利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

305 条记录 (耗时 0.01 秒)

    Recovery of 3D Human Pose by Jointly Learning Metrics and Mixtures of Experts
    2.
    发明申请
    Recovery of 3D Human Pose by Jointly Learning Metrics and Mixtures of Experts 有权
    通过联合学习指标和专家组合恢复3D人体姿势

    公开(公告)号：US20100049675A1

    公开(公告)日：2010-02-25

    申请号：US12277284

    申请日：2008-11-24

    申请人： Huazhong Ning ,  Wei Xu ,  Yihong Gong

    发明人： Huazhong Ning ,  Wei Xu ,  Yihong Gong

    IPC分类号： G06F15/18 ,  G06N5/04

    CPC分类号： G06K9/00342 ,  G06K9/6212

    摘要： Systems and methods are disclosed for determining human pose by generating an Appearance and Position Context (APC) local descriptor that achieves selectivity and invariance while requiring no background subtraction; jointly learning visual words and pose regressors in a supervised manner; and estimating the human pose.

    摘要翻译： 公开了用于通过生成实现选择性和不变性而不需要背景减除的外观和位置上下文（APC）局部描述符来确定人类姿势的系统和方法; 以监督的方式联合学习视觉词和姿态回归; 并估计人的姿势。

    Recovery of 3D human pose by jointly learning metrics and mixtures of experts
    3.
    发明授权
    Recovery of 3D human pose by jointly learning metrics and mixtures of experts 有权
    通过联合学习指标和专家混合来恢复3D人体姿势

    公开(公告)号：US08311954B2

    公开(公告)日：2012-11-13

    申请号：US12277284

    申请日：2008-11-24

    申请人： Huazhong Ning ,  Wei Xu ,  Yihong Gong

    发明人： Huazhong Ning ,  Wei Xu ,  Yihong Gong

    IPC分类号： G06F15/18 ,  G06K9/62

    CPC分类号： G06K9/00342 ,  G06K9/6212

    摘要： Systems and methods are disclosed for determining 3D human pose by generating an Appearance and Position Context (APC) local descriptor that achieves selectivity and invariance while requiring no background subtraction; jointly learning visual words and pose regressors in a supervised manner; and estimating the 3D human pose.

    摘要翻译： 公开了用于通过生成实现选择性和不变性而不需要背景减除的外观和位置上下文（APC）局部描述符来确定3D人体姿态的系统和方法; 以监督的方式联合学习视觉词和姿态回归; 并估计3D人体姿势。

    Efficient multi-hypothesis multi-human 3D tracking in crowded scenes
    4.
    发明授权
    Efficient multi-hypothesis multi-human 3D tracking in crowded scenes 有权
    在拥挤的场景中有效的多假设多人类3D跟踪

    公开(公告)号：US08098891B2

    公开(公告)日：2012-01-17

    申请号：US12277278

    申请日：2008-11-24

    申请人： Fengjun Lv ,  Wei Xu ,  Yihong Gong

    发明人： Fengjun Lv ,  Wei Xu ,  Yihong Gong

    IPC分类号： G06K9/00 ,  H04N7/18

    CPC分类号： G06T7/292 ,  G06T7/285 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30232 ,  G06T2207/30241

    摘要： System and methods are disclosed to perform multi-human 3D tracking with a plurality of cameras. At each view, a module receives each camera output and provides 2D human detection candidates. A plurality of 2D tracking modules are connected to the CNNs, each 2D tracking module managing 2D tracking independently. A 3D tracking module is connected to the 2D tracking modules to receive promising 2D tracking hypotheses. The 3D tracking module selects trajectories from the 2D tracking modules to generate 3D tracking hypotheses.

    摘要翻译： 公开了用多个摄像机进行多人3D跟踪的系统和方法。 在每个视图中，模块接收每个摄像机输出并提供2D人类检测候选。 多个2D跟踪模块连接到CNN，每个2D跟踪模块独立管理2D跟踪。 3D跟踪模块连接到2D跟踪模块，以接收有希望的2D跟踪假设。 3D跟踪模块从2D跟踪模块中选择轨迹，以生成3D跟踪假设。

    Soft Edge Smoothness Prior and Application on Alpha Channel Super Resolution
    6.
    发明申请
    Soft Edge Smoothness Prior and Application on Alpha Channel Super Resolution 有权
    软边缘平滑度先前和Alpha通道超分辨率应用

    公开(公告)号：US20080267525A1

    公开(公告)日：2008-10-30

    申请号：US11869906

    申请日：2007-10-10

    申请人： Shengyang Dai ,  Mei Han ,  Wei Xu ,  Ying Wu ,  Yihong Gong

    发明人： Shengyang Dai ,  Mei Han ,  Wei Xu ,  Ying Wu ,  Yihong Gong

    IPC分类号： G06K9/40

    CPC分类号： G06T3/403

    摘要： Systems and methods are disclosed for processing a low resolution image by performing a high resolution edge segment extraction on the low resolution image; performing an image super resolution on each edge segment; performing reconstruction constraint reinforcement; and generating a high quality image from the low quality image.

    摘要翻译： 公开了通过在低分辨率图像上执行高分辨率边缘段提取来处理低分辨率图像的系统和方法; 在每个边缘片段上执行图像超分辨率; 执行重建约束加固; 并从低质量图像生成高质量图像。

    Transfer learning methods and systems for feed-forward visual recognition systems
    7.
    发明授权
    Transfer learning methods and systems for feed-forward visual recognition systems 有权
    转移前馈视觉识别系统的学习方法和系统

    公开(公告)号：US08345962B2

    公开(公告)日：2013-01-01

    申请号：US12277504

    申请日：2008-11-25

    申请人： Kai Yu ,  Wei Xu ,  Yihong Gong

    发明人： Kai Yu ,  Wei Xu ,  Yihong Gong

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6256 ,  G06N3/08

    摘要： A method and system for training a neural network of a visual recognition computer system, extracts at least one feature of an image or video frame with a feature extractor; approximates the at least one feature of the image or video frame with an auxiliary output provided in the neural network; and measures a feature difference between the extracted at least one feature of the image or video frame and the approximated at least one feature of the image or video frame with an auxiliary error calculator. A joint learner of the method and system adjusts at least one parameter of the neural network to minimize the measured feature difference.

    摘要翻译： 一种用于训练视觉识别计算机系统的神经网络的方法和系统，使用特征提取器提取图像或视频帧的至少一个特征; 使用在神经网络中提供的辅助输出近似图像或视频帧的至少一个特征; 并且利用辅助误差计算器测量提取的图像或视频帧的至少一个特征与图像或视频帧的近似的至少一个特征之间的特征差异。 该方法和系统的联合学习者调整神经网络的至少一个参数以最小化测量的特征差异。

    Video foreground segmentation method
    9.
    发明授权
    Video foreground segmentation method 失效
    视频前景分割方法

    公开(公告)号：US07440615B2

    公开(公告)日：2008-10-21

    申请号：US11553043

    申请日：2006-10-26

    申请人： Yihong Gong ,  Mei Han ,  Wei Xu

    发明人： Yihong Gong ,  Mei Han ,  Wei Xu

    IPC分类号： G06K9/34

    CPC分类号： G06K9/38 ,  G06T7/12 ,  G06T7/181 ,  G06T7/194 ,  G06T7/215 ,  G06T7/277 ,  G06T2207/10016 ,  H04N7/141

    摘要： A fully automatic, computationally efficient segmentation method of video employing sequential clustering of sparse image features. Both edge and corner features of a video scene are employed to capture an outline of foreground objects and the feature clustering is built on motion models which work on any type of object and moving/static camera in which two motion layers are assumed due to camera and/or foreground and the depth difference between the foreground and background. Sequential linear regression is applied to the sequences and the instantaneous replacements of image features in order to compute affine motion parameters for foreground and background layers and consider temporal smoothness simultaneously. The Foreground layer is then extracted based upon sparse feature clustering which is time efficient and refined incrementally using Kalman filtering.

    摘要翻译： 一种使用稀疏图像特征的顺序聚类的全自动，计算效率高的视频分割方法。 使用视频场景的边缘和角落特征来捕获前景对象的轮廓，并且特征聚类建立在对任何类型的对象和移动/静态相机工作的运动模型上，其中由于相机而假设两个运动层， /或前景和前景和背景之间的深度差。 序列线性回归应用于图像特征的序列和瞬时替换，以便计算前景和背景层的仿射运动参数，同时考虑时间平滑度。 然后基于稀疏特征聚类提取前景层，这是使用卡尔曼滤波进行时间有效和精确地提取的。

    Soft edge smoothness prior and application on alpha channel super resolution
    10.
    发明授权
    Soft edge smoothness prior and application on alpha channel super resolution 有权
    软边缘光滑度先于Alpha通道超分辨率应用

    公开(公告)号：US08335403B2

    公开(公告)日：2012-12-18

    申请号：US11869906

    申请日：2007-10-10

    申请人： Shengyang Dai ,  Mei Han ,  Wei Xu ,  Ying Wu ,  Yihong Gong

    发明人： Shengyang Dai ,  Mei Han ,  Wei Xu ,  Ying Wu ,  Yihong Gong

    IPC分类号： G06K9/32

    CPC分类号： G06T3/403

    摘要： Systems and methods are disclosed for processing a low resolution image by performing a high resolution edge segment extraction on the low resolution image; performing an image super resolution on each edge segment; performing reconstruction constraint reinforcement; and generating a high quality image from the low quality image.

    摘要翻译： 公开了通过在低分辨率图像上执行高分辨率边缘段提取来处理低分辨率图像的系统和方法; 在每个边缘片段上执行图像超分辨率; 执行重建约束加固; 并从低质量图像生成高质量图像。