公开(公告)号：US20090164405A1

公开(公告)日：2009-06-25

申请号：US12276128

申请日：2008-11-21

申请人： Ming-Hsuan Yang ,  Ananth Ranganathan

发明人： Ming-Hsuan Yang ,  Ananth Ranganathan

IPC分类号： G06N5/02

CPC分类号： G06K9/32 ,  G06K9/6214 ,  G06K9/6273

摘要： An online sparse matrix Gaussian process (OSMGP) uses online updates to provide an accurate and efficient regression for applications such as pose estimation and object tracking. A regression calculation module calculates a regression on a sequence of input images to generate output predictions based on a learned regression model. The regression model is efficiently updated by representing a covariance matrix of the regression model using a sparse matrix factor (e.g., a Cholesky factor). The sparse matrix factor is maintained and updated in real-time based on the output predictions. Hyperparameter optimization, variable reordering, and matrix downdating techniques can also be applied to further improve the accuracy and/or efficiency of the regression process.

摘要翻译： 在线稀疏矩阵高斯过程（OSMGP）使用在线更新来为姿态估计和对象跟踪等应用程序提供准确有效的回归。 回归计算模块根据学习的回归模型计算输入图像序列的回归以产生输出预测。 通过使用稀疏矩阵因子（例如，Cholesky因子）表示回归模型的协方差矩阵来有效地更新回归模型。 基于输出预测，稀疏矩阵因子实时维护和更新。 超参数优化，可变重排序和矩阵减法技术也可以应用于进一步提高回归过程的准确性和/或效率。

公开(公告)号：US07430315B2

公开(公告)日：2008-09-30

申请号：US10858930

申请日：2004-06-01

申请人： Ming-Hsuan Yang ,  Jongwoo Lim ,  David Ross ,  Takahiro Ohashi

发明人： Ming-Hsuan Yang ,  Jongwoo Lim ,  David Ross ,  Takahiro Ohashi

IPC分类号： G06K9/62 ,  G06K9/64 ,  G06K9/40

CPC分类号： G06K9/6269 ,  G06K9/00228 ,  G06K9/6857

摘要： The face detection system and method attempts classification of a test image before performing all of the kernel evaluations. Many subimages are not faces and should be relatively easy to identify as such. Thus, the SVM classifier try to discard non-face images using as few kernel evaluations as possible using a cascade SVM classification. In the first stage, a score is computed for the first two support vectors, and the score is compared to a threshold. If the score is below the threshold value, the subimage is classified as not a face. If the score is above the threshold value, the cascade SVM classification function continues to apply more complicated decision rules, each time doubling the number of kernel evaluations, classifying the image as a non-face (and thus terminating the process) as soon as the test image fails to satisfy one of the decision rules. Finally, if the subimage has satisfied all intermediary decision rules, and has now reached the point at which all support vectors must be considered, the original decision function is applied. Satisfying this final rule, and all intermediary rules, is the only way for a test image to garner a positive (face) classification.

摘要翻译： 面部检测系统和方法在执行所有内核评估之前尝试对测试图像进​​行分类。 许多子图像不是面孔，应该比较容易识别。 因此，SVM分类器尝试使用级联SVM分类使用尽可能少的内核评估来丢弃非面部图像。 在第一阶段，对前两个支持向量计算分数，并将分数与阈值进行比较。 如果分数低于阈值，则子图像被分类为不是脸部。 如果分数高于阈值，则级联SVM分类功能继续应用更复杂的决策规则，每次将内核评估的数量加倍，将图像分类为非面（并因此终止进程），一旦 测试图像不能满足其中一个决策规则。 最后，如果子图像满足了所有的中介决策规则，并且现在已经到了必须考虑所有支持向量的点，则应用原始决策函数。 满足这个最终规则和所有中介规则是测试图像获得积极（面部）分类的唯一方法。

公开(公告)号：US20060285770A1

公开(公告)日：2006-12-21

申请号：US11450045

申请日：2006-06-09

申请人： Jongwoo Lim ,  Ming-Hsuan Yang

发明人： Jongwoo Lim ,  Ming-Hsuan Yang

IPC分类号： G06K9/36 ,  G06K9/00

CPC分类号： G06T7/20 ,  G06K9/6206

摘要： A system and a method model the motion of a non-rigid object using a thin plate spline (TPS) transform. A first image of a video sequence is received, and a region of interest, referred to as a template, is chosen manually or automatically. A set of arbitrarily-chosen fixed reference points is positioned on the template. A target image of the video sequence is chosen for motion estimation relative to the template. A set of pixels in the target image corresponding to the pixels of the template is determined, and this set of pixels is back-warped to match the template using a thin-plate-spline-based technique. The error between the template and the back-warped image is determined and iteratively minimized using a gradient descent technique. The TPS parameters can then be used to estimate the relative motion between the template and the corresponding region of the target image. According to one embodiment, a stiff-to-flexible approach mitigates instability that can arise when reference points lie in textureless regions, or when the initial TPS parameters are not close to the desired ones. The value of a regularization parameter is varied from a larger to a smaller value, varying the nature of the warp from stiff to flexible, so as to progressively emphasize local non-rigid deformations.

公开(公告)号：US20060098865A1

公开(公告)日：2006-05-11

申请号：US11266830

申请日：2005-11-03

申请人： Ming-Hsuan Yang ,  Gang Hua

发明人： Ming-Hsuan Yang ,  Gang Hua

IPC分类号： G06K9/62

CPC分类号： G06K9/00362

摘要： A statistical formulation estimates two-dimensional human pose from single images. This is based on a Markov network and on inferring pose parameters from cues such as appearance, shape, edge, and color. A data-driven belief propagation Monte Carlo algorithm performs efficient Bayesian inferencing within a rigorous statistical framework. Experimental results demonstrate the effectiveness of the method in estimating human pose from single images.

摘要翻译： 统计公式估计单一图像的二维人类姿势。 这是基于马尔可夫网络，并从提示，如外观，形状，边缘和颜色推断姿态参数。 数据驱动的信念传播蒙特卡罗算法在严格的统计框架内执行高效的贝叶斯推理。 实验结果证明了该方法在从单个图像估计人类姿势方面的有效性。

公开(公告)号：US20060023916A1

公开(公告)日：2006-02-02

申请号：US11179280

申请日：2005-07-11

申请人： Ming-Hsuan Yang ,  Ruei-Sung Lin

发明人： Ming-Hsuan Yang ,  Ruei-Sung Lin

IPC分类号： G06K9/00

CPC分类号： G06K9/00241 ,  G06K9/00261 ,  G06K9/3233 ,  G06K9/6214 ,  G06K9/6234 ,  G06K9/6247 ,  G06T7/246 ,  G06T7/277 ,  G06T7/70 ,  G06T2207/30241

摘要： Visual tracking over a sequence of images is formulated by defining an object class and one or more background classes. The most discriminant features available in the images are then used to select a portion of each image as belonging to the object class. Fisher's linear discriminant method is used to project high-dimensional image data onto a lower-dimensional space, e.g., a line, and perform classification in the lower-dimensional space. The projection function is incrementally updated.

摘要翻译： 通过定义一个对象类和一个或多个后台类来制定一系列图像的视觉跟踪。 然后使用图像中可用的最大判别特征来将每个图像的一部分选择为属于对象类。 Fisher线性判别方法用于将高维图像数据投影到较低维空间（例如一行）上，并在低维空间中进行分类。 投影功能逐步更新。

公开(公告)号：US20050238200A1

公开(公告)日：2005-10-27

申请号：US11021672

申请日：2004-12-22

申请人： Rakesh Gupta ,  Ming-Hsuan Yang ,  Jason Meltzer

发明人： Rakesh Gupta ,  Ming-Hsuan Yang ,  Jason Meltzer

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC分类号： G06K9/6255 ,  G06K9/00201 ,  G06K9/00664 ,  G06K9/6248 ,  G06K2209/29

摘要： Simultaneous localization and mapping (SLAM) utilizes multiple view feature descriptors to robustly determine location despite appearance changes that would stifle conventional systems. A SLAM algorithm generates a feature descriptor for a scene from different perspectives using kernel principal component analysis (KPCA). When the SLAM module subsequently receives a recognition image after a wide baseline change, it can refer to correspondences from the feature descriptor to continue map building and/or determine location. Appearance variations can result from, for example, a change in illumination, partial occlusion, a change in scale, a change in orientation, change in distance, warping, and the like. After an appearance variation, a structure-from-motion module uses feature descriptors to reorient itself and continue map building using an extended Kalman Filter. Through the use of a database of comprehensive feature descriptors, the SLAM module is also able to refine a position estimation despite appearance variations.

摘要翻译： 同时定位和映射（SLAM）利用多个视图特征描述符来鲁棒地确定位置，尽管出现了会阻碍常规系统的变化。 SLAM算法使用内核主成分分析（KPCA）从不同的角度生成场景的特征描述符。 当SLAM模块随后在宽基线改变之后接收到识别图像时，其可以参考来自特征描述符的对应关系，以继续构建图像和/或确定位置。 外观变化可以由例如照明变化，部分遮挡，尺度变化，取向变化，距离变化，翘曲等引起。 在外观变化之后，运动结构模块使用特征描述符重新定向自身，并使用扩展卡尔曼滤波器继续构建地图。 通过使用综合特征描述符的数据库，SLAM模块也可以改进位置估计，尽管外观变化。