会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 6. 发明申请
    • DEVICE IMPAIRMENT DETECTION
    • 器件损害检测
    • WO2017049164A1
    • 2017-03-23
    • PCT/US2016/052258
    • 2016-09-16
    • SONOS, INC.
    • HARTUNG, KlausBRIGHT, Greg
    • H04R3/04H04S7/00G06N3/02
    • G10L25/30G06F3/16G06N3/02G06N3/084H04R3/04H04R27/00H04R29/007H04R2227/005H04S7/301
    • Examples described herein involve detecting known impairments or other known conditions using a neural network. An example implementation involves receiving data indicating a response of a playback device as captured by a microphone. The implementation also involves determining an input vector by projecting a response vector that represents the response of the playback device onto a principle component matrix representing variance caused by one or more known impairments. The implementation further involves providing the determined input vector to a neural network that includes an output layer comprising neurons that correspond to respective known impairments. The implementation involves detecting that the input vector caused one or more neurons of the neural network to fire such that the neural network indicates that a particular known impairment is affecting the microphone and/or the playback device and adjusting operation of the playback device and/or the microphone to offset the particular known impairment.
    • 本文描述的示例涉及使用神经网络来检测已知的损伤或其他已知的条件。 示例实现涉及接收指示由麦克风捕获的播放设备的响应的数据。 该实现还包括通过将表示回放设备的响应的响应向量投影到表示由一个或多个已知损伤引起的方差的原理分量矩阵上来确定输入向量。 该实现还包括将确定的输入向量提供给神经网络,该神经网络包括包括对应于各自已知损伤的神经元的输出层。 该实现涉及检测输入向量导致神经网络的一个或多个神经元触发,使得神经网络指示特定的已知损伤影响麦克风和/或播放设备并且调整播放设备的操作和/或 麦克风抵消特定的已知损伤。
    • 7. 发明申请
    • POSITION-CONTROLLED ROBOTIC FLEET WITH VISUAL HANDSHAKES
    • 位置控制的机动车与可视海盗
    • WO2016077243A1
    • 2016-05-19
    • PCT/US2015/059767
    • 2015-11-09
    • GOOGLE INC.
    • MASON, JulianKONOLIGE, Kurt
    • G05B19/418
    • G05D1/0246B65G1/1373G05B19/41815G05B2219/39129G05B2219/40605G05D1/0287Y02P90/08
    • Example methods and systems may provide for a system that includes a control system communicatively coupled to a first robotic device and a second robotic device. The control system may identify a collaborative operation to be performed by a first robotic device and a second robotic device that is based on a relative positioning between the first robotic device and the second robotic device. The control system may also determine respective locations of the first robotic device and the second robotic device. The control system may further initiate a movement of the first robotic device along a path from the determined location of the first robotic device towards the determined location of the second robotic device. The first robotic device and the second robotic device may then establish a visual handshake that indicates the relative positioning between the first robotic device and the second robotic device for the collaborative operation.
    • 示例性方法和系统可以提供包括通信地耦合到第一机器人设备和第二机器人设备的控制系统的系统。 控制系统可以识别由第一机器人设备和第二机器人设备执行的协作操作,其基于第一机器人设备和第二机器人设备之间的相对定位。 控制系统还可以确定第一机器人装置和第二机器人装置的相应位置。 控制系统还可以启动第一机器人装置沿着从第一机器人装置的确定位置朝向第二机器人装置的确定位置的路径的移动。 然后,第一机器人装置和第二机器人装置可以建立视觉握手,其指示用于协作操作的第一机器人装置和第二机器人装置之间的相对定位。
    • 8. 发明申请
    • MULTI-VIDEO DECODING WITH INPUT SWITCHING
    • 具有输入开关的多视频解码
    • WO2016069466A1
    • 2016-05-06
    • PCT/US2015/057353
    • 2015-10-26
    • GOOGLE INC.
    • LEWIS, Andrew, BenedictCOHEN, Richard, Zarek
    • H04N19/597H04N19/176H04N19/172H04N19/107H04N19/114H04N19/157H04N19/40H04N21/234H04N21/2365
    • H04N19/114H04N19/107H04N19/157H04N19/172H04N19/176H04N19/40H04N19/597H04N21/47202H04N21/47217
    • In some aspects, methods and systems described herein provide for preparing component videos for combining into a bitstream. An example system may receive a source video. The system may also receive data representing a compression format. The system may encode a reference frame as an intra-coded picture that is sub-divided into intra-coded units. The system may encode the sequence of source frames as a sequence of predictive-coded pictures conforming to the compression format. The sequence may be divided into groups of pictures that include a first predictive-coded picture followed by one or more second predictive-coded pictures. The first predictive-coded picture may be sub-divided into intra- coded units that represent respective portions of a source frame by describing the pixels of the portion so as to simulate intra-coded pictures. The system may concatenate the sequence of predictive-coded pictures after the intra-coded picture so as to produce a bitstream.
    • 在一些方面,本文描述的方法和系统提供了用于组合成比特流的分量视频。 示例系统可以接收源视频。 系统还可以接收表示压缩格式的数据。 系统可以将参考帧编码为被分割为帧内编码单位的帧内编码图像。 系统可将源帧序列编码为符合压缩格式的预测编码图像序列。 该序列可以被划分为包括第一预测编码图像和随后的一个或多个第二预测编码图像的图像组。 第一预测编码图像可以通过描述该部分的像素以便模拟帧内编码的图像而被细分成代表源帧的各个部分的帧内编码单元。 系统可以在帧内编码图像之后连接预测编码图像的序列,以便产生比特流。