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

US20130084006A1 Method and Apparatus for Foreground Object Detection 有权
标题翻译：前景物体检测方法与装置
公开(公告)号：US20130084006A1
公开(公告)日：2013-04-04
申请号：US13248242
申请日：2011-09-29
申请人： Tao Zhang , Yu-Pao Tsai
发明人： Tao Zhang , Yu-Pao Tsai
IPC分类号： G06K9/34
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10028
摘要： The present invention utilizes depth images captured by a depth camera to detect foreground/background. In one embodiment, the method comprises establishing a single background distribution model, updating the background distribution model if a new depth value for the pixel can be represented by the background distribution model, skipping update of the background distribution model if the pixel is before the background, and replacing the background distribution model if the pixel is behind the background. In case that the background distribution model does not exist initially, a new background distribution model is created. In one embodiment of the present invention, the non-meaningful pixels are handled. In another embodiment, fluctuation of the depth value due to noise is handled by using a candidate background distribution model. In yet another embodiment, the noise for pixels around object edges is handled by using a mixture of two background distribution models.
摘要翻译：本发明利用深度相机拍摄的深度图像来检测前景/背景。在一个实施例中，该方法包括建立单个背景分布模型，如果像素的新深度值可以由背景分布模型表示，则更新背景分布模型，如果像素在背景之前跳过背景分布模型的更新并且如果像素在背景之后，则替换背景分布模型。在背景分布模型最初不存在的情况下，将创建一个新的背景分布模型。在本发明的一个实施例中，处理非有意义的像素。在另一个实施例中，通过使用候选背景分布模型来处理由噪声引起的深度值的波动。在另一个实施例中，通过使用两个背景分布模型的混合来处理对象边缘周围的像素的噪声。

2. 发明授权

US08873852B2 Method and apparatus for foreground object detection 有权
标题翻译：用于前景对象检测的方法和装置
公开(公告)号：US08873852B2
公开(公告)日：2014-10-28
申请号：US13248242
申请日：2011-09-29
申请人： Tao Zhang , Yu-Pao Tsai
发明人： Tao Zhang , Yu-Pao Tsai
IPC分类号： G06K9/34 , G06K9/00 , G06T7/00
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10028
摘要： The present invention utilizes depth images captured by a depth camera to detect foreground/background. The method comprises establishing a single background distribution model, updating the background distribution model if a new depth value for the pixel can be represented by the background distribution model, skipping update of the background distribution model if the pixel is before the background, and replacing the background distribution model if the pixel is behind the background. In case that the background distribution model does not exist initially, a new background distribution model is created. The fluctuation of the depth value due to noise is handled by using a candidate background distribution model. Furthermore, the noise for pixels around object edges is handled by using a mixture of two background distribution models.
摘要翻译：本发明利用深度相机拍摄的深度图像来检测前景/背景。该方法包括建立单个背景分布模型，如果用于像素的新的深度值可以由背景分布模型表示，则跳过背景分布模型，如果像素在背景之前跳过背景分布模型的更新，则更新背景分布模型背景分布模型如果像素背后的背景。在背景分布模型最初不存在的情况下，将创建一个新的背景分布模型。通过使用候选背景分布模型来处理由噪声引起的深度值的波动。此外，通过使用两个背景分布模型的混合来处理对象边缘周围的像素的噪声。

3. 发明申请

US20170078807A1 PACKET LOSS CONCEALMENT FOR BIDIRECTIONAL EAR-TO-EAR STREAMING 有权
标题翻译：双向远程流量分组丢失隐患
公开(公告)号：US20170078807A1
公开(公告)日：2017-03-16
申请号：US14854716
申请日：2015-09-15
申请人： Frederic Philippe Denis Mustiere , Ivo Merks , Tao Zhang
发明人： Frederic Philippe Denis Mustiere , Ivo Merks , Tao Zhang
IPC分类号： H04R25/00 , G10L19/005
CPC分类号： H04R25/554 , G10L19/005 , H04R25/552
摘要： Embodiments of packet loss concealment in a hearing assistance device are generally described herein. A method for packet loss concealment can include receiving, at a first hearing assistance device, a first encoded packet stream from a second hearing assistance device and a signal frame. The method can include encoding, at the first hearing assistance device, the signal frame and determining, at the first hearing assistance device, that a second encoded packet stream was not received from the second hearing assistance device within a predetermined time. In response to determining that the second encoded packet stream was not received, the method can include decoding, at the first hearing assistance device, the encoded signal frame, and outputting the signal frame and the decoded signal frame.
摘要翻译：这里一般地描述助听装置中的分组丢失隐藏的实施例。一种用于分组丢失隐藏的方法可以包括在第一听力辅助装置处接收来自第二助听装置的第一编码分组流和信号帧。该方法可以包括在第一听力辅助装置处编码信号帧，并且在第一听力辅助装置处确定在预定时间内没有从第二听力辅助装置接收到第二编码分组流。响应于确定未接收到第二编码分组流，该方法可以包括在第一听力辅助设备处对编码的信号帧进行解码，以及输出信号帧和解码的信号帧。

4. 发明申请

US20160302014A1 NEURAL NETWORK-DRIVEN FREQUENCY TRANSLATION 审中-公开
标题翻译：神经网络驱动频率翻译
公开(公告)号：US20160302014A1
公开(公告)日：2016-10-13
申请号：US15092487
申请日：2016-04-06
申请人： Kelly Fitz , Tao Zhang , Buye Xu , Mohammad Abdollahi
发明人： Kelly Fitz , Tao Zhang , Buye Xu , Mohammad Abdollahi
IPC分类号： H04R25/00 , G06N3/08 , G10L25/84
CPC分类号： H04R25/353 , G06N3/08 , G10L25/84 , H04R25/507 , H04R25/55 , H04R2225/021 , H04R2225/023 , H04R2225/025
摘要： Disclosed herein, among other things, are apparatus and methods for neural network-driven frequency translation for hearing assistance devices. Various embodiments include a method of signal processing an input signal in a hearing assistance device, the hearing assistance device including a receiver and a microphone. The method includes performing neural network processing to train a processor to identify acoustic features in a plurality of audio signals and predict target outputs for the plurality of audio signals, and using the trained processor to control frequency translation of the input signal.
摘要翻译：这里公开的是用于听力辅助装置的神经网络驱动频率转换的装置和方法。各种实施例包括在听力辅助装置中信号处理输入信号的方法，所述助听装置包括接收器和麦克风。该方法包括执行神经网络处理以训练处理器以识别多个音频信号中的声学特征并且预测多个音频信号的目标输出，以及使用经过训练的处理器来控制输入信号的频率转换。

5. 发明授权

US09412335B2 Color calibration and compensation for 3D display systems 有权
标题翻译： 3D显示系统的色彩校准和补偿
公开(公告)号：US09412335B2
公开(公告)日：2016-08-09
申请号：US13816522
申请日：2010-08-19
申请人： Zhe Wang , Jiefu Zhai , Tao Zhang
发明人： Zhe Wang , Jiefu Zhai , Tao Zhang
IPC分类号： G09G5/06 , G09G3/00 , H04N13/04
CPC分类号： G09G5/06 , G09G3/003 , G09G2320/0209 , G09G2320/0606 , G09G2320/0666 , G09G2320/0686 , G09G2320/0693 , H04N13/324 , H04N13/327 , H04N13/332
摘要： A method and system for calibration and compensation of color in a three dimensional display system includes user calibration of individual color channels using a multiplicity of grey screens while viewing with three dimensional glasses. Look-up tables are generated to ease conversion of input pixels to color corrected pixels to pre-distort the color of the pixels being driven by the three dimensional display system. Input pixels are then converted using the look-up tables and color corrected frames are displayed to a user. The pre-distortion effect allows a user to perceive colors in the three dimensional system as intended with the distortions caused by the viewing glasses and other aspects of the three dimensional display system.
摘要翻译：用于在三维显示系统中校准和补偿颜色的方法和系统包括使用多个灰色屏幕的用户校准各个颜色通道，同时用三维眼镜观看。生成查找表以简化输入像素到颜色校正像素的转换，以预先变形由三维显示系统驱动的像素的颜色。然后使用查找表转换输入像素，并且向用户显示颜色校正的帧。预失真效果允许用户以三维显示系统的观看眼镜和其他方面所引起的失真的方式感知三维系统中的颜色。

6. 发明授权

US09307393B2 Peer-to-peer mobility management in heterogeneous IPV4 networks 有权
标题翻译：异构IPV4网络中的对等移动性管理
公开(公告)号：US09307393B2
公开(公告)日：2016-04-05
申请号：US12466914
申请日：2009-05-15
申请人： Yuan-Ying Hsu , Tao Zhang , Chung-Min Chen
发明人： Yuan-Ying Hsu , Tao Zhang , Chung-Min Chen
IPC分类号： G06F15/16 , H04W8/14 , H04L29/12 , H04W80/04 , H04L29/06
CPC分类号： H04W8/14 , H04L29/12066 , H04L29/12349 , H04L29/12396 , H04L29/12405 , H04L61/1511 , H04L61/2507 , H04L61/251 , H04L61/2525 , H04L61/2528 , H04L65/1006 , H04W80/04
摘要： Peer-to-peer mobility management in heterogeneous IP networks provides a peer-to-peer mobility module operable to intercept a data packet received at a communication protocol layer of an Internet Protocol communication stack. A translation table may be stored on memory device. The translation table stores real address of one or more network interfaces and a corresponding virtual address. The peer-to-peer mobility module may be further operable to modify the intercepted data packet using the real address and virtual address stored on the translation table.
摘要翻译：异构IP网络中的对等移动性管理提供了对等移动性模块，其可操作地拦截在因特网协议通信栈的通信协议层处接收的数据分组。翻译表可以存储在存储器设备上。翻译表存储一个或多个网络接口的真实地址和相应的虚拟地址。对等移动性模块可以进一步可操作以使用存储在转换表上的实际地址和虚拟地址来修改拦截的数据分组。

7. 发明授权

US09222090B2 RNA interference target for treating AIDS 有权
标题翻译：治疗艾滋病的RNA干扰目标
公开(公告)号：US09222090B2
公开(公告)日：2015-12-29
申请号：US13584319
申请日：2012-08-13
申请人： Tong Cheng , Tao Zhang , Yali Zhang , Ji Miao , Jun Zhang , Ningshao Xia
发明人： Tong Cheng , Tao Zhang , Yali Zhang , Ji Miao , Jun Zhang , Ningshao Xia
IPC分类号： C12N15/11 , C12N15/113
CPC分类号： C12N15/1132 , C12N2310/11 , C12N2310/12 , C12N2310/14
摘要： The RNAi target sequences, which could be used for treating AIDS through targeting HIV. Based on the target sequences, recombinant expression vectors, packaging vectors and cells were constructed, which express siRNA and/or miRNA and/or ribozyme and/or antisense oligonucleotide for targeting HIV. And the applications of said recombinant expression vectors, packaging vectors and cells in preparing medicament for treating AIDS.
摘要翻译： RNAi靶序列，可用于通过靶向HIV来治疗艾滋病。基于靶序列，构建重组表达载体，包装载体和细胞，其表达用于靶向HIV的siRNA和/或miRNA和/或核酶和/或反义寡核苷酸。以及所述重组表达载体，包装载体和细胞在制备用于治疗AIDS的药物中的应用。

8. 发明授权

US09210518B2 Method and apparatus for microphone matching for wearable directional hearing device using wearer's own voice 有权
标题翻译：用于使用佩戴者自己的声音的可穿戴式定向听力装置的麦克风匹配的方法和装置
公开(公告)号：US09210518B2
公开(公告)日：2015-12-08
申请号：US13251358
申请日：2011-10-03
申请人： Tao Zhang
发明人： Tao Zhang
IPC分类号： H04R3/00 , H04R25/00 , H04R29/00
CPC分类号： H04R25/407 , H04R29/006
摘要： Method and apparatus for microphone matching for wearable directional hearing assistance devices are provided. An embodiment includes a method for matching at least a first microphone to a second microphone, using a user's voice from the user's mouth. The user's voice is processed as received by at least one microphone to determine a frequency profile associated with voice of the user. Intervals are detected where the user is speaking using the frequency profile. Variations in microphone reception between the first microphone and the second microphone are adaptively canceled during the intervals and when the first microphone and second microphone are in relatively constant spatial position with respect to the user's mouth.
摘要翻译：提供了一种用于穿戴式定向听力辅助装置的麦克风匹配的方法和装置。实施例包括使用来自用户嘴部的用户声音来将至少第一麦克风与第二麦克风相匹配的方法。处理用户的话音由至少一个麦克风接收以确定与用户的语音相关联的频率分布。使用频率分布检测用户正在说话的间隔。在第一麦克风和第二麦克风之间的麦克风接收的变化在间隔期间自适应地消除，并且当第一麦克风和第二麦克风相对于用户的嘴处于相对恒定的空间位置时。

9. 发明申请

US20150274705A1 SUBSTITUTED HETEROARYL COMPOUNDS AND METHODS OF USE 有权
标题翻译：取代异腈化合物及其使用方法
公开(公告)号：US20150274705A1
公开(公告)日：2015-10-01
申请号：US14670422
申请日：2015-03-27
申请人： Ning Xi , Minxiong Li , Xiaobo Li , Tao Zhang , Yanjun Wu
发明人： Ning Xi , Minxiong Li , Xiaobo Li , Tao Zhang , Yanjun Wu
IPC分类号： C07D403/14 , A61K45/06 , C07D401/14 , A61K31/527 , A61K31/506
CPC分类号： C07D403/14 , A61K31/506 , A61K31/527 , A61K45/06 , C07D401/14 , C07D403/12 , C07D493/04
摘要： The present invention provides novel heteroaryl compounds, pharmaceutical acceptable salts and formulations thereof useful in preventing, treating or lessening the severity of a protein-mediated disease. The invention also provides pharmaceutically acceptable compositions comprising such compounds and methods of using the compositions in the treatment of protein kinase-mediated disease.
摘要翻译：本发明提供了用于预防，治疗或减轻蛋白质介导的疾病的严重性的新颖的杂芳基化合物，其药学上可接受的盐和制剂。本发明还提供包含这些化合物的药学上可接受的组合物和使用该组合物治疗蛋白激酶介导的疾病的方法。

10. 发明授权

US09031316B2 Method for identifying view order of image frames of stereo image pair according to image characteristics and related machine readable medium thereof 有权
标题翻译：用于根据图像特征及其相关的机器可读介质识别立体图像对的图像帧的视图顺序的方法
公开(公告)号：US09031316B2
公开(公告)日：2015-05-12
申请号：US13612893
申请日：2012-09-13
申请人： Tao Zhang , Shan Liu
发明人： Tao Zhang , Shan Liu
IPC分类号： G06K9/00 , H04N13/00
CPC分类号： H04N13/106 , H04N2013/0081 , H04N2213/007
摘要： A method for identifying an actual view order of image frames of a stereo image pair includes at least the following steps: receiving the image frames; obtaining image characteristics by analyzing the image frames according to an assumed view order; and identifying the actual view order by checking the image characteristics. In addition, a machine readable medium storing a program code is provided. The program causes a processor to perform at least the following steps for identifying an actual view order of image frames of a stereo image pair when executed by the processor: receiving the image frames; obtaining image characteristics by analyzing the image frames according to an assumed view order; and identifying the actual view order by checking the image characteristics.
摘要翻译：用于识别立体图像对的图像帧的实际视图顺序的方法至少包括以下步骤：接收图像帧; 通过根据假定的视图顺序分析图像帧来获得图像特征; 并通过检查图像特征来识别实际的视图顺序。此外，提供了存储程序代码的机器可读介质。该程序使得处理器至少执行以下步骤，以便在由处理器执行时识别立体图像对的图像帧的实际视图顺序：接收图像帧; 通过根据假定的视图顺序分析图像帧来获得图像特征; 并通过检查图像特征来识别实际的视图顺序。

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