-
公开(公告)号：US08705857B2
公开(公告)日：2014-04-22
申请号：US13572198
申请日：2012-08-10
IPC分类号： G06K9/00
CPC分类号： H04N9/646
摘要： An image processing system and method corrects the perceptual quality of an image by adjusting the image colors. “Color” in this sense is to be understood as encompassing three-dimensional parameterizations of color, incorporating both intensity and hue. These measurements are made using creative computations developed and adapted from the RETINEX™ theory (Land, 1977), where the RETINEX implementation adjusts any pixel in any direction in color space and further to automatically determine the best direction for it to be adjusted to increase the perceptual visibility of the algorithm with a minimal amount of change to the original image values.
摘要翻译： 图像处理系统和方法通过调整图像颜色来校正图像的感知质量。 在这个意义上说，“颜色”应被理解为包含颜色的三维参数化，包括强度和色相。 这些测量是使用RETINEX™理论（Land，1977）开发和改编的创意计算进行的，其中RETINEX实现调整颜色空间中任何方向的任何像素，并进一步自动确定调整其最佳方向以增加 具有对原始图像值的最小量变化的算法的感知可见性。
-
2.发明授权公开(公告)号：US08521659B2
公开(公告)日：2013-08-27
申请号：US12541857
申请日：2009-08-14
CPC分类号： G06N99/005 , G06K9/6226 , G06K9/6254
摘要： Discovering mixtures of models includes: initiating learning algorithms, determining, data sets including a cluster of points in a first region of a domain and a set of points distributed near a first line extending across the domain; inferencing parameters from the cluster and the set of points; creating a description of the cluster of points in the first region of the domain and computing approximations of a first learned mixture model and a second learned mixture model; determining a first and second probability, generating a confidence rating that each point of the cluster of points in the first region of the domain corresponds to the first learned mixture model and generating a confidence rating that each point of the set of points distributed near the first line correspond to the second learned mixture model, thus causing determinations of behavior of a system described by the learned mixture models.
摘要翻译： 发现模型的混合包括：启动学习算法，确定包括域的第一区域中的点集合和分布在跨域延伸的第一行附近的一组点的数据集; 从集群推导参数和集合点; 创建域的第一区域中的点集合的描述，并计算第一学习混合模型和第二学习混合模型的近似值; 确定第一和第二概率，产生置信度等级，所述域的所述第一区域中的所述聚类点的每个点对应于所述第一学习混合模型，并且生成置信度等级，所述置信区间中的每个点分布在第一 线对应于第二个学习混合模型，从而导致由所学习的混合模型描述的系统的行为的确定。
-
公开(公告)号：US08477147B2
公开(公告)日：2013-07-02
申请号：US12416716
申请日：2009-04-01
IPC分类号： G09G5/00
CPC分类号： G06K9/00275 , G06K9/00281 , G06K9/4609 , G06K9/469
摘要： Methods and systems of representation and manipulation of surfaces with perceptual geometric features, using a computer graphics rendering system, include executing algorithmic instructions to compute a plurality of vertices, edges and surfaces in a mesh for the purpose of defining representations of surfaces on grids. Normals and distances are determined for triangular surfaces to be considered. Additionally, height fields of a function are defined. A set of feature curves and a set of feature points are determined, based on the defined function. Infinitesimal movements along the representations of the surfaces are determined, along with determinations of properties of representations of continuous surfaces. Additional determinations of perceptual geometric features include determinations such as zero crossings, parabolic curves, flecnodes, ruffles, gutterpoints, conical points and biflecnodes in a given mesh. After these determinations are made, visual representations are rendered which capture perceptually important features for smoothly varying shapes.
摘要翻译： 使用计算机图形绘制系统来表示和操纵具有感知几何特征的表面的方法和系统包括执行算法指令以计算网格中的多个顶点，边缘和表面，以定义网格表面的表示。 确定要考虑的三角形表面的法线和距离。 另外，定义了一个函数的高度域。 基于定义的功能确定一组特征曲线和一组特征点。 确定沿着表面的表示的无限小的运动以及连续表面的表示的性质的确定。 感知几何特征的附加测定包括给定网格中的过零点，抛物线曲线，点阵，褶边，沟槽点，圆锥点和双点定位等确定。 在进行这些确定之后，渲染视觉表示，捕获感知重要的特征，以便平滑变化的形状。
-
4.发明授权
公开(公告)号：US5870136A
公开(公告)日：1999-02-09
申请号：US986309
申请日：1997-12-05
CPC分类号： H04N13/0207 , G01S5/16 , G06T7/0044 , H04N13/0253 , H04N5/222 , H04N5/2224 , G06T2207/10016 , G06T2207/10024 , G06T2207/30244 , H04N2013/0081
摘要： Methods, systems and computer products are provided for tracking objects within a scene using imperceptible structured light. The imperceptible structured light may be used in environments where humans work and therefore avoids disorienting observers. The structured light patterns are generated dynamically, allowing tracking without physical landmarks. Moreover, the occlusion of the generated landmarks is overcome by determining the position of objects using a determined camera position. The imperceptible structured light may be used in systems without tracking. The tracking may be used without imperceptible structured light.
摘要翻译： 提供了方法，系统和计算机产品，用于使用不可察觉的结构光跟踪场景内的物体。 不可察觉的结构光可以用于人类工作的环境中，从而避免观察者迷失方向。 结构化光图案是动态生成的，允许在没有物理地标的情况下进行跟踪。 此外，通过使用确定的相机位置确定对象的位置来克服生成的地标的遮挡。 不可察觉的结构光可以用于没有跟踪的系统中。 跟踪可以在没有不可察觉的结构光的情况下使用。
-
5.发明申请公开(公告)号：US20100042563A1
公开(公告)日：2010-02-18
申请号：US12541857
申请日：2009-08-14
CPC分类号： G06N99/005 , G06K9/6226 , G06K9/6254
摘要： Discovering mixtures of models includes: initiating learning algorithms, determining, data sets including a cluster of points in a first region of a domain and a set of points distributed near a first line extending across the domain; inferencing parameters from the cluster and the set of points; creating a description of the cluster of points in the first region of the domain and computing approximations of a first learned mixture model and a second learned mixture model; determining a first and second probability, generating a confidence rating that each point of the cluster of points in the first region of the domain corresponds to the first learned mixture model and generating a confidence rating that each point of the set of points distributed near the first line correspond to the second learned mixture model, thus causing determinations of behavior of a system described by the learned mixture models.
摘要翻译： 发现模型的混合包括：启动学习算法，确定包括域的第一区域中的点集合和分布在跨域延伸的第一行附近的一组点的数据集; 从集群推导参数和集合点; 创建域的第一区域中的点集合的描述，并计算第一学习混合模型和第二学习混合模型的近似值; 确定第一和第二概率，产生置信度等级，所述域的所述第一区域中的所述聚类点的每个点对应于所述第一学习混合模型，并且生成置信度等级，所述置信区间中的每个点分布在第一 线对应于第二个学习混合模型，从而导致由所学习的混合模型描述的系统的行为的确定。
-
公开(公告)号：US20130039575A1
公开(公告)日：2013-02-14
申请号：US13572198
申请日：2012-08-10
IPC分类号： G06K9/00
CPC分类号： H04N9/646
摘要： An image processing system and method corrects the perceptual quality of an image by adjusting the image colors. “Color” in this sense is to be understood as encompassing three-dimensional parameterizations of color, incorporating both intensity and hue. These measurements are made using creative computations developed and adapted from the RETINEX™ theory (Land, 1977), where the RETINEX implementation adjusts any pixel in any direction in color space and further to automatically determine the best direction for it to be adjusted to increase the perceptual visibility of the algorithm with a minimal amount of change to the original image values.
摘要翻译： 图像处理系统和方法通过调整图像颜色来校正图像的感知质量。 在这个意义上的颜色应被理解为包含颜色的三维参数化，包括强度和色相。 这些测量是使用RETINEX™理论（Land，1977）开发和改编的创意计算进行的，其中RETINEX实现调整颜色空间中任何方向的任何像素，并进一步自动确定调整其最佳方向以增加 具有对原始图像值的最小量变化的算法的感知可见性。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.017 秒)
