-
公开(公告)号:US08249369B2
公开(公告)日:2012-08-21
申请号:US12367032
申请日:2009-02-06
申请人: Liang-Gee Chen , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Homer H. Chen , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Homer H. Chen , Ling-Hsiu Huang
IPC分类号: G06K9/36
CPC分类号: G06K9/4638
摘要: A method and apparatus of tile-based belief propagation are disclosed. An image is split into a number of tiles. Messages are iteratively generated within each of the tiles based on the messages from neighboring pixels to the tile at a previous iteration, wherein each message represents information of a state of the pixel. The generated messages for sending out of the tiles are stored. Labels are then determined based on the stored messages, wherein each label represents the state of the pixel.
摘要翻译: 公开了一种基于瓦片的信念传播的方法和装置。 图像被分割成多个图块。 基于在先前迭代的来自相邻像素到瓦片的消息,在每个瓦片内迭代地生成消息,其中每个消息表示像素的状态的信息。 生成的用于发送出瓦片的消息被存储。 然后基于存储的消息确定标签,其中每个标签表示像素的状态。
-
公开(公告)号:US20100135585A1
公开(公告)日:2010-06-03
申请号:US12367032
申请日:2009-02-06
申请人: Liang-Gee Chen , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Homer H. Chen , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Homer H. Chen , Ling-Hsiu Huang
IPC分类号: G06K9/68
CPC分类号: G06K9/4638
摘要: A method and apparatus of tile-based belief propagation are disclosed. An image is split into a number of tiles. Messages are iteratively generated within each of the tiles based on the messages from neighboring pixels to the tile at a previous iteration, wherein each message represents information of a state of the pixel. The generated messages for sending out of the tiles are stored. Labels are then determined based on the stored messages, wherein each label represents the state of the pixel.
摘要翻译: 公开了一种基于瓦片的信念传播的方法和装置。 图像被分割成多个图块。 基于在先前迭代的来自相邻像素到瓦片的消息,在每个瓦片内迭代地生成消息,其中每个消息表示像素的状态的信息。 生成的用于发送出瓦片的消息被存储。 然后基于存储的消息确定标签,其中每个标签表示像素的状态。
-
公开(公告)号:US20110285701A1
公开(公告)日:2011-11-24
申请号:US13118526
申请日:2011-05-30
申请人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Ling-Hsiu Huang
CPC分类号: G06K9/4638 , G06T7/97 , G06T2207/10012 , G06T2207/20076 , G06T2207/20228 , H04N13/111 , H04N13/271 , H04N2013/0081
摘要: In accordance with at least some embodiments of the present disclosure, a processor for performing stereo matching of a first image and a second image is described. The processor may include a first pipeline stage configured to generate data costs associated with a first tile selected from the first image, wherein the data costs is generated based on pixels in the first tile and corresponding pixels in the second image. The processor may include a second pipeline stage configured to generate disparity values associated with the first tile and an outbound message from the first tile to one of neighboring tiles in the first image, wherein the disparity values and the outbound message are generated based on the data costs and inbound messages from the neighboring tiles to the first tile. The processor may further include a third pipeline stage configured to store the disparity values and the outbound message in a memory, wherein the outbound message is used by the second pipeline stage as one of the inbound messages during processing of a second tile selected from the first image.
摘要翻译: 根据本公开的至少一些实施例,描述了用于执行第一图像和第二图像的立体匹配的处理器。 处理器可以包括被配置为生成与从第一图像中选择的第一图块相关联的数据成本的第一流水线阶段,其中基于第一图块中的像素和第二图像中的对应像素生成数据成本。 处理器可以包括第二流水线级,其被配置为产生与第一瓦片相关联的视差值,以及从第一瓦片到第一图像中的相邻瓦片之一的出站消息,其中基于数据生成视差值和出站消息 成本和从邻近瓦片到第一瓦片的入站邮件。 处理器可以进一步包括第三流水线级,其被配置为将存储器中的视差值和出站消息存储在存储器中,其中出站消息由第二流水线级用作处理从第一流 图片。
-
公开(公告)号:US08761491B2
公开(公告)日:2014-06-24
申请号:US13118526
申请日:2011-05-30
申请人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Chia-Kai Liang , Yen-Chieh Lai , Ling-Hsiu Huang
IPC分类号: G06K9/00
CPC分类号: G06K9/4638 , G06T7/97 , G06T2207/10012 , G06T2207/20076 , G06T2207/20228 , H04N13/111 , H04N13/271 , H04N2013/0081
摘要: In accordance with at least some embodiments of the present disclosure, a processor for performing stereo matching of a first image and a second image is described. The processor may include a first pipeline stage configured to generate data costs associated with a first tile selected from the first image, wherein the data costs is generated based on pixels in the first tile and corresponding pixels in the second image. The processor may include a second pipeline stage configured to generate disparity values associated with the first tile and an outbound message from the first tile to one of neighboring tiles in the first image, wherein the disparity values and the outbound message are generated based on the data costs and inbound messages from the neighboring tiles to the first tile. The processor may further include a third pipeline stage configured to store the disparity values and the outbound message in a memory, wherein the outbound message is used by the second pipeline stage as one of the inbound messages during processing of a second tile selected from the first image.
摘要翻译: 根据本公开的至少一些实施例,描述了用于执行第一图像和第二图像的立体匹配的处理器。 处理器可以包括被配置为生成与从第一图像中选择的第一图块相关联的数据成本的第一流水线阶段,其中基于第一图块中的像素和第二图像中的对应像素生成数据成本。 处理器可以包括第二流水线级,其被配置为产生与第一瓦片相关联的视差值,以及从第一瓦片到第一图像中的相邻瓦片之一的出站消息,其中基于数据生成视差值和出站消息 成本和从邻近瓦片到第一瓦片的入站邮件。 处理器可以进一步包括第三流水线级,其被配置为将存储器中的视差值和出站消息存储在存储器中,其中出站消息由第二流水线级用作处理从第一流 图片。
-
公开(公告)号:US09007435B2
公开(公告)日:2015-04-14
申请号:US13109310
申请日:2011-05-17
CPC分类号: G06T15/205 , G06T5/003 , G06T2207/20012 , G06T2207/20192
摘要: An example process to enhance a two-dimensional (2D) image may include generating a depth map for the 2D image based on edges detected from the 2D image, wherein the depth map can be used to convert the 2D image to a 3D image. The process may further include enhancing the 2D image using the depth map.
摘要翻译: 用于增强二维(2D)图像的示例性过程可以包括基于从2D图像检测到的边缘生成2D图像的深度图,其中可以使用深度图将2D图像转换为3D图像。 该过程还可以包括使用深度图增强2D图像。
-
公开(公告)号:US20120293615A1
公开(公告)日:2012-11-22
申请号:US13109310
申请日:2011-05-17
CPC分类号: G06T15/205 , G06T5/003 , G06T2207/20012 , G06T2207/20192
摘要: In accordance with at least some embodiments of the present disclosure, a process for enhancing a two-dimensional (2D) image is described. The process may include generating a depth map for the 2D image based on edges detected from the 2D image, wherein the depth map can be used to convert the 2D image to a 3D image. The process may further include enhancing the 2D image using the depth map.
摘要翻译: 根据本公开的至少一些实施例,描述了用于增强二维(2D)图像的过程。 该过程可以包括基于从2D图像检测到的边缘来生成2D图像的深度图,其中可以使用深度图将2D图像转换为3D图像。 该过程还可以包括使用深度图增强2D图像。
-
公开(公告)号:US08655054B2
公开(公告)日:2014-02-18
申请号:US13226317
申请日:2011-09-06
申请人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Yen-Chieh Lai , Chien Wu , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Yen-Chieh Lai , Chien Wu , Ling-Hsiu Huang
CPC分类号: G06T5/002 , G06K9/00201 , G06K9/469 , G06K9/52 , G06T2207/20028 , G06T2207/20192
摘要: A system and method of correcting a depth map for 3D image is disclosed. A spatial spectral transform unit extracts pixels of object boundaries according to an input image, wherein the spatial spectral transform unit adopts Hilbert-Huang transform (HHT). A correction unit corrects an input depth map corresponding to the input image according to the pixels of object boundaries, thereby resulting in an output depth map.
摘要翻译: 公开了一种用于校正3D图像的深度图的系统和方法。 空间光谱变换单元根据输入图像提取对象边界的像素,其中空间光谱变换单元采用希尔伯特 - 黄变换(HHT)。 校正单元根据对象边界的像素校正与输入图像对应的输入深度图,从而得到输出深度图。
-
公开(公告)号:US08629901B2
公开(公告)日:2014-01-14
申请号:US13111843
申请日:2011-05-19
申请人: Liang-Gee Chen , Chien Wu , Chung-Te Li , Yen-Chieh Lai , Chao-Chung Cheng , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chien Wu , Chung-Te Li , Yen-Chieh Lai , Chao-Chung Cheng , Ling-Hsiu Huang
IPC分类号: H04N13/02
CPC分类号: H04N13/128
摘要: A method of revising depth of a three-dimensional (3D) image is disclosed. The method comprises the following steps: firstly, at least one initial depth map associated with one image of the 3D image pair based on stereo matching technique is received, wherein the one image comprises a plurality of pixels, and the initial depth map carries an initial depth value of each pixel. Then, the inconsistence among the pixels of the one image of the 3D image pair is detected to estimate a reliable map. Finally, the initial depth value is interpolated according to the reliable map and the proximate pixels, so as to generate a revised depth map by revising the initial depth value.
摘要翻译: 公开了修改三维(3D)图像深度的方法。 该方法包括以下步骤:首先,接收与基于立体匹配技术的3D图像对的一个图像相关联的至少一个初始深度图,其中一个图像包括多个像素,并且初始深度图携带初始 每个像素的深度值。 然后,检测3D图像对的一个图像的像素之间的不一致性,以估计可靠的图。 最后,根据可靠的地图和邻近像素对初始深度值进行插值,以便通过修改初始深度值来生成修正的深度图。
-
公开(公告)号:US20100080481A1
公开(公告)日:2010-04-01
申请号:US12242650
申请日:2008-09-30
申请人: Liang-Gee Chen , Chao-Chung Cheng , Chung-Te Li , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chao-Chung Cheng , Chung-Te Li , Ling-Hsiu Huang
CPC分类号: G06T7/529
摘要: A system of generating three-dimensional (3D) depth information is disclosed. A color and object independent local blurriness estimation unit analyzes blurriness of each pixel of a two-dimensional (2D) image. Subsequently, a depth assignment unit assigns depth information to the 2D image according to the analyzed blurriness.
摘要翻译: 公开了一种产生三维(3D)深度信息的系统。 颜色和对象独立的局部模糊估计单元分析二维(2D)图像的每个像素的模糊度。 随后,深度分配单元根据分析的模糊度将深度信息分配给2D图像。
-
公开(公告)号:US20130071008A1
公开(公告)日:2013-03-21
申请号:US13233048
申请日:2011-09-15
申请人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Ling-Hsiu Huang
发明人: Liang-Gee Chen , Chung-Te Li , Chao-Chung Cheng , Ling-Hsiu Huang
IPC分类号: G06K9/00
CPC分类号: G06T7/50 , G06T2207/20072 , H04N13/261 , H04N13/271
摘要: In accordance with at least some embodiments of the present disclosure, a process for converting a two-dimensional (2D) image based on edge information is described. The process may include partitioning the 2D image to generate a plurality of blocks, segmenting the plurality of blocks into a group of regions based on edges determined in the plurality of blocks, assigning depth values to the plurality of blocks based on a depth gradient hypothesis associated with the group of regions, wherein pixels in each of the plurality of blocks are associated with a same depth value, and generating the depth map based on the depth values of the plurality of blocks.
摘要翻译: 根据本公开的至少一些实施例,描述了用于基于边缘信息转换二维(2D)图像的处理。 该过程可以包括划分2D图像以生成多个块,基于在多个块中确定的边缘将多个块分割成一组区域,基于相关的深度梯度假设向多个块分配深度值 与所述一组区域相关联,其中所述多个块中的每一个中的像素与相同的深度值相关联,并且基于所述多个块的深度值生成所述深度图。
-
-
-
-
-
-
-
-
-