DISCRIMINATIVE MOTION MODELING FOR HUMAN MOTION TRACKING
    11.
    发明申请
    DISCRIMINATIVE MOTION MODELING FOR HUMAN MOTION TRACKING 失效
    人体运动跟踪的辨别运动建模

    公开(公告)号:US20070103471A1

    公开(公告)日:2007-05-10

    申请号:US11553374

    申请日:2006-10-26

    IPC分类号: G06T15/70

    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。

    Clustering appearances of objects under varying illumination conditions
    12.
    发明授权
    Clustering appearances of objects under varying illumination conditions 有权
    在不同照明条件下物体的聚类外观

    公开(公告)号:US07103225B2

    公开(公告)日:2006-09-05

    申请号:US10703294

    申请日:2003-11-06

    IPC分类号: G06K9/62 G06K9/00

    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。

    Adaptive discriminative generative model and application to visual tracking
    13.
    发明申请
    Adaptive discriminative generative model and application to visual tracking 有权
    自适应识别生成模型和应用于视觉跟踪

    公开(公告)号:US20060036399A1

    公开(公告)日:2006-02-16

    申请号:US11179881

    申请日:2005-07-11

    IPC分类号: G06F17/18

    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。

    Method, apparatus and program for detecting an object
    14.
    发明申请
    Method, apparatus and program for detecting an object 有权
    用于检测物体的方法,装置和程序

    公开(公告)号:US20050180602A1

    公开(公告)日:2005-08-18

    申请号:US10858878

    申请日:2004-06-01

    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。

    Image clustering with metric, local linear structure, and affine symmetry
    15.
    发明申请
    Image clustering with metric, local linear structure, and affine symmetry 有权
    具有度量,局部线性结构和仿射对称性的图像聚类

    公开(公告)号:US20050141769A1

    公开(公告)日:2005-06-30

    申请号:US10989967

    申请日:2004-11-15

    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。

    Visual tracking using incremental fisher discriminant analysis
    16.
    发明授权
    Visual tracking using incremental fisher discriminant analysis 有权
    使用增量渔民判别分析的视觉跟踪

    公开(公告)号:US07650011B2

    公开(公告)日:2010-01-19

    申请号:US11179280

    申请日:2005-07-11

    IPC分类号: G06K9/00

    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。

    Extended Isomap using Fisher Linear Discriminant and Kernel Fisher Linear Discriminant
    17.
    发明授权
    Extended Isomap using Fisher Linear Discriminant and Kernel Fisher Linear Discriminant 失效
    使用Fisher线性判别和内核Fisher线性判别的扩展Isomap

    公开(公告)号:US07379602B2

    公开(公告)日:2008-05-27

    申请号:US10621872

    申请日:2003-07-16

    申请人: Ming-Hsuan Yang

    发明人: Ming-Hsuan Yang

    CPC分类号: G06K9/6252 G06K9/6234

    摘要: A method for representing images for pattern classification extends the conventional Isomap method with Fisher Linear Discriminant (FLD) or Kernel Fisher Linear Discriminant (KFLD) for classification. The extended Isomap method estimates the geodesic distance of data points corresponding to images for pattern classification, and uses pairwise geodesic distances as feature vectors. The method applies FLD to the feature vectors to find an optimal projection direction to maximize the distances between cluster centers of the feature vectors. The method may apply KFLD to the feature vectors instead of FLD.

    摘要翻译: 用于表示图案分类的图像的方法扩展了用于分类的具有Fisher线性判别(FLD)或内核Fisher线性判别(KFLD)的常规Isomap方法。 扩展的Isomap方法估计与图像分类对应的数据点的测地距离,并使用成对测地距离作为特征向量。 该方法将FLD应用于特征向量以找到最佳投影方向,以最大化特征向量的聚类中心之间的距离。 该方法可以将KFLD应用于特征向量而不是FLD。

    Method, apparatus and program for detecting an object
    18.
    发明授权
    Method, apparatus and program for detecting an object 有权
    用于检测物体的方法,装置和程序

    公开(公告)号:US07224831B2

    公开(公告)日:2007-05-29

    申请号:US10858878

    申请日:2004-06-01

    IPC分类号: G06K9/36

    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。

    Face recognition using kernel fisherfaces
    19.
    发明授权
    Face recognition using kernel fisherfaces 有权
    使用内核渔船进行脸部识别

    公开(公告)号:US07054468B2

    公开(公告)日:2006-05-30

    申请号:US10201429

    申请日:2002-07-22

    申请人: Ming-Hsuan Yang

    发明人: Ming-Hsuan Yang

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00275

    摘要: A face recognition system and method project an input face image and a set of reference face images from an input space to a high dimensional feature space in order to obtain more representative features of the face images. The Kernel Fisherfaces of the input face image and the reference face images are calculated, and are used to project the input face image and the reference face images to a face image space lower in dimension than the input space and the high dimensional feature space. The input face image and the reference face images are represented as points in the face image space, and the distance between the input face point and each of the reference image points are used to determine whether or not the input face image resembles a particular face image of the reference face images.

    摘要翻译: 面部识别系统和方法将输入面部图像和一组参考面部图像从输入空间投影到高维特征空间,以便获得面部图像的更具代表性的特征。 计算输入面部图像和参考面部图像的内容面积,并将输入面部图像和参考面部图像投影到尺寸小于输入空间和高维特征空间的面部图像空间。 输入面部图像和参考面部图像被表示为面部图像空间中的点,并且使用输入面部点与每个参考图像点之间的距离来确定输入面部图像是否类似于特定面部图像 的参考面部图像。

    Adaptive probabilistic visual tracking with incremental subspace update
    20.
    发明申请
    Adaptive probabilistic visual tracking with incremental subspace update 有权
    具有增量子空间更新的自适应概率视觉跟踪

    公开(公告)号:US20050175219A1

    公开(公告)日:2005-08-11

    申请号:US10989966

    申请日:2004-11-15

    IPC分类号: G06K9/00 G06K9/46 G06T7/20

    摘要: A system and a method are disclosed for adaptive probabilistic tracking of an object within a motion video. The method utilizes a time-varying Eigenbasis and dynamic, observation and inference models. The Eigenbasis serves as a model of the target object. The dynamic model represents the motion of the object and defines possible locations of the target based upon previous locations. The observation model provides a measure of the distance of an observation of the object relative to the current Eigenbasis. The inference model predicts the most likely location of the object based upon past and present observations. The method is effective with or without training samples. A computer-based system provides a means for implementing the method. The effectiveness of the system and method are demonstrated through simulation.

    摘要翻译: 公开了用于运动视频内的对象的自适应概率跟踪的系统和方法。 该方法利用时变特征向量和动态,观察和推理模型。 Eigenbasis作为目标对象的模型。 动态模型表示对象的运动,并根据先前的位置定义目标的可能位置。 观察模型提供了对象相对于当前Eigenbasis的观察距离的度量。 推论模型基于过去和现在的观察预测对象的最可能的位置。 该方法在有或没有训练样本的情况下是有效的。 基于计算机的系统提供了实现该方法的手段。 通过仿真证明了系统和方法的有效性。