公开(公告)号：US07499574B1

公开(公告)日：2009-03-03

申请号：US10703288

申请日：2003-11-06

申请人： Ming-Hsuan Yang ,  Jeffrey Ho ,  Kuang-Chih Lee

发明人： Ming-Hsuan Yang ,  Jeffrey Ho ,  Kuang-Chih Lee

IPC分类号： G06K9/00

CPC分类号： G06K9/00335 ,  G06K9/00275 ,  G06K9/00288 ,  G06K9/3208 ,  G06K9/6232

摘要： The present invention meets these needs by providing temporal coherency to recognition systems. One embodiment of the present invention comprises a manifold recognition module to use a sequence of images for recognition. A manifold training module receives a plurality of training image sequences (e.g. from a video camera), each training image sequence including an individual in a plurality of poses, and establishes relationships between the images of a training image sequence. A probabilistic identity module receives a sequence of recognition images including a target individual for recognition, and identifies the target individual based on the relationship of training images corresponding to the recognition images. An occlusion module masks occluded portions of an individual's face to prevent distorted identifications.

摘要翻译： 本发明通过向识别系统提供时间一致性来满足这些需求。 本发明的一个实施例包括使用一系列图像进行识别的歧管识别模块。 歧管训练模块接收多个训练图像序列（例如，从摄像机），每个训练图像序列包括多个姿势中的个体，并且建立训练图像序列的图像之间的关系。 概率识别模块接收包括用于识别的目标个体的识别图像序列，并且基于与识别图像相对应的训练图像的关系来识别目标个体。 闭塞模块遮挡个人脸部的遮挡部分以防止变形的识别。

公开(公告)号：US20080137956A1

公开(公告)日：2008-06-12

申请号：US11950662

申请日：2007-12-05

申请人： Ming-Hsuan Yang ,  Alessandro Bissacco

发明人： Ming-Hsuan Yang ,  Alessandro Bissacco

IPC分类号： G06K9/00

CPC分类号： G06K9/00342 ,  G06K9/6257

摘要： Methods and systems are described for three-dimensional pose estimation. A training module determines a mapping function between a training image sequence and pose representations of a subject in the training image sequence. The training image sequence is represented by a set of appearance and motion patches. A set of filters are applied to the appearance and motion patches to extract features of the training images. Based on the extracted features, the training module learns a multidimensional mapping function that maps the motion and appearance patches to the pose representations of the subject. A testing module outputs a fast human pose estimation by applying the learned mapping function to a test image sequence.

摘要翻译： 描述了用于三维姿态估计的方法和系统。 训练模块确定训练图像序列和训练图像序列中的对象的姿态表示之间的映射函数。 训练图像序列由一组外观和运动补丁表示。 将一组滤镜应用于外观和运动补片以提取训练图像的特征。 基于提取的特征，训练模块学习将运动和外观补片映射到对象的姿态表示的多维映射函数。 测试模块通过将学习的映射函数应用于测试图像序列来输出快速人体姿态估计。

公开(公告)号：US20070103471A1

公开(公告)日：2007-05-10

申请号：US11553374

申请日：2006-10-26

申请人： Ming-Hsuan Yang ,  Zhimin Fan

发明人： Ming-Hsuan Yang ,  Zhimin Fan

IPC分类号： G06T15/70

CPC分类号： G06K9/00369 ,  A61B5/1038 ,  G06T7/246

摘要： A system and method recognizes and tracks human motion from different motion classes. In a learning stage, a discriminative model is learned to project motion data from a high dimensional space to a low dimensional space while enforcing discriminance between motions of different motion classes in the low dimensional space. Additionally, low dimensional data may be clustered into motion segments and motion dynamics learned for each motion segment. In a tracking stage, a representation of human motion is received comprising at least one class of motion. The tracker recognizes and tracks the motion based on the learned discriminative model and the learned dynamics.

摘要翻译： 系统和方法识别和跟踪来自不同运动类别的人运动。 在学习阶段，学习将辨别模型从高维空间投影到低维空间，同时在低维空间中执行不同运动类别运动之间的鉴别。 此外，低维数据可以被聚集成运动段并且为每个运动段学习运动动力学。 在跟踪阶段，接收包括至少一类运动的人体运动的表示。 跟踪者基于学习的歧视模型和学习的动态来识别和跟踪动作。

公开(公告)号：US07103225B2

公开(公告)日：2006-09-05

申请号：US10703294

申请日：2003-11-06

申请人： Ming-Hsuan Yang ,  Jeffrey Ho

发明人： Ming-Hsuan Yang ,  Jeffrey Ho

IPC分类号： G06K9/62 ,  G06K9/00

CPC分类号： G06K9/4661 ,  G06K9/00275 ,  G06K9/6218

摘要： Taking a set of unlabeled images of a collection of objects acquired under different imaging conditions, and decomposing the set into disjoint subsets corresponding to individual objects requires clustering. Appearance-based methods for clustering a set of images of 3-D objects acquired under varying illumination conditions can be based on the concept of illumination cones. A clustering problem is equivalent to finding convex polyhedral cones in the high-dimensional image space. To efficiently determine the conic structures hidden in the image data, the concept of conic affinity can be used which measures the likelihood of a pair of images belonging to the same underlying polyhedral cone. Other algorithms can be based on affinity measure based on image gradient comparisons operating directly on the image gradients by comparing the magnitudes and orientations of the image gradient.

摘要翻译： 采用在不同成像条件下获取的对象集合的一组未标记图像，并将该集合分解为与各个对象对应的不相关的子集需要聚类。 用于聚类在变化的照明条件下获取的3-D物体的一组图像的基于外观的方法可以基于照明锥的概念。 聚类问题相当于在高维图像空间中发现凸多面体锥。 为了有效地确定隐藏在图像数据中的圆锥形结构，可以使用锥形亲和度的概念，其测量属于相同底层多面体锥体的一对图像的可能性。 其他算法可以基于通过比较图像梯度的幅度和方向基于图像梯度直接操作的图像梯度比较的亲和测量。

公开(公告)号：US20060036399A1

公开(公告)日：2006-02-16

申请号：US11179881

申请日：2005-07-11

申请人： Ming-Hsuan Yang ,  Ruei-Sung Lin ,  Jongwoo Lim ,  David Ross

发明人： Ming-Hsuan Yang ,  Ruei-Sung Lin ,  Jongwoo Lim ,  David Ross

IPC分类号： G06F17/18

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： A system and a method are disclosed for an adaptive discriminative generative model with a probabilistic interpretation. As applied to visual tracking, the discriminative generative model separates the target object from the background more accurately and efficiently than conventional methods. A computationally efficient algorithm constantly updates the discriminative model over time. The discriminative generative model adapts to accommodate dynamic appearance variations of the target and background. Experiments show that the discriminative generative model effectively tracks target objects undergoing large pose and lighting changes.

摘要翻译： 公开了一种具有概率解释的自适应识别生成模型的系统和方法。 应用于视觉跟踪，鉴别生成模型比传统方法更准确有效地将目标对象与背景分离。 计算有效的算法随着时间不断更新辨别模型。 鉴别生成模型适应于适应目标和背景的动态外观变化。 实验表明，识别性生成模型有效地跟踪目标物体的大姿态和照明变化。

公开(公告)号：US20050180602A1

公开(公告)日：2005-08-18

申请号：US10858878

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： G06K9/00 ,  G06K9/36 ,  G06K9/48

CPC分类号： G06K9/00201

摘要： The advantage of the present invention is to appropriately detect the object. The object detection apparatus in the present invention has a plurality of cameras to determine the distance to the objects, a distance determination unit to determine the distance therein, a histogram generation unit to specify the frequency of the pixels against the distances to the pixels, an object distance determination unit that determines the most likely distance, a probability mapping unit that provides the probabilities of the pixels based on the difference of the distance, a kernel detection unit that determines a kernel region as a group of the pixels, a periphery detection unit that determines a peripheral region as a group of the pixels, selected from the pixels being close to the kernel region and an object specifying unit that specifies the object region where the object is present with a predetermined probability.

摘要翻译： 本发明的优点是适当地检测物体。 本发明的物体检测装置具有多个照相机，用于确定与物体的距离，距离确定单元，用于确定其中的距离;直方图生成单元，用于根据与像素的距离来指定像素的频率; 确定最可能的距离的对象距离确定单元，基于距离差提供像素概率的概率映射单元，将核区域确定为像素组的内核检测单元，周边检测单元 将外围区域确定为从接近核心区域的像素中选择的像素组，以及以预定概率指定对象存在的对象区域的对象指定单元。

公开(公告)号：US20050141769A1

公开(公告)日：2005-06-30

申请号：US10989967

申请日：2004-11-15

申请人： Jeffrey Ho ,  Jongwoo Lim ,  Ming-Hsuan Yang

发明人： Jeffrey Ho ,  Jongwoo Lim ,  Ming-Hsuan Yang

IPC分类号： G06K20060101 ,  G06K9/00 ,  G06K9/62

CPC分类号： G06K9/6224 ,  G06K9/6215 ,  G06K9/6252

摘要： A system and a method are disclosed for clustering images of objects seen from different viewpoints. That is, given an unlabelled set of images of n objects, an unsupervised algorithm groups the images into N disjoint subsets such that each subset only contains images of a single object. The clustering method makes use of a broad geometric framework that exploits the interplay between the geometry of appearance manifolds and the symmetry of the 2D affine group.

摘要翻译： 公开了一种系统和方法，用于对从不同视点看到的对象的图像进行聚类。 也就是说，给定n个对象的未标记的图像集合，无监督的算法将图像分组为N个不相交的子集，使得每个子集仅包含单个对象的图像。 聚类方法利用了广泛的几何框架，利用了外观多样性的几何和2D仿射组的对称性之间的相互作用。

公开(公告)号：US08218817B2

公开(公告)日：2012-07-10

申请号：US12339029

申请日：2008-12-18

申请人： Ming-Hsuan Yang ,  Jeffrey Ho

发明人： Ming-Hsuan Yang ,  Jeffrey Ho

IPC分类号： G06K9/00

CPC分类号： G06K9/3241 ,  G06K9/00369 ,  G06K9/4647 ,  G06T7/248 ,  G06T2207/10016

摘要： A visual tracker tracks an object in a sequence of input images. A tracking module detects a location of the object based on a set of weighted blocks representing the object's shape. The tracking module then refines a segmentation of the object from the background image at the detected location. Based on the refined segmentation, the set of weighted blocks are updated. By adaptively encoding appearance and shape into the block configuration, the present invention is able to efficiently and accurately track an object even in the presence of rapid motion that causes large variations in appearance and shape of the object.

摘要翻译： 视觉跟踪器以输入图像序列跟踪对象。 跟踪模块基于表示对象形状的一组加权块检测对象的位置。 跟踪模块然后在检测到的位置处从背景图像中精细地分割对象。 基于精细分割，更新加权块集合。 通过将外观和形状自适应地编码成块结构，本发明能够即使在存在引起物体的外观和形状的大的变化的快速运动的情况下也能有效且准确地跟踪物体。

公开(公告)号：US07831094B2

公开(公告)日：2010-11-09

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： G06K9/46

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。

公开(公告)号：US07519201B2

公开(公告)日：2009-04-14

申请号：US11553388

申请日：2006-10-26

申请人： Ming-Hsuan Yang ,  Alessandro Bissacco

发明人： Ming-Hsuan Yang ,  Alessandro Bissacco

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/4647 ,  G06K9/00369

摘要： A method and system efficiently and accurately detects humans in a test image and classifies their pose. In a training stage, a probabilistic model is derived in an unsupervised or semi-supervised manner such that at least some poses are not manually labeled. The model provides two sets of model parameters to describe the statistics of images containing humans and images of background scenes. In a testing stage, the probabilistic model is used to determine if a human is present in the image, and classify the human's pose based on the poses in the training images. A solution is efficiently provided to both human detection and pose classification by using the same probabilistic model to solve the problems.

摘要翻译： 一种方法和系统有效和准确地检测测试图像中的人类并对其姿态进行分类。 在训练阶段，以无监督或半监督的方式导出概率模型，使得至少一些姿势不是手动标记的。 该模型提供两组模型参数来描述包含人类和背景场景图像的图像的统计。 在测试阶段，概率模型用于确定人物是否存在于图像中，并且基于训练图像中的姿态对人的姿势进行分类。 通过使用相同的概率模型来解决问题，有效地提供了人类检测和姿态分类的解决方案。