the input color image with each pixel of the input depth image based on the transformation function. Image processing apparatus, including: a first selection unit selecting a first pixel group including at least one pixel from an input color image; a second selection unit selecting a second pixel group including at least one pixel corresponding to each of the at least one pixel included in the first pixel group from an input depth image; a calculation unit calculating a transformation function of the first pixel group and second pixel group based on a coordinate value of each of the at least one pixel included in the first pixel group and a coordinate value of each of the at least one pixel included in the second pixel group; and an image matching unit matching each pixel of the input color image with each pixel of the input depth image based on the transformation function.
摘要:
Provided is an image processing apparatus, medium, and method. The image processing apparatus may include a first calculator and a second calculator. The first calculator may calculate a first weight of a first frame depth value of a first pixel of a depth image and a second weight of a second frame depth value of the first pixel, based on an obtainment time difference between the first frame depth value of the first pixel and the second frame depth value of the first pixel among a plurality of frame depth values of the first pixel. The second calculator may determine a corrected first frame depth value of the first pixel using a linear sum that is calculated by applying the first weight to the first frame depth value of the first pixel, and by applying the second weight to the second frame depth value of the first pixel.
摘要:
An apparatus and method for generating a skeleton model using motion data and image data. The apparatus for generating the skeleton model may synchronize the image data and the motion data, and generate a three-dimensional (3D) skeleton model of an entire body of a user using a silhouette extracted from the image data and also using a position or orientation of a joint of the user extracted from the motion data. The skeleton model may be generated using the image data and the motion data, thereby improving accuracy of the skeleton model of the entire body of the user.
摘要:
A method of determining a ground line from an input image. The method includes determining a plurality of ground line candidates from the image, determining a certain band a central-line of which is a boundary between a G region and other regions in a Ground Building Sky (GBS) map of the image, and determining the ground line of the image by selecting a ground line candidate, among the plurality of ground line candidates, having the greatest extent crossing the certain band.