Image processing method
    21.
    发明授权
    Image processing method 有权
    图像处理方法

    公开(公告)号:US08305377B2

    公开(公告)日:2012-11-06

    申请号:US12385625

    申请日:2009-04-14

    IPC分类号: G06T15/00

    CPC分类号: G06T7/12 G06T7/529

    摘要: An image processing method which determines and depth-unfolds a depth folding region in an input depth image. A depth folding region of an input depth image may be determined based on a variance of the input depth, image or a gradient image. A predetermined first depth value may be added to a depth value of each pixel of the determined depth folding region and depth information of the input depth image may be updated.

    摘要翻译: 一种图像处理方法,其确定并深度展开输入深度图像中的深度折叠区域。 可以基于输入深度图像或梯度图像的方差来确定输入深度图像的深度折叠区域。 可以将预定的第一深度值添加到所确定的深度折叠区域的每个像素的深度值,并且可以更新输入深度图像的深度信息。

    Apparatus and method for bidirectionally inpainting occlusion area based on predicted volume
    22.
    发明申请
    Apparatus and method for bidirectionally inpainting occlusion area based on predicted volume 有权
    基于预测体积双向修复闭塞区域的装置和方法

    公开(公告)号:US20120001902A1

    公开(公告)日:2012-01-05

    申请号:US13064785

    申请日:2011-04-14

    IPC分类号: G06T15/00

    摘要: An apparatus and method for bidirectionally inpainting an occlusion area appearing during generation of a virtual viewpoint image, using a foreground area and a background area based on a predicted volume are provided. The method includes receiving an input of a depth image and a color image, the depth image having depth information for a first viewpoint, and the color image having color information for the first viewpoint, generating a virtual viewpoint image at a second viewpoint based on the depth image and the color image, separating the virtual viewpoint image into a foreground area and a background area, based on the depth information and direction information regarding a direction from the first viewpoint to the second viewpoint, predicting a three-dimensional (3D) volume of the foreground area, and inpainting an occlusion area bidirectionally using the foreground area and the background area, based on the predicted 3D volume, the occlusion area being included in the virtual viewpoint image.

    摘要翻译: 提供了使用基于预测体积的前景区域和背景区域来双向地绘制在虚拟视点图像生成期间出现的遮挡区域的装置和方法。 该方法包括接收深度图像和彩色图像的输入,深度图像具有用于第一视点的深度信息,以及具有用于第一视点的颜色信息的彩色图像,基于第二视点生成虚拟视点图像 基于从第一视点到第二视点的方向的深度信息和方向信息,将虚拟视点图像分离成前景区域和背景区域,预测三维(3D)体积 并且基于所预测的3D体积,使用所述前景区域和所述背景区域双向地修复遮挡区域,所述遮挡区域包括在所述虚拟视点图像中。

    Image processing apparatus and method
    23.
    发明申请
    Image processing apparatus and method 有权
    图像处理装置及方法

    公开(公告)号:US20100111446A1

    公开(公告)日:2010-05-06

    申请号:US12453121

    申请日:2009-04-29

    IPC分类号: G06K9/54 G06K9/36

    摘要: An image processing apparatus and method are provided. A control unit may divide input image array data into a plurality of sub-blocks, and a first arithmetic logic unit (ALU) may generate an integral image of at least one of the plurality of sub-blocks. The control unit may determine each of the plurality of sub-blocks to be included in any one of a first sub-block group and a second sub-block group, store the integral image of each sub-block included in the first sub-block group on the first memory, and store the integral image of each sub-block included in the second sub-block group on the second memory.

    摘要翻译: 提供了一种图像处理装置和方法。 控制单元可以将输入图像阵列数据划分成多个子块,并且第一算术逻辑单元(ALU)可以生成多个子块中的至少一个子块的积分图像。 控制单元可以确定要包括在第一子块组和第二子块组中的任何一个中的多个子块中的每一个,存储包括在第一子块组中的每个子块的积分图像 组合在第一存储器上,并将包括在第二子块组中的每个子块的积分图像存储在第二存储器上。

    Image processing method
    24.
    发明申请
    Image processing method 有权
    图像处理方法

    公开(公告)号:US20100097389A1

    公开(公告)日:2010-04-22

    申请号:US12385625

    申请日:2009-04-14

    IPC分类号: G09G5/02

    CPC分类号: G06T7/12 G06T7/529

    摘要: An image processing method which determines and depth-unfolds a depth folding region in an input depth image. A depth folding region of an input depth image may be determined based on a variance of the input depth image, a gradient image, and the like. A predetermined first depth value may be added to a depth value of each pixel of the determined depth folding region and depth information of the input depth image may be updated.

    摘要翻译: 一种图像处理方法,其确定并深度展开输入深度图像中的深度折叠区域。 可以基于输入深度图像,梯度图像等的方差来确定输入深度图像的深度折叠区域。 可以将预定的第一深度值添加到所确定的深度折叠区域的每个像素的深度值,并且可以更新输入深度图像的深度信息。

    Apparatus and method for generating depth image
    27.
    发明申请
    Apparatus and method for generating depth image 有权
    用于产生深度图像的装置和方法

    公开(公告)号:US20120162370A1

    公开(公告)日:2012-06-28

    申请号:US13067390

    申请日:2011-05-27

    IPC分类号: H04N13/02

    摘要: Provided is a depth image generating apparatus. The depth image generating apparatus may include a filtering unit, a modulation unit, and a sensing unit. The filtering unit may band pass filter an infrared light of a first wavelength band among infrared lights received from an object. The modulation unit may modulate the infrared light of the first wavelength band to an infrared light of a second wavelength band. The sensing unit may generate an electrical signal by sensing the modulated infrared light of the second wavelength band.

    摘要翻译: 提供了一种深度图像生成装置。 深度图像生成装置可以包括滤波单元,调制单元和感测单元。 滤波单元可以对从物体接收的红外光中的第一波长带的红外光进行带通滤波。 调制单元可以将第一波长带的红外光调制成第二波长带的红外光。 感测单元可以通过感测第二波长带的调制的红外光来产生电信号。

    Image processing apparatus and method
    28.
    发明授权
    Image processing apparatus and method 有权
    图像处理装置及方法

    公开(公告)号:US08885920B2

    公开(公告)日:2014-11-11

    申请号:US12923452

    申请日:2010-09-22

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00369

    摘要: An image processing apparatus is provided. A silhouette extractor may extract a silhouette image of a target object from an input depth image. A first calculator may determine a location of at least one limb of the target object and a location of at least one joint connecting the at least one limb by applying a rectangle fitting algorithm with respect to the silhouette image.

    摘要翻译: 提供一种图像处理装置。 剪影提取器可以从输入的深度图像中提取目标对象的剪影图像。 第一计算器可以通过对轮廓图像应用矩形拟合算法来确定目标对象的至少一个肢体的位置和连接至少一个肢体的至少一个关节的位置。

    Image processing apparatus, medium, and method
    29.
    发明授权
    Image processing apparatus, medium, and method 有权
    图像处理装置,介质和方法

    公开(公告)号:US08810602B2

    公开(公告)日:2014-08-19

    申请号:US12755615

    申请日:2010-04-07

    IPC分类号: G06T15/00 G06G5/00

    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.

    摘要翻译: 提供了一种图像处理装置,介质和方法。 图像处理装置可以包括第一计算器和第二计算器。 第一计算器可以基于第一帧深度值与第一像素的第一帧深度值之间的获得时间差来计算深度图像的第一像素的第一像素深度值和第一像素的第二帧深度值的第二权重的第一权重, 第一像素的第一像素和第二帧深度值在第一像素的多个帧深度值中。 第二计算器可以使用通过将第一权重应用于第一像素的第一帧深度值而计算的线性和,并且通过将第二权重应用于第二帧深度值来确定第一像素的校正的第一帧深度值 的第一个像素。

    Image processing apparatus and method
    30.
    发明授权
    Image processing apparatus and method 有权
    图像处理装置及方法

    公开(公告)号:US08537155B2

    公开(公告)日:2013-09-17

    申请号:US12662855

    申请日:2010-05-06

    申请人: Hwa Sup Lim

    发明人: Hwa Sup Lim

    IPC分类号: G06T17/00

    摘要: An image processing apparatus. The image processing apparatus may generate a texture by synthesizing a facial area of an input color image and a template texture, generate a mesh model by matching a template mesh model corresponding to the template texture and a depth image corresponding to the input color image, and generate a three-dimensional (3D) facial model based on the texture and the mesh model.

    摘要翻译: 一种图像处理装置。 图像处理装置可以通过合成输入彩色图像和模板纹理的面部区域来生成纹理,通过匹配与模板纹理对应的模板网格模型和与输入彩色图像相对应的深度图像来生成网格模型,以及 基于纹理和网格模型生成三维(3D)面部模型。