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
    • 92. 发明申请
    • Multi-view cognitive swarm for object recognition and 3D tracking
    • 用于对象识别和3D跟踪的多视角认知群
    • US20070183669A1
    • 2007-08-09
    • US11385983
    • 2006-03-20
    • Yuri OwechkoSwarup MedasaniPayam Saisan
    • Yuri OwechkoSwarup MedasaniPayam Saisan
    • G06K9/62G06K9/46
    • G06K9/6229G06K9/00369G06K9/6292
    • An object recognition system is described that incorporates swarming classifiers. The swarming classifiers comprise a plurality of software agents configured to operate as a cooperative swarm to classify an object in a domain as seen from multiple view points. Each agent is a complete classifier and is assigned an initial velocity vector to explore a solution space for object solutions. Each agent is configured to perform an iteration, the iteration being a search in the solution space for a potential solution optima where each agent keeps track of its coordinates in multi-dimensional space that are associated with an observed best solution (pbest) that the agent has identified, and a global best solution (gbest) where the gbest is used to store the best location among all agents. Each velocity vector changes towards pbest and gbest, allowing the cooperative swarm to concentrate on the vicinity of the object and classify the object.
    • 描述了包含群组分类器的对象识别系统。 群集分类器包括被配置为作为协作群进行操作的多个软件代理,用于对从多个视点看到的域中的对象进行分类。 每个代理是一个完整的分类器,并分配一个初始速度向量来探索对象解决方案的解空间。 每个代理被配置为执行迭代,迭代是针对潜在解决方案空间的解决方案空间中的搜索,其中每个代理跟踪其在与所观察到的最佳解(pbest)相关联的多维空间中的坐标,代理 已经确定了全球最佳解决方案(gbest),其中gbest用于存储所有代理商中的最佳位置。 每个速度向量向pbest和gbest变化,允许合作群集集中在对象附近并对对象进行分类。
    • 93. 发明授权
    • Application-specific object-based segmentation and recognition system
    • 特定于应用程序的基于对象的分割和识别系统
    • US07227893B1
    • 2007-06-05
    • US10646585
    • 2003-08-22
    • Narayan SrinivasaSwarup S. MedasaniYuri OwechkoDeepak Khosla
    • Narayan SrinivasaSwarup S. MedasaniYuri OwechkoDeepak Khosla
    • H04N7/18
    • G08B13/19606G06K9/00771G08B13/19602G08B13/19608G08B13/19613
    • A video detection and monitoring method and apparatus utilizes an application-specific object based segmentation and recognition system for locating and tracking an object of interest within a number of sequential frames of data collected by a video camera or similar device. One embodiment includes a background modeling and object segmentation module to isolate from a current frame at least one segment of the current frame containing a possible object of interest, and a classification module adapted to determine whether or not any segment of the output from the background modeling apparatus includes an object of interest and to characterize any such segment as an object segment. An object segment tracking apparatus is adapted to track the location within a current frame of any object segment and to determine a projected location of the object segment in a subsequent frame.
    • 视频检测和监测方法和装置利用基于特定目标的对象分割和识别系统来定位和跟踪由摄像机或类似设备收集的多个数据的连续数据帧内的感兴趣对象。 一个实施例包括背景建模和对象分割模块,以从当前帧与当前帧的至少一个分段包含可能的感兴趣对象隔离,并且分类模块适于确定来自背景建模的输出的任何分段 装置包括感兴趣的对象并且将任何这样的片段表征为对象片段。 对象段跟踪装置适于跟踪任何对象段的当前帧内的位置,并且确定对象段在随后帧中的投影位置。
    • 94. 发明授权
    • Collision avoidance system utilizing machine vision taillight tracking
    • 碰撞避免系统利用机器视觉尾灯跟踪
    • US06317691B1
    • 2001-11-13
    • US09504634
    • 2000-02-16
    • Srinivasa NarayanYuri Owechko
    • Srinivasa NarayanYuri Owechko
    • G06F1550
    • G08G1/166G08G1/165
    • A vehicle-mounted sensing method and apparatus capable of monitoring the relative speed, distance, and closure rate between a sensor-equipped host vehicle and a sensed target object. The sensor uses an electronic camera to passively collect information and to provide the information to a system that identifies objects of interest using visual clues such as color, shape, and symmetry. The object's proximity may be determined, to a first approximation, by taking advantage of symmetrical relationships inherent in the vehicle of interest. The method and apparatus are particularly well-suited vehicular safety systems to provide for optimal risk assessment and deployment of multiple safety systems.
    • 一种车载感测方法和装置,其能够监测装备有传感器的主车辆和感测到的目标物体之间的相对速度,距离和关闭速率。 传感器使用电子照相机来被动地收集信息,并使用诸如颜色,形状和对称性之类的视觉线索将信息提供给识别感兴趣对象的系统。 物体的接近度可以通过利用感兴趣的车辆中固有的对称关系来确定为第一近似。 该方法和装置是特别适合的车辆安全系统,以提供多种安全系统的最佳风险评估和部署。
    • 95. 发明授权
    • Electro-optic channelized modulator and receiver
    • 电光通道调制器和接收器
    • US5105380A
    • 1992-04-14
    • US446838
    • 1989-12-06
    • Yuri Owechko
    • Yuri Owechko
    • G01S7/02G06E3/00
    • G01S7/021G06E3/005
    • A wideband electrical input signal is applied to a tapped delay line to produce a spatial representation of the input signal distributed along the delay line taps. Inputs of individual elements of a linear electro-optic modulator array are connected to the respective delay line taps, such that the modulator array produces a spatial optical pattern in which the transmittance varies in accordance with the amplitude of the input signal. A laser directs a coherent light beam through the modulator array for modulation by the optical pattern. A Fourier transform lens transforms the modulated light beam into a spatial light distribution pattern in which the light intensity varies in accordance with the amplitudes of the frequency components in the input signal. A photodetector array produces channelized electrical outputs corresponding to portions of the light distribution pattern which themselves correspond to respective ranges of frequencies in the input signal.
    • 将宽带电输入信号施加到抽头延迟线以产生沿着延迟线抽头分布的输入信号的空间表示。 线性电光调制器阵列的各个元件的输入连接到相应的延迟线抽头,使得调制器阵列产生空间光学图案,其中透射率根据输入信号的幅度而变化。 激光器将相干光束引导通过调制器阵列以通过光学图案进行调制。 傅里叶变换透镜将调制后的光束变换为光强度根据输入信号中的频率分量的振幅而变化的空间配光图案。 光电检测器阵列产生对应于自身对应于输入信号中的各个频率范围的配光图案的部分的通道化电输出。
    • 96. 发明授权
    • Associative memory system with spatial light modulator
    • 具有空间光调制器的关联记忆系统
    • US4961615A
    • 1990-10-09
    • US356808
    • 1989-05-24
    • Yuri OwechkoBernard H. Soffer
    • Yuri OwechkoBernard H. Soffer
    • G11C15/00
    • G11C15/00
    • An associative memory system is provided which incorporates a spatial light modulator (SLM) and thresholding components. In the preferred embodiment, a Fourier transform hologram is used to convolve a reference beam with correlated input images and stored object images. An iteration and feedback loop is provided which is used to derive an enhanced reference beam for use in matching and enhancing the associative memory of the hologram with the object input plane image. The iteration loop of SLM and optical amplifying components comprises a liquid crystal light valve (LCLV) which receives the correlation plane image and provides that image in the form of a spatially phase-modulated and amplitude modulated signal to a polarizing thresholding analyzer device. The analyzer/polarizer is adjustable and threshold limits the data at fast rates and, is used in the preferred embodiment to threshold the data with reference to the greatest amplitude portion of the correlation spot provided to the LCLV. After the optical analyzer/polarizer threshold has processed the signal, an improved signal is provided to the writing photoconductor side of the LCLV. This processed signal is used to phase-modulate a projection light readout beam. A polarizing beam splitter converts the phase modulation of the readout beam to an amplitude modulation wherein an enhanced reference beam is derived which is processed back to the hologram for readout at the output plane of the system. In this manner a variable-gain fast response spatial light modulator component system is provided for use as an associative memory.
    • 提供了一种结合存储器系统,其包括空间光调制器(SLM)和阈值分量。 在优选实施例中,傅里叶变换全息图用于将参考光束与相关的输入图像和存储的对象图像进行卷积。 提供迭代和反馈回路,其用于导出用于匹配和增强全息图的关联存储器与对象输入平面图像的增强参考光束。 SLM和光放大组件的迭代循环包括一个液晶光阀(LCLV),它接收相关平面图像,并以空间相位调制和幅度调制信号的形式将该图像提供给极化阈值分析器装置。 分析器/偏振器是可调节的,阈值以快速率限制数据,并且在优选实施例中用于参考提供给LCLV的相关点的最大幅度部分来阈值数据。 在光学分析仪/偏振器阈值处理该信号之后,将改进的信号提供给LCLV的写入感光体侧。 该处理信号用于相位调制投影光读出光束。 偏振分束器将读出光束的相位调制器转换成幅度调制,其中导出增强的参考光束,该参考光束被加工回到全息图,以在系统的输出平面读出。 以这种方式,提供可变增益快速响应空间光调制器组件系统用作关联存储器。
    • 97. 发明授权
    • Optical thresholding apparatus and method
    • 光学阈值设备及方法
    • US4934782A
    • 1990-06-19
    • US282889
    • 1988-12-09
    • Bernard H. SofferYuri Owechko
    • Bernard H. SofferYuri Owechko
    • G02B27/46G06K9/58G06G7/02
    • G02B27/46G06K9/58
    • An apparatus and method for processing optical beams designed to adaptively spatially threshold or filter an intensity histogram spectrum for re-transformation to a two-dimensional thresholded optical output. Such apparatus and method is used in optical computing and logic processing to selectively pass only certain light intensities, thereby blocking undesirable background noise while passing the desired signals. An incoming histogram light beam, containing an optical position distribution corresponding to the intensity distribution of an original optical beam, is split into first and second beams. The first beam is directed at a light detector array which transforms the optical position intensities of the first bema into directly proportional electrical signals. These signals are sent to a microprocessor which analyzes this input, determines the intensity distribution, calculates the algebraic mean and variance, sets the intensity threshold level based on pre-set information, and sends an electronic voltage signal to an optical selective reflector. The optical reflector, preferably a CCD LCLV, is positioned to receive the second split beam, and is instructed by the electronic voltage signal to selectively reflect only certain optical intensities onto an inverse Fourier transform lens. This lens re-transforms the quasi-one-dimensional second split beam into the desired two-dimensional thresholded optical output.
    • 一种用于处理光束的装置和方法,其被设计成自适应地空间阈值或滤波强度直方图谱,以便重新转换为二维阈值光输出。 这种装置和方法用于光学计算和逻辑处理中,以选择性地仅通过某些光强度,从而在传递所需信号的同时阻止不期望的背景噪声。 包含与原始光束的强度分布对应的光学位置分布的入射直方图光束被分割成第一和第二光束。 第一个光束被引导到光检测器阵列,其将第一个bema的光学位置强度变换成直接成比例的电信号。 这些信号被发送到分析该输入的微处理器,确定强度分布,计算代数均值和方差,基于预置信息设置强度阈值电平,并将电子电压信号发送到光学选择反射器。 光反射器(优选CCD LCLV)被定位成接收第二分束,并且由电子电压信号指示,以仅选择性地将某些光强度反射到傅里叶逆变换透镜上。 该透镜将准一维第二分割光束重新变换为期望的二维阈值光学输出。