专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2005081792A3 METHOD, APPARATUS AND PROGRAM FOR DETECTING AN OBJECT 审中-公开
标题翻译：用于检测对象的方法，装置和程序
公开(公告)号：WO2005081792A3
公开(公告)日：2006-09-21
申请号：PCT/US2005003822
申请日：2005-02-07
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , LIM JONGWOO , ROSS DAVID A , OHASHI TAKAHIRO
发明人： YANG MING-HSUAN , LIM JONGWOO , ROSS DAVID A , OHASHI TAKAHIRO
IPC分类号： G06K9/36 , G06K9/00 , 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 (2) to determine the distance to the objects, a distance determination unit (11) to determine the distance therein, a histogram generation unit (13) to specify the frequency of the pixels against the distances to the pixels, an object distance determination unit (14) that determines the most likely distance, a probability mapping unit (15) that provides the probabilities of the pixels based on the difference of the distance, a kernel detection unit (16a) that determines a kernel region as a group of the pixels, a periphery detection unit (16b) 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 (17) 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（2），用于确定与物体的距离，距离确定单元（11），用于确定其中的距离;直方图生成单元（13），用于指定相对于像素的距离的像素，确定最可能的距离的对象距离确定单元（14），基于距离的差异提供像素的概率的概率映射单元（15），内核检测单元确定作为像素组的核心区域的周边检测单元（16b），其将周围区域确定为从接近所述核心区域的像素中选择的像素组，以及对象指定单元（17 ）以预定概率指定对象存在的对象区域。

2. 发明申请

WO2005079237A3 FACE RECOGNITION SYSTEM 审中-公开
标题翻译：脸部识别系统
公开(公告)号：WO2005079237A3
公开(公告)日：2007-12-27
申请号：PCT/US2005003818
申请日：2005-02-07
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , LIM JONGWOO , ROSS DAVID A , OHASHI TAKAHIRO
发明人： YANG MING-HSUAN , LIM JONGWOO , ROSS DAVID A , OHASHI TAKAHIRO
IPC分类号： G06K9/62 , G06K9/00 , G06K9/68 , G06K9/74
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分类尽可能少地使用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。

3. 发明申请

WO2005050533A3 IMAGE CLUSTERING WITH METRIC, LOCAL LINEAR STRUCTURE, AND AFFINE SYMMETRY 审中-公开
标题翻译：具有公制，局部线性结构和AFFINE SYMETRY的图像聚类
公开(公告)号：WO2005050533A3
公开(公告)日：2006-11-23
申请号：PCT/US2004038347
申请日：2004-11-15
申请人： HONDA MOTOR CO LTD , HO JEFFREY , LIM JONGWOO , YANG MING-HSUAN
发明人： HO JEFFREY , LIM JONGWOO , YANG MING-HSUAN
IPC分类号： G06K9/62 , G06K20060101 , G06K9/00 , G06K9/46
CPC分类号： G06K9/6224 , G06K9/6215 , G06K9/6252
摘要： A system and a method are disclosed for clustering (370) images of objects seen from different viewpoints. That is, given an unlabelled set of images of n objects (310), 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，用于从不同视点看到的对象的聚类（370）图像。也就是说，给定n个对象（310）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。

4. 发明申请

WO2006010129A2 ADAPTIVE DISCRIMINATIVE GENERATIVE MODEL AND INCREMENTAL FISHER DISCRIMINANT ANALYSIS AND APPLICATION TO VISUAL TRACKING 审中-公开
标题翻译：自适应分辨率生成模型和增量渔业分析分析和应用于视觉跟踪
公开(公告)号：WO2006010129A2
公开(公告)日：2006-01-26
申请号：PCT/US2005024582
申请日：2005-07-11
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , LIN RUEI-SUNG , LIM JONGWOO , ROSS DAVID
发明人： YANG MING-HSUAN , LIN RUEI-SUNG , LIM JONGWOO , ROSS DAVID
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： 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. According to an alternate embodiment, visual tracking 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：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。根据替代实施例，通过定义对象类和一个或多个后台类来形成视觉跟踪。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。

5. 发明申请

WO2007001884A3 DIRECT METHOD FOR MODELING NON-RIGID MOTION WITH THIN FILM PLATE SPLINE TRANSFORMATION 审中-公开
标题翻译：用薄膜板样条变换建立非刚性运动的直接方法
公开(公告)号：WO2007001884A3
公开(公告)日：2007-12-06
申请号：PCT/US2006023350
申请日：2006-06-15
申请人： HONDA MOTOR CO LTD , LIM JONGWOO , YANG MING-HSUAN
发明人： LIM JONGWOO , YANG MING-HSUAN
IPC分类号： G06K9/36
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.
摘要翻译：系统和方法使用薄板样条（TPS）变换来模拟非刚性物体的运动。接收视频序列的第一图像，并且手动或自动选择被称为模板的感兴趣区域。一组任意选择的固定参考点位于模板上。视频序列的目标图像被选择用于相对于模板的运动估计。确定目标图像中与模板的像素相对应的一组像素，并且使用基于薄板样条的技术来对这组像素进行反向翘曲以匹配模板。使用梯度下降技术确定模板和反向变形图像之间的误差并迭代最小化。然后可以使用TPS参数来估计模板与目标图像的对应区域之间的相对运动。根据一个实施例，当参考点位于无纹理区域中时，或者当初始TPS参数不接近期望值时，刚性到柔性方法减轻可能出现的不稳定性。正则化参数的值从较大值变化到较小值，从而使经线的性质从刚性变为柔性，从而逐渐强调局部非刚性变形。

6. 发明申请

WO2004042539A9 VIDEO-BASED FACE RECOGNITION USING PROBABILISTIC APPEARANCE MANIFOLDS 审中-公开
标题翻译：基于视觉的面部识别使用概念外观图
公开(公告)号：WO2004042539A9
公开(公告)日：2005-07-21
申请号：PCT/US0335496
申请日：2003-11-06
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , HO JEFFREY , LEE KUANG-CHIH
发明人： YANG MING-HSUAN , HO JEFFREY , LEE KUANG-CHIH
IPC分类号： G06F20060101 , G06K9/00 , G06K9/62 , G06K9/64 , G06K9/74 , G06T11/20 , G06T15/00 , H04N7/00 , H04N7/18 , H04N9/47 , H04N13/02 , H04N13/04 , H04N15/00
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。

7. 发明申请

WO2005104737A3 SIMULTANEOUS LOCALIZATION AND MAPPING USING MULTIPLE VIEW FEATURE DESCRIPTORS 审中-公开
标题翻译：使用多个视图功能描述符的同时定位和映射
公开(公告)号：WO2005104737A3
公开(公告)日：2009-04-16
申请号：PCT/US2005014365
申请日：2005-04-26
申请人： HONDA MOTOR CO LTD , GUPTA RAKESH , YANG MING-HSUAN , MELTZER JASON
发明人： GUPTA RAKESH , YANG MING-HSUAN , MELTZER JASON
IPC分类号： G06K9/46 , G06K9/00 , 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。

8. 发明申请

WO2008070701A3 FAST HUMAN POSE ESTIMATION USING APPEARANCE AND MOTION VIA MULTI-DIMENSIONAL BOOSTING REGRESSION 审中-公开
标题翻译：使用多维推进回归的外观和运动快速进行人体姿势估计
公开(公告)号：WO2008070701A3
公开(公告)日：2008-10-23
申请号：PCT/US2007086458
申请日：2007-12-05
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , BISSACCO ALESSANDRO
发明人： YANG MING-HSUAN , BISSACCO ALESSANDRO
IPC分类号： G06K9/62
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与训练图像序列中的对象的姿势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。将一组过滤器应用于外观和运动补丁以提取训练图像的特征。基于提取的特征，训练模块学习多维映射函数，其将运动和外观片映射到对象的姿势表示。测试模块通过将学习映射函数应用于测试图像序列来输出快速人体姿势估计。

9. 发明申请

WO2004042539A2 VIDEO-BASED FACE RECOGNITION USING PROBABILISTIC APPEARANCE MANIFOLDS 审中-公开
标题翻译：基于视频的人脸识别使用概率外观人工神经网络
公开(公告)号：WO2004042539A2
公开(公告)日：2004-05-21
申请号：PCT/US0335496
申请日：2003-11-06
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , HO JEFFREY
发明人： YANG MING-HSUAN , HO JEFFREY , LEE KUANG-CHIH
IPC分类号： G06F20060101 , G06K9/00 , G06K9/62 , G06K9/64 , G06K9/74 , G06T11/20 , G06T15/00 , H04N7/00 , H04N7/18 , H04N9/47 , H04N13/02 , H04N13/04 , H04N15/00 , G06F
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。流形训练模块接收多个训练图像序列（例如来自摄像机），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对应的训练图像的关系来识别目标个体。遮挡模块遮挡个人脸部的遮挡部分以防止扭曲的标识。

10. 发明申请

WO2007053469A2 DISCRIMINATIVE MOTION MODELING FOR HUMAN MOTION TRACKING 审中-公开
标题翻译：人体运动跟踪的辨别运动建模
公开(公告)号：WO2007053469A2
公开(公告)日：2007-05-10
申请号：PCT/US2006042088
申请日：2006-10-27
申请人： HONDA MOTOR CO LTD , YANG MING-HSUAN , FAN ZHIMIN
发明人： YANG MING-HSUAN , FAN ZHIMIN
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。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式