专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明申请

US20120155766A1 PATCH DESCRIPTION AND MODELING FOR IMAGE SUBSCENE RECOGNITION 有权
标题翻译：图像描述和图像识别的建模
公开(公告)号：US20120155766A1
公开(公告)日：2012-06-21
申请号：US12972162
申请日：2010-12-17
申请人： Ximin Zhang , Ming-Chang Liu
发明人： Ximin Zhang , Ming-Chang Liu
IPC分类号： G06K9/34 , G06K9/62
CPC分类号： G06K9/00664 , G06F17/30256 , G06K9/4676
摘要： A method and apparatus is described that categorizes images by extracting regions and describing the regions with a set of 15-dimensional image patch feature vectors, which are concatenations of color and texture feature vectors. By comparing the image patch feature vectors in images with similarly-obtained image patch vectors in a Gaussian mixture based model pool (obtained in an image patch modeling phase), the images may be categorized (in an image patch recognition phase) with probabilities relating to each image patch. Higher probabilities are likelier correlations. The device may be a single or multiple core CPU, or parallelized vector processor for characterizing many images. The images may be photographs, videos, or video stills, without restriction. When used real-time, the method may be used for visual searching or sorting.
摘要翻译：描述了一种方法和装置，其通过提取区域并且用一组15维图像贴片特征向量来描述图像，该图像斑块特征向量是颜色和纹理特征向量的连接。通过将图像中的图像块特征向量与基于高斯混合的模型池（在图像块建模阶段中获得）中的类似获得的图像块向量进行比较，可以将图像分类（在图像块识别阶段中），其概率与每个图像补丁。更高的概率是可能的相关性。该设备可以是用于表征许多图像的单个或多个核心CPU或并行化矢量处理器。图像可以是照片，视频或视频静止图像，没有限制。当实时使用时，该方法可用于视觉搜索或排序。

32. 发明申请

US20110222778A1 COLOR AND INTENSITY BASED MEANINGFUL OBJECT OF INTEREST DETECTION 有权
标题翻译：基于颜色和强度的意义敏感的目标检测
公开(公告)号：US20110222778A1
公开(公告)日：2011-09-15
申请号：US12723438
申请日：2010-03-12
申请人： Ximin Zhang , Ming-Chang Liu
发明人： Ximin Zhang , Ming-Chang Liu
IPC分类号： G06K9/46
CPC分类号： G06K9/00664 , G06K9/3241
摘要： An apparatus and method for detecting “Object Portraits” (photographs or images with a stand-out object of interest or a set of stand-out objects of interest) is described. A set of tools has been developed for object of interest detection, including “Sunset-like” scene detection, pseudo-color saturation-based detection and object of interest isolation, block intensity based detection and object of interest isolation. By effectively integrating these tools together, the “Object Portrait” images and “Non-Object Portrait” images are successfully identified. Meaningful object of interest areas are thereby successfully isolated in a low complexity manner without human intervention.
摘要翻译：描述了用于检测“对象肖像”（具有引人注目的对象的感兴趣的对象或一组待排除的对象的照片或图像）的装置和方法。已经开发了一套工具，用于感兴趣的检测对象，包括“日落样”场景检测，基于伪彩色饱和的检测和感兴趣的对象隔离，基于块强度的检测和感兴趣的对象隔离。通过有效地将这些工具集成在一起，“对象人像”图像和“非对象肖像”图像被成功识别。因此，有意义的利益领域的对象在没有人为干预的情况下以低复杂度方式被成功隔离。

33. 发明申请

US20100321531A1 SYSTEM AND METHOD FOR IMAGE QUALITY ENHANCEMENT BY REDUCING THE EFFECTS OF AIR POLLUTION AND HAZE 失效
标题翻译：降低空气污染和危害的影响的图像质量提高的系统和方法
公开(公告)号：US20100321531A1
公开(公告)日：2010-12-23
申请号：US12486519
申请日：2009-06-17
申请人： Ximin Zhang , Ming-Chang Liu
发明人： Ximin Zhang , Ming-Chang Liu
IPC分类号： H04N9/68 , G06K9/00
CPC分类号： G06T5/008
摘要： A low cost image quality enhancement method to be utilized in an ordinary consumer camera and for post processing of an existing image database is described herein. The quality enhancement is transferred into an adaptive intensity stretching process in the YUV domain. A different enhancement process is designed for a luminance (Y) channel and chrominance (UV) channel. The parameters in the enhancement process are estimated based on the contents of the image. After the stretching-based enhancement, an adaptive unsharp masking process is applied to the luminance data. The quality is significantly improved for the images shot under unfavorable conditions.
摘要翻译：这里描述了在普通消费者相机中使用的低成本图像质量增强方法和用于对现有图像数据库进行后处理的方法。质量增强转移到YUV域中的自适应强度拉伸过程。为亮度（Y）通道和色度（UV）通道设计了不同的增强过程。基于图像的内容来估计增强处理中的参数。在基于拉伸的增强之后，对亮度数据应用自适应锐化掩蔽处理。在不利条件下拍摄的图像质量明显提高。

34. 发明申请

US20090180532A1 Picture mode selection for video transcoding 失效
标题翻译：视频转码的图像模式选择
公开(公告)号：US20090180532A1
公开(公告)日：2009-07-16
申请号：US12009054
申请日：2008-01-15
申请人： Ximin Zhang , Ming-Chang Liu
发明人： Ximin Zhang , Ming-Chang Liu
IPC分类号： H04B1/66
CPC分类号： H04N19/103 , H04N19/139 , H04N19/14 , H04N19/16 , H04N19/176 , H04N19/40 , H04N19/61
摘要： An adaptive picture mode selection transcoder selects an encoding mode in a second format for frames of video previously encoded in a first format by determining a magnitude of interlacing phenomenon in the using picture information obtained during decoding of the video from the first format. In one aspect, the picture information includes discrete cosine coefficients for macroblocks in the frame. In another aspect, the picture information includes an encoding mode for the macroblocks in the first format. In yet another aspect, the picture information includes motion vector information for the macroblocks. In still another aspect, the determining is specific to an encoding mode for the frame.
摘要翻译：自适应图像模式选择代码转换器通过确定在从第一格式的视频解码期间获得的使用图像信息中的交织现象的大小来选择第二格式的用于以第一格式预编码的视频帧的编码模式。在一个方面，图像信息包括用于该帧中的宏块的离散余弦系数。在另一方面，图像信息包括用于第一格式的宏块的编码模式。在另一方面，图像信息包括用于宏块的运动矢量信息。在另一方面，该确定特定于该帧的编码模式。

35. 发明申请

US20080165852A1 VIDEO CODING SYSTEM 有权
标题翻译：视频编码系统
公开(公告)号：US20080165852A1
公开(公告)日：2008-07-10
申请号：US11620598
申请日：2007-01-05
申请人： Ximin Zhang
发明人： Ximin Zhang
IPC分类号： H04N7/12
CPC分类号： H04N19/17 , H04N19/124 , H04N19/139 , H04N19/159 , H04N19/176 , H04N19/177 , H04N19/513 , H04N19/61
摘要： A video coding system is provided including generating a motion vector for a macro block in a picture, the motion vectors indicative of displacement of an object in the macro block; grouping a cluster of the motion vectors; and adjusting a dynamic quantization parameter modulation of a subsequent picture based on the grouping for displaying the displacement of the object in the subsequent picture.
摘要翻译：提供了一种视频编码系统，包括生成图像中的宏块的运动矢量，指示宏块中的对象的位移的运动矢量; 对一组运动矢量进行分组; 以及基于用于显示随后图像中的对象的位移的分组来调整后续图像的动态量化参数调制。

36. 发明授权

US10499063B2 Method and apparatus for prediction mode and partition mode syntax coding for coding units in HEVC 有权
公开(公告)号：US10499063B2
公开(公告)日：2019-12-03
申请号：US14342357
申请日：2012-08-29
申请人： Ximin Zhang , Shan Liu
发明人： Ximin Zhang , Shan Liu
IPC分类号： H04N19/157 , H04N19/159 , H04N19/70 , H04N19/13 , H04N19/174
CPC分类号： H04N19/159 , H04N19/13 , H04N19/174 , H04N19/70
摘要： A method and apparatus for coding of syntax elements are disclosed to allow prediction units in P and B slices to share the same syntax coding table. In one embodiment according to the present invention, the method and apparatus coding of syntax elements selectively apply a syntax coding table to encode or decode the syntax element associated with the partition mode of a coding unit of a picture region according to the slice type of the picture region. A first syntax coding table is used to process the syntax element if the slice type is an I mode and a second syntax coding table is used to process the syntax element if the slice type is not an I mode.

37. 发明授权

US09560347B2 Method and system of transform block processing according to quantization matrix in video coding 有权
标题翻译：根据视频编码中的量化矩阵进行变换块处理的方法和系统
公开(公告)号：US09560347B2
公开(公告)日：2017-01-31
申请号：US14234505
申请日：2012-08-21
申请人： Ximin Zhang , Shan Liu
发明人： Ximin Zhang , Shan Liu
IPC分类号： H04B1/66 , G06K9/36 , H04N19/122 , H04N19/124 , H04N19/115 , H04N7/26 , H04N11/02 , G06K9/32 , H04N19/196 , H04N19/176 , H04N19/70 , H04N19/60 , H04N19/126 , H04N19/18 , H04N19/80
CPC分类号： H04N19/126 , H04N19/122 , H04N19/176 , H04N19/18 , H04N19/197 , H04N19/198 , H04N19/60 , H04N19/70 , H04N19/80
摘要： A method and system process transform blocks according to quantization matrices in a video coding system. Embodiments of the present invention derive one or more derived quantization matrices from one or more initial quantization matrices or from one previously derived quantization matrix. In one embodiment, the initial quantization matrices include a 4×4 and 8×8 quantization matrices, which can be either default or user-defined. All quantization matrices larger than 8×8 can be derived from the 4×4 and 8×8 initial quantization matrices. Non-square quantization matrices can be derived from at least one initial square quantization matrix or at least one derived square quantization matrix. Individual initial quantization matrices may be used to derive respective larger quantization matrices. Furthermore, the individual initial quantization matrices may be derived from larger quantization matrices designed for corresponding transform sizes. Syntax design also enables the quantization matrix representation.
摘要翻译：一种方法和系统处理根据视频编码系统中的量化矩阵来变换块。本发明的实施例从一个或多个初始量化矩阵或从一个先前导出的量化矩阵导出一个或多个导出的量化矩阵。在一个实施例中，初始量化矩阵包括4×4和8×8个量化矩阵，其可以是默认的或用户定义的。大于8×8的所有量化矩阵可以从4×4和8×8个初始量化矩阵导出。可以从至少一个初始平方量化矩阵或至少一个导出的平方量化矩阵导出非平方量化矩阵。各个初始量化矩阵可以用于导出相应较大的量化矩阵。此外，各个初始量化矩阵可以从为相应的变换大小设计的较大的量化矩阵导出。语法设计还支持量化矩阵表示。

38. 发明申请

US20140211850A1 METHOD AND APPARATUS FOR PREDICTION MODE AND PARTITION MODE SYNTAX CODIND FOR CODING UNITS IN HEVC 审中-公开
标题翻译：用于HEVC中编码单元的预测模式和分割模式语法编码的方法和装置
公开(公告)号：US20140211850A1
公开(公告)日：2014-07-31
申请号：US14342357
申请日：2012-08-29
申请人： Ximin Zhang , Shan Liu
发明人： Ximin Zhang , Shan Liu
IPC分类号： H04N19/157 , H04N19/66 , H04N19/169 , H04N19/174
CPC分类号： H04N19/159 , H04N19/13 , H04N19/174 , H04N19/70
摘要： A method and apparatus for coding of syntax elements are disclosed to allow prediction units in P and B slices to share the same syntax coding table. In one embodiment according to the present invention, the method and apparatus coding of syntax elements selectively apply a syntax coding table to encode or decode the syntax element associated with the partition mode of a coding unit of a picture region according to the slice type of the picture region. A first syntax coding table is used to process the syntax element if the slice type is an I mode and a second syntax coding table is used to process the syntax element if the slice type is not an I mode.
摘要翻译：公开了用于编码语法元素的方法和装置，以允许P和B片段中的预测单元共享相同的语法编码表。在根据本发明的一个实施例中，语法元素的方法和装置编码选择性地应用语法编码表，以根据图像区域的切片类型来编码或解码与图像区域的编码单元的分割模式相关联的语法元素图片区域。如果片类型是I模式，则第一语法编码表用于处理语法元素，并且如果片类型不是I模式，则使用第二语法编码表来处理语法元素。

39. 发明申请

US20130216134A1 System And Method For Effectively Performing A Scene Representation Procedure 有权
标题翻译：有效执行场景表示过程的系统和方法
公开(公告)号：US20130216134A1
公开(公告)日：2013-08-22
申请号：US13398948
申请日：2012-02-17
申请人： Liangyin Yu , Ming-Chang Liu , Ximin Zhang
发明人： Liangyin Yu , Ming-Chang Liu , Ximin Zhang
IPC分类号： G06K9/34
CPC分类号： G06K9/00718 , G06K9/469
摘要： A system for performing a scene representation procedure includes an image manager that processes source images from a given scene to define subscenes in the source images. The image manager creates an image understanding graph for each of the source images, and also creates a scene representation graph for each of the source images based upon the corresponding subscenes and certain image characteristics. The image manager further generates an integrated scene representation to represent all of the source images with a single representation. A processor of an electronic device controls the image manager to perform the scene representation procedure.
摘要翻译：用于执行场景表示过程的系统包括图像管理器，其处理来自给定场景的源图像以在源图像中定义子信号。图像管理器为每个源图像创建图像理解图，并且还基于相应的子像素和某些图像特征为每个源图像创建场景表示图。图像管理器进一步生成集成的场景表示以用单个表示来表示所有源图像。电子设备的处理器控制图像管理器执行场景表示过程。

40. 发明授权

US08503768B2 Shape description and modeling for image subscene recognition 有权
标题翻译：形象描述和建模图像子叶识别
公开(公告)号：US08503768B2
公开(公告)日：2013-08-06
申请号：US12975950
申请日：2010-12-22
申请人： Ximin Zhang , Ming-Chang Liu
发明人： Ximin Zhang , Ming-Chang Liu
IPC分类号： G06K9/62
CPC分类号： G06K9/00684 , G06K9/4642 , G06K9/4676 , G06K9/48
摘要： A method and apparatus is described here that categorizes images by extracting a subscene and describing the subscene with a top level feature vector and a division feature vector, which are descriptions of edge gradient classifications within rectangular bounding boxes. By filtering subscene feature vectors in images with a Gaussian mixture based model pool (obtained in a subscene modeling phase), the images may be categorized (in an subscene recognition phase) with probabilities relating to each subscene. Higher probabilities are likelier correlations. The device may be a single or multiple core CPU, or parallelized vector processor for characterizing many images. The images may be photographs, videos, or video stills, without restriction. When used real-time, the method may be used for visual searching or sorting.
摘要翻译：这里描述了一种方法和装置，其通过提取一个子序列并用顶层特征向量和分割特征向量来描述该次序，从而对图像进行分类，这是在矩形边界框内的边缘梯度分类的描述。通过使用基于高斯混合的模型池（在亚视觉建模阶段获得），在图像中过滤子图像特征向量，可以将图像分类（在子序列识别阶段），其具有与每个亚素相关的概率。更高的概率是可能的相关性。该设备可以是用于表征许多图像的单个或多个核心CPU或并行化矢量处理器。图像可以是照片，视频或视频静止图像，没有限制。当实时使用时，该方法可用于视觉搜索或排序。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式