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

US20100202681A1 DETECTING DEVICE OF SPECIAL SHOT OBJECT AND LEARNING DEVICE AND METHOD THEREOF 有权
标题翻译：检测特殊拍摄对象和学习装置的装置及其方法
公开(公告)号：US20100202681A1
公开(公告)日：2010-08-12
申请号：US12602635
申请日：2008-05-30
申请人： Haizhou Ai , Yuan Li , Shihong Lao , Takayoshi Yamashita
发明人： Haizhou Ai , Yuan Li , Shihong Lao , Takayoshi Yamashita
IPC分类号： G06K9/62
CPC分类号： G06K9/6257 , G06K9/00248
摘要： The invention discloses a detecting device for specific subjects and a learning device and method thereof. The detecting device for specific subjects includes an input unit, one or more strong classifying units, a storage unit and a judging unit, wherein the input unit is used for inputting images to be detected; the strong classifying units are used for carrying out strong classification to the image, each strong classifying unit includes one or more weak classifying units, and the weak classifying unit carries out weak classification to the image with a weak classifying template; the storage unit stores the weak classifying template used by the weak classifying unit; and the judging unit judges whether or not the image contains specific subjects according to the classification result of the strong classifying unit. The detecting device for specific subjects also includes an incremental sample input unit and a learning unit, wherein the incremental sample input unit is used for inputting data for incremental learning, namely for inputting an incremental learning sample, which is data undetected and wrongly detected by the detecting device or other detecting devices for specific subjects; the learning unit is used for updating the weak classifying template stored in the storage unit according to the incremental learning sample inputted by the incremental sample input unit.
摘要翻译：本发明公开了一种特定对象的检测装置及其学习装置及其方法。用于特定对象的检测装置包括输入单元，一个或多个强分类单元，存储单元和判断单元，其中输入单元用于输入要检测的图像; 强分类单位用于对图像进行强分类，每个强分类单位包括一个或多个弱分类单位，弱分类单位用弱分类模板对图像进行弱分类; 存储单元存储由弱分类单元使用的弱分类模板; 并且判断单元根据强分类单元的分类结果判断图像是否包含特定对象。用于特定主体的检测装置还包括增量采样输入单元和学习单元，其中增量采样输入单元用于输入用于增量学习的数据，即用于输入增量学习样本，该增量学习样本是未被检测到并被错误检测的数据用于特定对象的检测装置或其他检测装置; 学习单元用于根据由增量抽样输入单元输入的递增学习样本来更新存储在存储单元中的弱分类模板。

2. 发明授权

US08548195B2 Tracking method and device adopting a series of observation models with different life spans 有权
标题翻译：跟踪方法和装置采用不同寿命的一系列观察模型
公开(公告)号：US08548195B2
公开(公告)日：2013-10-01
申请号：US12664588
申请日：2008-06-13
申请人： Haizhou Ai , Yuan Li , Shihong Lao , Takayoshi Yamashita
发明人： Haizhou Ai , Yuan Li , Shihong Lao , Takayoshi Yamashita
IPC分类号： G06K9/00
CPC分类号： G06T7/277 , G06T2207/10016 , G06T2207/30201
摘要： The present invention relates to a tracking method and a tracking device adopting multiple observation models with different life spans. The tracking method is suitable for tracking an object in a low frame rate video or with abrupt motion, and uses three observation models with different life spans to track and detect a specific subject in frame images of a video sequence. An observation model I performs online learning with one frame image prior to the current image, an observation model II performs online learning with five frames prior to the current image, and an observation model III is offline trained. The three observation models are combined by a cascade particle filter so that the specific subject in the low frame rate video or the object with abrupt motion can be tracked quickly and accurately.
摘要翻译：本发明涉及采用具有不同寿命的多个观察模型的跟踪方法和跟踪装置。跟踪方法适用于跟踪低帧率视频或突然运动的对象，并且使用具有不同寿命的三个观察模型来跟踪和检测视频序列的帧图像中的特定主体。观察模型I在当前图像之前用一帧图像执行在线学习，观察模型II在当前图像之前用五帧执行在线学习，并且观察模型III被离线训练。三个观察模型通过级联粒子滤波器组合，使得低帧率视频中的特定对象或具有突然运动的对象能够被快速准确地跟踪。

3. 发明申请

US20100195870A1 TRACKING METHOD AND DEVICE ADOPTING A SERIES OF OBSERVATION MODELS WITH DIFFERENT LIFE SPANS 有权
标题翻译：跟踪方法和设备采用不同生活模式的观察模型系列
公开(公告)号：US20100195870A1
公开(公告)日：2010-08-05
申请号：US12664588
申请日：2008-06-13
申请人： Haizhou Ai , Yuan Li , Shihong Lao , Takayoshi Yamashita
发明人： Haizhou Ai , Yuan Li , Shihong Lao , Takayoshi Yamashita
IPC分类号： G06K9/62
CPC分类号： G06T7/277 , G06T2207/10016 , G06T2207/30201
摘要： The present invention relates to a tracking method and a tracking device adopting multiple observation models with different life spans. The tracking method is suitable for tracking an object in a low frame rate video or with abrupt motion, and uses three observation models with different life spans to track and detect a specific subject in frame images of a video sequence. An observation model I performs online learning with one frame image prior to the current image, an observation model II performs online learning with five frames prior to the current image, and an observation model III is offline trained. The three observation models are combined by a cascade particle filter so that the specific subject in the low frame rate video or the object with abrupt motion can be tracked quickly and accurately.
摘要翻译：本发明涉及采用具有不同寿命的多个观察模型的跟踪方法和跟踪装置。跟踪方法适用于跟踪低帧率视频或突然运动的对象，并且使用具有不同寿命的三个观察模型来跟踪和检测视频序列的帧图像中的特定主体。观察模型I在当前图像之前用一帧图像执行在线学习，观察模型II在当前图像之前用五帧执行在线学习，并且观察模型III被离线训练。三个观察模型通过级联粒子滤波器组合，使得低帧率视频中的特定对象或具有突然运动的对象能够被快速准确地跟踪。

4. 发明授权

US07876965B2 Apparatus and method for detecting a particular subject 有权
标题翻译：用于检测特定受试者的装置和方法
公开(公告)号：US07876965B2
公开(公告)日：2011-01-25
申请号：US11543158
申请日：2006-10-05
申请人： Haizhou Ai , Chang Huang , Yuan Li , Shihong Lao
发明人： Haizhou Ai , Chang Huang , Yuan Li , Shihong Lao
IPC分类号： G06K9/70
CPC分类号： G06K9/6257 , G06K9/00208 , G06K9/00228 , G06K9/6282
摘要： An apparatus and a method for detecting from an image a particular subject corresponding to multiple views of the subject by dividing a particular subject space into a plurality of subject subspaces and further dividing a subject subspace into subject subspaces representing multiple views; configuring a tree-structured detector wherein the tree structure has a root node that covers all subject subspaces and has a plurality of branches, each branch corresponding to a child node that covers at least one subject subspace; training each node to determine which nodes in the adjacent lower layer the images of the subject in the corresponding nodes should be sent.
摘要翻译：一种用于通过将特定对象空间划分成多个对象子空间并且将主题子空间划分成表示多个视图的对象子空间来检测与对象的多个视图相对应的特定对象的图像的装置和方法; 配置树结构检测器，其中所述树结构具有覆盖所有对象子空间并具有多个分支的根节点，每个分支对应于覆盖至少一个主题子空间的子节点; 训练每个节点以确定相邻下层中哪些节点应该发送相应节点中的对象的图像。

5. 发明申请

US20070086660A1 Apparatus and method for detecting a particular subject 有权
标题翻译：用于检测特定受试者的装置和方法
公开(公告)号：US20070086660A1
公开(公告)日：2007-04-19
申请号：US11543158
申请日：2006-10-05
申请人： Haizhou Ai , Chang Huang , Yuan Li , Shihong Lao
发明人： Haizhou Ai , Chang Huang , Yuan Li , Shihong Lao
IPC分类号： G06K9/68
CPC分类号： G06K9/6257 , G06K9/00208 , G06K9/00228 , G06K9/6282
摘要： An apparatus and a method for detecting from an image a particular subject corresponding to multiple views of the subject by dividing a particular subject space into a plurality of subject subspaces and further dividing a subject subspace into subject subspaces representing multiple views; configuring a tree-structured detector wherein the tree structure has a root node that covers all subject subspaces and has a plurality of branches, each branch corresponding to a child node that covers at least one subject subspace; training each node to determine which nodes in the adjacent lower layer the images of the subject in the corresponding nodes should be sent.
摘要翻译：一种用于通过将特定对象空间划分成多个对象子空间并且将主题子空间划分成表示多个视图的对象子空间来检测与对象的多个视图相对应的特定对象的图像的装置和方法; 配置树结构检测器，其中所述树结构具有覆盖所有对象子空间并具有多个分支的根节点，每个分支对应于覆盖至少一个主题子空间的子节点; 训练每个节点以确定相邻下层中哪些节点应该发送相应节点中的对象的图像。

6. 发明申请

US20180267929A1 Reconfigurable Parallel Processing 审中-公开
公开(公告)号：US20180267929A1
公开(公告)日：2018-09-20
申请号：US15919681
申请日：2018-03-13
申请人： Yuan Li , Jianbin Zhu
发明人： Yuan Li , Jianbin Zhu
IPC分类号： G06F15/80 , G06F9/30
摘要： Processors, systems and methods are provided for thread level parallel processing. A processor may comprise a plurality of processing elements (PEs) that each may comprise a configuration buffer, a sequencer coupled to the configuration buffer of each of the plurality of PEs and configured to distribute one or more PE configurations to the plurality of PEs, and a gasket memory coupled to the plurality of PEs and being configured to store at least one PE execution result to be used by at least one of the plurality of PEs during a next PE configuration.

7. 发明授权

US09805265B2 Surveillance camera control device and video surveillance system 有权
公开(公告)号：US09805265B2
公开(公告)日：2017-10-31
申请号：US14403771
申请日：2012-05-30
申请人： Masaya Itoh , Ryo Yumiba , Yuan Li
发明人： Masaya Itoh , Ryo Yumiba , Yuan Li
IPC分类号： G06K9/00 , H04N7/18 , G08B13/196
CPC分类号： G06K9/00718 , G06K9/00771 , G06K2009/00738 , G08B13/19641 , G08B13/19693 , H04N7/181
摘要： In a video surveillance system, confirming videos from plurality of cameras causes a heavy burden on surveillance officers, and it is difficult to select a suitable video for observation.A video surveillance system includes a plurality of cameras which pick up images in a surveillance area, and a recognition unit which detects an object from videos acquired by the plurality of cameras. In the case where an object is detected in a surveillance area where images are picked up duplicately by the plurality of cameras, the recognition unit acquires a recognition result that is a feature quantity of the object for each camera. A display selection unit is, provided which, on the basis of the recognition result and a degree of priority of the recognition result, prioritizes the video from each of the cameras according to the degree of priority.

8. 发明授权

US08918695B2 Methods and apparatus for early stop algorithm of turbo decoding 有权
标题翻译： turbo解码的早期停止算法的方法和装置
公开(公告)号：US08918695B2
公开(公告)日：2014-12-23
申请号：US12973951
申请日：2010-12-21
申请人： Yuan Li , Jianbin Zhu , Tao Zhang
发明人： Yuan Li , Jianbin Zhu , Tao Zhang
IPC分类号： H03M13/00 , H04L1/00
CPC分类号： H04L1/005 , H04L1/006
摘要： Methods and apparatus for early stop algorithm of turbo decoding are disclosed. An example method comprises of combination of comparing of hard decisions of soft outputs of the current iteration and the previous iteration and comparing the minimum log likelihood results against a threshold. The decoding iteration is stopped once the hard decisions are matched and the minimum soft decoding result exceeds a threshold.
摘要翻译：公开了用于turbo解码的早期停止算法的方法和装置。一个示例性方法包括将当前迭代的软输出的硬判决与先前迭代进行比较并将最小对数似然结果与阈值进行比较的组合。一旦硬判决匹配并且最小软解码结果超过阈值，则停止解码迭代。

9. 发明授权

US08896124B2 Via network structures and method therefor 有权
标题翻译：通过网络结构及其方法
公开(公告)号：US08896124B2
公开(公告)日：2014-11-25
申请号：US13079579
申请日：2011-04-04
申请人： Yuan Li , Som Nath , Maarten Jeroen Van Dort
发明人： Yuan Li , Som Nath , Maarten Jeroen Van Dort
IPC分类号： H01L23/48 , H01L23/52 , H01L23/00
CPC分类号： H01L21/76877 , H01L21/76805 , H01L24/05 , H01L2224/02166 , H01L2224/0392 , H01L2224/0401 , H01L2224/04042 , H01L2224/05025 , H01L2224/05086 , H01L2224/05088 , H01L2224/05093 , H01L2224/05096 , H01L2224/05098 , H01L2224/05556 , H01L2224/45124 , H01L2924/00013 , H01L2924/00014 , H01L2924/01029 , H01L2924/01074 , H01L2924/01022 , H01L2924/01007 , H01L2924/01073 , H01L2224/13099 , H01L2224/13599 , H01L2224/05599 , H01L2224/05099 , H01L2224/29099 , H01L2224/29599 , H01L2924/00 , H01L2224/48
摘要： A circuit device is configured with robust circuit connectors. In connection with various example embodiments, an integrated circuit device includes one or more via network layers below a bond pad contact, connecting the bond pad contact with one or more underlying metal layers. Each via network layer includes a plurality of via strips extending about parallel to the bond pad contact and in different directions to structurally support the bond pad contact.
摘要翻译：电路设备配置有鲁棒的电路连接器。结合各种示例实施例，集成电路器件包括在接合焊盘触点下方的一个或多个通孔网络层，将接合焊盘触点与一个或多个下面的金属层相连接。每个通孔网络层包括多个通孔，其平行于接合焊盘触点并沿不同的方向延伸，以在结构上支撑接合焊盘触点。

10. 发明授权

US08829245B2 3-aminomethyl-3, 5, 5-trimethyl cyclohexylamine preparation method 有权
标题翻译： 3-氨基甲基-3,5,5-三甲基环己胺制备方法
公开(公告)号：US08829245B2
公开(公告)日：2014-09-09
申请号：US14113907
申请日：2011-09-06
申请人： Changsheng Chen , Yuan Li , Wenjuan Zhao , Hongyin Cui , Weiqi Hua
发明人： Changsheng Chen , Yuan Li , Wenjuan Zhao , Hongyin Cui , Weiqi Hua
IPC分类号： C07C209/48 , C07C209/62 , C07C211/36
CPC分类号： C07C209/62 , C07C209/48 , C07C209/52 , C07C211/36 , C07C253/30 , C07C2601/14 , C07C255/61 , C07C255/46
摘要： Provided is a 3-aminomethyl-3,5,5-trimethylcyclohexylamine preparation method. A feeding flow of 3-cyano-3,5,5-trimethylcyclohexylamine is reacted with NH3 and hydrogen in the presence of a hydrogenation catalyst; the method is characterized by: firstly adding a basic compound to the feeding flow of 3-cyano-3,5,5-trimethylcyclohexylamine, and then after a portion of 3-cyano-3,5,5-trimethylcyclohexylamine has reacted, adding an acidic compound to reaction materials for further hydrogenation reaction to prepare the product. The method ensures that the aminonitrile content in the product is low, thus effectively reducing the duration of the reaction and greatly reducing the consumption of the catalyst during the hydrogenation reaction process.
摘要翻译：提供了3-氨基甲基-3,5,5-三甲基环己胺的制备方法。在氢化催化剂存在下，使3-氰基-3,5,5-三甲基环己胺的进料流与NH 3和氢气反应; 该方法的特征在于：首先向3-氰基-3,5,5-三甲基环己胺的进料流中加入碱性化合物，然后在一部分3-氰基-3,5,5-三甲基环己胺反应后，加入酸性化合物与反应物进行进一步氢化反应制备产物。该方法可确保产品中的氨腈含量低，有效降低反应持续时间，大大降低催化剂在氢化反应过程中的消耗。

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