-
公开(公告)号：US20100220924A1
公开(公告)日：2010-09-02
申请号：US12396380
申请日：2009-03-02
申请人： Gwo Giun Lee , Ming-Jiun Wang , Ling-Hsiu Huang
发明人： Gwo Giun Lee , Ming-Jiun Wang , Ling-Hsiu Huang
IPC分类号： G06K9/00
CPC分类号： G06K9/4652
摘要： A method and system of extracting a perceptual feature set for image/video segmentation are disclosed. An input image is converted to obtain a hue component and a saturation component, where the hue component is quantized into a number of quantum values. After weighting the quantized hue component with the saturation component, the weighted quantized hue component and the saturation component are subjected to a statistical operation in order to extract feature vectors. Accordingly, the method and system provide overall segmentation results that are very close to human interpretation.
摘要翻译： 公开了一种提取图像/视频分割的感知特征集的方法和系统。 输入图像被转换以获得色相分量和饱和分量，其中色调分量被量化为多个量子值。 在用饱和分量对量化的色调分量进行加权之后，对加权的量化色调分量和饱和分量进行统计运算，以便提取特征向量。 因此，该方法和系统提供了非常接近人类解释的整体分割结果。
-
公开(公告)号：US08150150B2
公开(公告)日：2012-04-03
申请号：US12396380
申请日：2009-03-02
申请人： Gwo Giun Lee , Ming-Jiun Wang , Ling-Hsiu Huang
发明人： Gwo Giun Lee , Ming-Jiun Wang , Ling-Hsiu Huang
IPC分类号： G06K9/34
CPC分类号： G06K9/4652
摘要： A method and system of extracting a perceptual feature set for image/video segmentation are disclosed. An input image is converted to obtain a hue component and a saturation component, where the hue component is quantized into a number of quantum values. After weighting the quantized hue component with the saturation component, the weighted quantized hue component and the saturation component are subjected to a statistical operation in order to extract feature vectors. Accordingly, the method and system provide overall segmentation results that are very close to human interpretation.
摘要翻译： 公开了一种提取图像/视频分割的感知特征集的方法和系统。 输入图像被转换以获得色相分量和饱和分量，其中色调分量被量化为多个量子值。 在用饱和分量对量化的色调分量进行加权之后，对加权的量化色调分量和饱和分量进行统计运算，以便提取特征向量。 因此，该方法和系统提供了非常接近人类解释的整体分割结果。
-
公开(公告)号：US20130124593A1
公开(公告)日：2013-05-16
申请号：US13700336
申请日：2011-07-20
申请人： Gwo Giun Lee , He-Yuan Lin
发明人： Gwo Giun Lee , He-Yuan Lin
IPC分类号： G06F17/16
摘要： The quantifying method for intrinsic data transfer rate of algorithms is provided. The provided quantifying method for an intrinsic data transfer rate includes steps of: detecting whether or not a datum is used; providing a dataflow graph G including n vertices and m edges, and a Laplacian matrix L having ixj elements L(i,j) when the datum is not reused, wherein each of the vertices represents one of an operation and a datum, each of the edges represents a data transfer, and vi is the ith vertex; and using the Laplacian matrix L to estimate a maximum quantity of the intrinsic data transfer rate.
摘要翻译： 提供了算法的固有数据传输速率的量化方法。 所提供的固有数据传输速率的量化方法包括以下步骤：检测是否使用数据; 提供包括n个顶点和m个边缘的数据流图G以及当不再使用数据时具有ixj个元素L（i，j）的拉普拉斯矩阵L，其中每个顶点表示操作和基准之一， 边表示数据传输，vi是第i个顶点; 并使用拉普拉斯矩阵L来估计固有数据传输速率的最大数量。
-
4.发明申请METHOD FOR HIGH THROUGHPUT PARALLEL AVC/H.264 CONTEXT-BASED ADAPTIVE BINARY ARITHMETIC CODING DECODER 有权用于高通量并行AVC / H.264基于语境的自适应二进制算术解码器的方法公开(公告)号：US20120293343A1
公开(公告)日：2012-11-22
申请号：US13474106
申请日：2012-05-17
申请人： Gwo Giun Lee , He-Yuan Lin , Jia-Wei Liang , Ching-Jui Hsiao
发明人： Gwo Giun Lee , He-Yuan Lin , Jia-Wei Liang , Ching-Jui Hsiao
IPC分类号： H03M7/34
CPC分类号： H04N19/436 , H04N19/91
摘要： Methods for decoding are provided. The proposed method includes steps of: receiving a most probable symbol (MPS) value and a probability value for generating a probability model update; and receiving the probability model update for generating the MPS value and the probability value, wherein when the probability value shows that an MPS is occurred, a path corresponds to the MPS is estimated and a first bin included in the path is decoded beforehand.
摘要翻译： 提供解码方法。 所提出的方法包括以下步骤：接收最可能的符号（MPS）值和用于生成概率模型更新的概率值; 以及接收用于生成所述MPS值和所述概率值的概率模型更新，其中当所述概率值表示发生MPS时，估计对应于所述MPS的路径，并且预先包含所述路径中包括的第一仓。
-
公开(公告)号：US11379558B2
公开(公告)日：2022-07-05
申请号：US16872371
申请日：2020-05-12
申请人： Gwo Giun Lee , Shih-Yu Chen
发明人： Gwo Giun Lee , Shih-Yu Chen
摘要： The present invention relates to computing-implemented method and system that improves matrix multiplication efficiency, especially to method and system optimizing matrix multiplication using sparse basis approach. Matrices to be multiplied are organized into specially ordered vectors with zero values, facilitates speed up during linear combination computation or synthesis process.
-
公开(公告)号：US20110099330A1
公开(公告)日：2011-04-28
申请号：US11575487
申请日：2005-09-16
申请人： Shaori Guo , Selliah Rathnam , Gwo Giun Lee
发明人： Shaori Guo , Selliah Rathnam , Gwo Giun Lee
IPC分类号： G06F12/08
CPC分类号： H04N19/426 , H04N7/014 , H04N19/433
摘要： Memory storage requirements for digital signal processing operations, for example, motion-compensated video scan rate conversion, that produce intermediate output data, which is then used as an input to the operation, are reduced by reordering operations and organizing memory allocations in a special manner to allow intermediate output at a particular execution time, to substantially share the same memory space as the intermediate output of a previous execution time. Such a reduction in the amount of memory required for processing operations advantageously reduces cost and power consumption.
摘要翻译： 通过重排序操作和以特殊方式组织存储器分配，减少用于数字信号处理操作的存储器存储要求，例如，产生中间输出数据的运动补偿视频扫描速率转换，其被用作操作的输入 以允许在特定执行时间的中间输出基本上共享与先前执行时间的中间输出相同的存储空间。 这种减少处理操作所需的存储量有利地降低了成本和功耗。
-
公开(公告)号：US20210357476A1
公开(公告)日：2021-11-18
申请号：US16872371
申请日：2020-05-12
申请人： Gwo Giun Lee , Shih-Yu Chen
发明人： Gwo Giun Lee , Shih-Yu Chen
摘要： The present invention relates to computing-implemented method and system that improves matrix multiplication efficiency, especially to method and system optimizing matrix multiplication using sparse basis approach. Matrices to be multiplied are organized into specially ordered vectors with zero values, facilitates speed up during linear combination computation or synthesis process.
-
公开(公告)号：US09092384B2
公开(公告)日：2015-07-28
申请号：US13700336
申请日：2011-07-20
申请人： Gwo Giun Lee , He-Yuan Lin
发明人： Gwo Giun Lee , He-Yuan Lin
摘要： The quantifying method for intrinsic data transfer rate of algorithms is provided. The provided quantifying method for an intrinsic data transfer rate includes steps of: detecting whether or not a datum is used; providing a dataflow graph G including n vertices and m edges, and a Laplacian matrix L having ixj elements L(i,j) when the datum is not reused, wherein each of the vertices represents one of an operation and a datum, each of the edges represents a data transfer, and vi is the ith vertex; and using the Laplacian matrix L to estimate a maximum quantity of the intrinsic data transfer rate.
摘要翻译： 提供了算法的固有数据传输速率的量化方法。 所提供的固有数据传输速率的量化方法包括以下步骤：检测是否使用数据; 提供包括n个顶点和m个边缘的数据流图G以及当不再使用数据时具有ixj个元素L（i，j）的拉普拉斯矩阵L，其中每个顶点表示操作和基准之一， 边缘表示数据传输，vi是第i个顶点; 并使用拉普拉斯矩阵L来估计固有数据传输速率的最大数量。
-
9.发明授权Scale changing detection and scaling ratio determination by using motion information 有权通过运动信息确定比例变化检测和缩放比例公开(公告)号：US09087378B2
公开(公告)日：2015-07-21
申请号：US13537086
申请日：2012-06-29
申请人： Chunhui Cui , Chun-Fu Chen , Ciao-Siang Siao , Gwo Giun Lee , Yan Huo
发明人： Chunhui Cui , Chun-Fu Chen , Ciao-Siang Siao , Gwo Giun Lee , Yan Huo
CPC分类号： G06T7/0024 , G06K9/50 , G06K2009/3291 , G06T7/30 , G06T2207/10016 , G06T2207/30236
摘要： This invention discloses a method for object tracking, including determination of an area scaling ratio of the object in a video image sequence. In one embodiment, a centroid of the object is determined. One or more directed straight lines are selected, each passing through the centroid, extending from an end of the object's boundary to an opposite end thereof, and having a direction that is upward. A length scaling ratio for each directed straight line is determined by: determining a motion vector for each selected pixel on the line; computing a scalar component of the motion vector projected onto the line; estimating a change of the line's length according to the scalar components obtained for all pixels; and determining the length scaling ratio according to the change of the line's length. The area scaling ratio is computed based on the length scaling ratios for all directed straight lines.
摘要翻译： 本发明公开了一种用于对象跟踪的方法，包括确定视频图像序列中的对象的区域缩放比例。 在一个实施例中，确定对象的质心。 选择一个或多个指向的直线，每个直线通过质心，从物体边界的一端延伸到其相对端，并具有向上的方向。 每个指向直线的长度缩放比例由下式确定：确定线上每个所选像素的运动矢量; 计算投影到线上的运动矢量的标量分量; 根据为所有像素获得的标量分量来估计行长度的变化; 并根据线长度的变化来确定长度缩放比例。 基于所有指向直线的长度缩放比率来计算面积缩放比例。
-
10.发明授权Method for high throughput parallel AVC/H.264 context-based adaptive binary arithmetic coding decoder 有权高吞吐量并行AVC / H.264基于上下文的自适应二进制算术编码解码器的方法公开(公告)号：US08482440B2
公开(公告)日：2013-07-09
申请号：US13474106
申请日：2012-05-17
申请人： Gwo Giun Lee , He-Yuan Lin , Jia-Wei Liang , Ching-Jui Hsiao
发明人： Gwo Giun Lee , He-Yuan Lin , Jia-Wei Liang , Ching-Jui Hsiao
IPC分类号： H03M7/00
CPC分类号： H04N19/436 , H04N19/91
摘要： Methods for decoding are provided. The proposed method includes steps of: receiving a most probable symbol (MPS) value and a probability value for generating a probability model update; and receiving the probability model update for generating the MPS value and the probability value, wherein when the probability value shows that an MPS is occurred, a path corresponds to the MPS is estimated and a first bin included in the path is decoded beforehand.
摘要翻译： 提供解码方法。 所提出的方法包括以下步骤：接收最可能的符号（MPS）值和用于生成概率模型更新的概率值; 以及接收用于生成所述MPS值和所述概率值的概率模型更新，其中当所述概率值表示发生MPS时，估计对应于所述MPS的路径，并且预先包含所述路径中包括的第一仓。
-
-
-
-
-
-
-
-
-
搜索结果
13 条记录 (耗时 0.02 秒)
