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

US20100266159A1 HUMAN TRACKING APPARATUS, HUMAN TRACKING METHOD, AND HUMAN TRACKING PROCESSING PROGRAM 有权
标题翻译：人体跟踪装置，人体追踪方法和人体追踪处理程序
公开(公告)号：US20100266159A1
公开(公告)日：2010-10-21
申请号：US12427353
申请日：2009-04-21
申请人： Kazuya UEKI , Yihong Gong , Fengjun Lv
发明人： Kazuya UEKI , Yihong Gong , Fengjun Lv
IPC分类号： G06K9/00
CPC分类号： G06K9/00362 , G06K9/00261 , G06K9/00295
摘要： A human tracking apparatus and method capable of highly accurately tracking the movement of persons photographed in moving images includes: an image memory 107 that stores an inputted frame image; a human detecting unit 101 that detects persons photographed in the inputted frame image; a candidate registering unit 106 that registers already detected persons as candidates; a similarity index calculating unit 102 that calculates similarity indices indicating the similarity between the persons detected in the inputted frame image and the registered candidates for two or more types of parameters based on the stored frame images in relation to all combinations of the persons and the candidates; a normalizing unit 103 that normalizes the similarity indices; an integrating unit 104 that integrates the normalized indices for each combination of the detected persons and the candidates; and a tracking unit 105 that identifies a person the same as an arbitrary candidate based on the similarity indices.
摘要翻译：能够高精度地跟踪在运动图像中拍摄的人的移动的人体跟踪装置和方法包括：存储输入的帧图像的图像存储器107; 人物检测单元101，其检测在输入的帧图像中拍摄的人物; 将已经检测到的人登记为候选的候选登记单元106; 相似度计算单元102，其基于与人和候选者的所有组合相关联的所存储的帧图像，计算指示在输入的帧图像中检测到的人与两个或多个类型的参数之间的相似度的相似性 ; 归一化单元103，其使相似性指数标准化; 整合单元104，其将检测到的人和候选的每个组合的归一化指数进行积分; 以及跟踪单元105，其基于相似性索引来识别与任意候选者相同的人。

2. 发明申请

US20090296985A1 Efficient Multi-Hypothesis Multi-Human 3D Tracking in Crowded Scenes 有权
标题翻译：在拥挤的场景中的有效的多假设多人类3D跟踪
公开(公告)号：US20090296985A1
公开(公告)日：2009-12-03
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 , H04N5/225
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。

3. 发明授权

US08866876B2 Color correction for multiple video objects in telepresence applications 有权
标题翻译：远程呈现应用中的多个视频对象的颜色校正
公开(公告)号：US08866876B2
公开(公告)日：2014-10-21
申请号：US13467672
申请日：2012-05-09
申请人： Gregory W. Cook , Fengjun Lv , Antontius Kalker
发明人： Gregory W. Cook , Fengjun Lv , Antontius Kalker
IPC分类号： H04N7/15 , H04N19/20
CPC分类号： H04N7/15 , H04N7/142 , H04N7/147 , H04N19/20 , H04N19/80 , H04N19/85
摘要： A method comprising rendering a video display signal comprising combining local illumination video objects from different sources into each frame of a plurality of frames, wherein the local illumination video objects are video objects on which chromatic adaptation was performed using an illumination reference common to all video objects. An apparatus comprising a processor configured to render a video display signal comprising combining local illumination video objects from different sources into each frame of a plurality of frames, wherein the local illumination video objects are video objects on which chromatic adaptation was performed using an illumination reference common to all video objects.
摘要翻译：一种方法，包括渲染视频显示信号，包括将来自不同源的局部照明视频对象组合到多个帧的每个帧中，其中，所述局部照明视频对象是使用所有视频对象共同的照明参考来执行色彩适配的视频对象。一种装置，包括：处理器，被配置为呈现视频显示信号，包括将来自不同源的局部照明视频对象组合到多个帧的每个帧中，其中所述局部照明视频对象是使用照明参考公共到所有视频对象。

4. 发明授权

US08582807B2 Systems and methods for determining personal characteristics 有权
标题翻译：用于确定个人特征的系统和方法
公开(公告)号：US08582807B2
公开(公告)日：2013-11-12
申请号：US12790979
申请日：2010-05-31
申请人： Ming Yang , Shenghuo Zhu , Fengjun Lv , Kai Yu
发明人： Ming Yang , Shenghuo Zhu , Fengjun Lv , Kai Yu
IPC分类号： G06K9/00
CPC分类号： G06K9/00248 , G06K9/4628 , G06K2009/00322
摘要： Systems and methods are disclosed for determining personal characteristics from images by generating a baseline gender model and an age estimation model using one or more convolutional neural networks (CNNs); capturing correspondences of faces by face tracking, and applying incremental learning to the CNNs and enforcing correspondence constraint such that CNN outputs are consistent and stable for one person.
摘要翻译：公开了用于通过生成基线性别模型和使用一个或多个卷积神经网络（CNN）的年龄估计模型来确定来自图像的个人特征的系统和方法; 通过面部跟踪获取面部对应关系，并将增量学习应用于CNN，并执行对应约束，使得CNN输出对于一个人来说是一致和稳定的。

5. 发明申请

US20110222724A1 SYSTEMS AND METHODS FOR DETERMINING PERSONAL CHARACTERISTICS 有权
标题翻译：用于确定个人特征的系统和方法
公开(公告)号：US20110222724A1
公开(公告)日：2011-09-15
申请号：US12790979
申请日：2010-05-31
申请人： Ming Yang , Shenghuo Zhu , Fengjun Lv , Kai Yu
发明人： Ming Yang , Shenghuo Zhu , Fengjun Lv , Kai Yu
IPC分类号： G06K9/62
CPC分类号： G06K9/00248 , G06K9/4628 , G06K2009/00322
摘要： Systems and methods are disclosed for determining personal characteristics from images by generating a baseline gender model and an age estimation model using one or more convolutional neural networks (CNNs); capturing correspondences of faces by face tracking, and applying incremental learning to the CNNs and enforcing correspondence constraint such that CNN outputs are consistent and stable for one person.
摘要翻译：公开了用于通过生成基线性别模型和使用一个或多个卷积神经网络（CNN）的年龄估计模型来确定来自图像的个人特征的系统和方法; 通过面部跟踪获取面部对应关系，并将增量学习应用于CNN，并执行对应约束，使得CNN输出对于一个人来说是一致和稳定的。

6. 发明授权

US08577154B2 Automated single viewpoint human action recognition by matching linked sequences of key poses 有权
标题翻译：通过匹配关键姿势的连锁序列，自动单点观察人类行为识别
公开(公告)号：US08577154B2
公开(公告)日：2013-11-05
申请号：US12483050
申请日：2009-06-11
申请人： Ramakant Nevatia , Fengjun Lv
发明人： Ramakant Nevatia , Fengjun Lv
IPC分类号： G06K9/00 , G06K9/62 , G06K9/36 , G06T13/00 , H04N7/18 , H04N5/225
CPC分类号： G06K9/00342 , G06K9/4642
摘要： An automated human action recognition system may automatically recognize one or more actions of a human from 2D input image data representing a sequential series of input images of the human performing the one or more actions. Each input image may be from an unknown viewpoint. A computer memory system may contain 2D reference image data representing a plurality of reference actions which a human may perform. The 2D reference image data may include a plurality of linked sequences of key poses, including a linked sequence of key poses for each reference action. For each reference action, each key pose within the linked sequence of key poses for the reference action may consist essentially of 2D image data that is representative of a human figure performing the reference action at a selected point during the reference action. The timing of the selected points within the linked sequence of key poses for the reference action may be based on changes in the position of the human figure during the performance of the reference action. The linked sequence of key poses for the reference action may uniquely distinguish it from the linked sequence of key poses for all of the other reference actions. A computer processing system may be configured to determine which of the reference actions best matches the 2D input image data with no knowledge of the viewpoint of the 2D input image data.
摘要翻译：自动人体动作识别系统可以从表示执行一个或多个动作的人的输入图像的连续序列的2D输入图像数据自动识别人的一个或多个动作。每个输入图像可以来自未知视点。计算机存储器系统可以包含表示人可以执行的多个参考动作的2D参考图像数据。 2D参考图像数据可以包括多个关键姿势的链接序列，包括用于每个参考动作的链接的关键姿势序列。对于每个参考动作，用于参考动作的链接的关键姿势序列内的每个关键姿势可以基本上由代表在参考动作期间在选定点处执行参考动作的人物图形的2D图像数据组成。在参考动作的关键姿势的链接序列内的所选点的定时可以基于在执行参考动作期间人物的位置的变化。用于参考动作的关键姿势的链接序列可以将其与所有其他参考动作的关键姿势的链接序列唯一地区分开。计算机处理系统可以被配置为确定哪个参考动作与2D输入图像数据最佳匹配，而不知道2D输入图像数据的视点。

7. 发明授权

US08374979B2 Fast image parsing by graph adaptive dynamic programming (GADP) performing classification, detection, and segmentation simultaneously 有权
标题翻译：通过图形自适应动态规划（GADP）进行快速图像解析，同时执行分类，检测和分割
公开(公告)号：US08374979B2
公开(公告)日：2013-02-12
申请号：US12814449
申请日：2010-06-12
申请人： Xi Zhou , Jinjun Wang , Fengjun Lv , Kai Yu
发明人： Xi Zhou , Jinjun Wang , Fengjun Lv , Kai Yu
IPC分类号： G06F15/18
CPC分类号： G06K9/469 , G06K9/6892
摘要： Systems and methods are disclosed to perform image parsing on one or more images by identifying a set of similar regions from each image; assigning one or more region labels to each region and generating multiple hypotheses for region label assignment; and detecting class, location and boundary of each object in the image, wherein object classification, detection and segmentation are performed jointly during image parsing.
摘要翻译：公开了系统和方法，以通过从每个图像识别一组相似的区域来对一个或多个图像执行图像解析; 为每个区域分配一个或多个区域标签，并为区域标签分配生成多个假设; 并检测图像中每个对象的类别，位置和边界，其中在图像解析期间共同执行对象分类，检测和分割。

8. 发明授权

US08233711B2 Locality-constrained linear coding systems and methods for image classification 有权
标题翻译：局部约束线性编码系统和图像分类方法
公开(公告)号：US08233711B2
公开(公告)日：2012-07-31
申请号：US12822424
申请日：2010-06-24
申请人： Jinjun Wang , Fengjun Lv , Kai Yu
发明人： Jinjun Wang , Fengjun Lv , Kai Yu
IPC分类号： G06K9/00
CPC分类号： G06K9/4671 , G06K9/6223
摘要： Systems and methods are disclosed for classifying an input image by detecting one or more feature points on the input image; extracting one or more descriptors from each feature point; applying a codebook to quantize each descriptor and generate code from each descriptor; applying spatial pyramid matching to generate histograms; and concatenating histograms from all sub-regions to generate a final representation of the image for classification.
摘要翻译：公开了通过检测输入图像上的一个或多个特征点来对输入图像进行分类的系统和方法; 从每个特征点提取一个或多个描述符; 应用码本量化每个描述符并从每个描述符生成代码; 应用空间金字塔匹配来生成直方图; 以及从所有子区域连接直方图以生成用于分类的图像的最终表示。

9. 发明申请

US20100034462A1 Automated Single Viewpoint Human Action Recognition by Matching Linked Sequences of Key Poses 有权
标题翻译：通过匹配关键姿势的相关序列，自动单观点人类行为识别
公开(公告)号：US20100034462A1
公开(公告)日：2010-02-11
申请号：US12483050
申请日：2009-06-11
申请人： Ramakant Nevatia , Fengjun Lv
发明人： Ramakant Nevatia , Fengjun Lv
IPC分类号： G06K9/46
CPC分类号： G06K9/00342 , G06K9/4642
摘要： An automated human action recognition system may automatically recognize one or more actions of a human from 2D input image data representing a sequential series of input images of the human performing the one or more actions. Each input image may be from an unknown viewpoint. A computer memory system may contain 2D reference image data representing a plurality of reference actions which a human may perform. The 2D reference image data may include a plurality of linked sequences of key poses, including a linked sequence of key poses for each reference action. For each reference action, each key pose within the linked sequence of key poses for the reference action may consist essentially of 2D image data that is representative of a human figure performing the reference action at a selected point during the reference action. The timing of the selected points within the linked sequence of key poses for the reference action may be based on changes in the position of the human figure during the performance of the reference action. The linked sequence of key poses for the reference action may uniquely distinguish it from the linked sequence of key poses for all of the other reference actions. A computer processing system may be configured to determine which of the reference actions best matches the 2D input image data with no knowledge of the viewpoint of the 2D input image data.
摘要翻译：自动人体动作识别系统可以从表示执行一个或多个动作的人的输入图像的连续序列的2D输入图像数据自动识别人的一个或多个动作。每个输入图像可以来自未知视点。计算机存储器系统可以包含表示人可以执行的多个参考动作的2D参考图像数据。 2D参考图像数据可以包括多个关键姿势的链接序列，包括用于每个参考动作的链接的关键姿势序列。对于每个参考动作，用于参考动作的链接的关键姿势序列内的每个关键姿势可以基本上由代表在参考动作期间在选定点处执行参考动作的人物图形的2D图像数据组成。在参考动作的关键姿势的链接序列内的所选点的定时可以基于在执行参考动作期间人物的位置的变化。用于参考动作的关键姿势的链接序列可以将其与所有其他参考动作的关键姿势的链接序列唯一地区分开。计算机处理系统可以被配置为确定哪个参考动作与2D输入图像数据最佳匹配，而不知道2D输入图像数据的视点。

10. 发明授权

US08098891B2 Efficient multi-hypothesis multi-human 3D tracking in crowded scenes 有权
标题翻译：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。

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