利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

76 条记录 (耗时 0.025 秒)

    Constructing an Energy Matrix of a Radio Signal
    1.
    发明申请
    Constructing an Energy Matrix of a Radio Signal 失效
    构建无线电信号的能量矩阵

    公开(公告)号：US20090028221A1

    公开(公告)日：2009-01-29

    申请号：US11577143

    申请日：2005-04-22

    申请人： Zafer Sahinoglu ,  Fatih M. Porikli

    发明人： Zafer Sahinoglu ,  Fatih M. Porikli

    IPC分类号： H04B1/69 ,  H04B17/00

    CPC分类号： H04B1/71637 ,  G01S5/0221 ,  G01S13/76 ,  H04B17/318 ,  H04B17/336 ,  H04B17/345

    摘要： A method analyzes a radio signal received via a wireless channel. The radio signal includes multiple frames representing a transmitted symbol. Energy of ach frame is sampled during multiple of non-overlapping time windows. The sampled energies are stored in an energy matrix indexed by the number of frames and the number of time windows in each frame to analyze the radio signal.

    摘要翻译： 一种方法分析通过无线信道接收的无线电信号。 无线电信号包括表示发送符号的多个帧。 在多个不重叠的时间窗口中对ach帧的能量进行采样。 采样能量存储在由帧数和每个帧中的时间窗口数量索引的能量矩阵中，以分析无线电信号。

    Constructing an energy matrix of a radio signal
    3.
    发明授权
    Constructing an energy matrix of a radio signal 失效
    构建无线电信号的能量矩阵

    公开(公告)号：US07916778B2

    公开(公告)日：2011-03-29

    申请号：US11577143

    申请日：2005-04-22

    申请人： Zafer Sahinoglu ,  Fatih M. Porikli

    发明人： Zafer Sahinoglu ,  Fatih M. Porikli

    IPC分类号： H04B3/46 ,  H04B1/00

    CPC分类号： H04B1/71637 ,  G01S5/0221 ,  G01S13/76 ,  H04B17/318 ,  H04B17/336 ,  H04B17/345

    摘要： A method analyzes a radio signal received via a wireless channel. The radio signal includes multiple frames representing a transmitted symbol. Energy of each frame is sampled during multiple of non-overlapping time windows. The sampled energies are stored in an energy matrix indexed by the number of frames and the number of time windows in each frame to analyze the radio signal.

    摘要翻译： 一种方法分析通过无线信道接收的无线电信号。 无线电信号包括表示传输符号的多个帧。 每个帧的能量在多个不重叠的时间窗口中被采样。 采样能量存储在由帧数和每个帧中的时间窗口数量索引的能量矩阵中，以分析无线电信号。

    Object Detection Using Combinations of Relational Features in Images
    4.
    发明申请
    Object Detection Using Combinations of Relational Features in Images 审中-公开
    使用图像中关系特征组合的对象检测

    公开(公告)号：US20110293173A1

    公开(公告)日：2011-12-01

    申请号：US12786648

    申请日：2010-05-25

    申请人： Fatih M. Porikli ,  Vijay Venkatarman

    发明人： Fatih M. Porikli ,  Vijay Venkatarman

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6256 ,  G06K9/4642 ,  G06K9/629

    摘要： A classifier for detecting objects in images is constructed from a set of training images. For each training image, features are extracted from a window in the training image, wherein the window contains the object, and then randomly sample coefficients c of the features. N-combinations for each possible set of the coefficients are determined. For each possible combination of the coefficients, a Boolean valued proposition is determined using relational operators to generate a propositional space. Complex hypotheses of a classifier are defined by applying combinatorial functions of the Boolean operators to the propositional space to construct all possible logical propositions in the propositional space. Then, the complex hypotheses of the classifier can be applied to features in a test image to detect whether the test image contains the object.

    摘要翻译： 用于检测图像中的对象的分类器由一组训练图像构成。 对于每个训练图像，从训练图像中的窗口提取特征，其中窗口包含对象，然后随机抽取特征的系数c。 确定每个可能的系数集合的N个组合。 对于系数的每个可能的组合，使用关系运算符来确定布尔值的命题以产生命题空间。 分类器的复杂假设通过将布尔运算符的组合函数应用于命题空间来定义，以构成命题空间中的所有可能的逻辑命题。 然后，分类器的复杂假设可以应用于测试图像中的特征，以检测测试图像是否包含对象。

    System and Method for Adapting Generic Classifiers for Object Detection in Particular Scenes Using Incremental Training
    5.
    发明申请
    System and Method for Adapting Generic Classifiers for Object Detection in Particular Scenes Using Incremental Training 有权
    用于使用增量训练适应特定场景中的对象检测的通用分类器的系统和方法

    公开(公告)号：US20110293136A1

    公开(公告)日：2011-12-01

    申请号：US12791786

    申请日：2010-06-01

    申请人： Fatih M. Porikli

    发明人： Fatih M. Porikli

    IPC分类号： G06K9/62

    CPC分类号： G06K9/00771 ,  G06K9/6263 ,  G06K9/6269 ,  G06N99/005

    摘要： A generic classifier is adapted to detect an object in a particular scene, wherein the particular scene was unknown when the classifier was trained with generic training data. A camera acquires a video of frames of the particular scene. A model of the particular scene model is constructed using the frames in the video. The classifier is applied to the model to select negative examples, and new negative examples are added to the training data while removing another set of existing negative examples from the training data based on an uncertainty measure;. Selected positive examples are also added to the training data and the classifier is retrained until a desired accuracy level is reached to obtain a scene specific classifier.

    摘要翻译： 通用分类器适于检测特定场景中的对象，其中当分类器用通用训练数据训练时，特定场景是未知的。 相机获取特定场景的帧的视频。 使用视频中的帧构建特定场景模型的模型。 将分类器应用于模型以选择负面示例，并且将新的否定示例添加到训练数据中，同时基于不确定性度量从训练数据中移除另一组现有的负面示例。 选择的正例也被添加到训练数据中，分类器被重新训练直到达到期望的精度水平以获得场景特定的分类器。

    Method for Recognizing Traffic Signs
    6.
    发明申请
    Method for Recognizing Traffic Signs 有权
    识别交通标志的方法

    公开(公告)号：US20110109476A1

    公开(公告)日：2011-05-12

    申请号：US12414981

    申请日：2009-03-31

    申请人： Fatih M. Porikli ,  Andrzej Ruta

    发明人： Fatih M. Porikli ,  Andrzej Ruta

    IPC分类号： G06K9/46 ,  G08G1/09 ,  G06K9/00 ,  G06K9/62

    CPC分类号： G06K9/00818 ,  G06K9/3241 ,  G06K9/6256

    摘要： A method recognizes a set of traffic signs in a sequence of images acquired of a vehicle environment by a camera mounted in a moving vehicle by detecting in each image, a region of interest (ROI) using a parameter space transform. The ROI is tracked and classified as a particular one of the signs. The classifier only uses a same class and a different class, and a regression function to update the classifier.

    摘要翻译： 一种方法通过使用参数空间变换在每个图像中检测感兴趣区域（ROI）来识别通过安装在移动车辆中的照相机获取的车辆环境获取的图像序列中的一组交通标志。 ROI被跟踪并分类为特定的一个标志。 分类器仅使用相同的类和不同的类，以及更新分类器的回归函数。

    Method for Filtering Data with Arbitrary Kernel Filters
    7.
    发明申请
    Method for Filtering Data with Arbitrary Kernel Filters 失效
    使用任意内核过滤器过滤数据的方法

    公开(公告)号：US20080219580A1

    公开(公告)日：2008-09-11

    申请号：US11683482

    申请日：2007-03-08

    申请人： Fatih M. Porikli

    发明人： Fatih M. Porikli

    IPC分类号： G06K9/40 ,  G06F17/10

    CPC分类号： G06T5/20 ,  G06F17/153

    摘要： A computer implemented method filters input data with a kernel filter. A kernel filter is defined, and a set of unique filter coefficients for the kernel filter are determined. A linkage set is constructed for each unique filter coefficient such that the linkage set includes relative links to positions in the kernel filter that have identical filter coefficients, and in which each relative link is an inverse of the position of the unique filter coefficient. Each input data point is processed by multiply values on which the kernel filter is centered by each of the unique filter coefficients, and adding results of the multiplying to the corresponding output data points as referenced by the relative links.

    摘要翻译： 计算机实现的方法使用内核过滤器过滤输入数据。 定义内核过滤器，并确定内核过滤器的一组唯一的过滤器系数。 为每个唯一的滤波器系数构造一个链接集合，使得链接集合包括具有相同滤波器系数的核滤波器中的位置的相对链接，并且其中每个相对链路是唯一滤波器系数的位置的倒数。 每个输入数据点由乘法值处理，其中内核滤波器由每个唯一的滤波器系数居中，并将乘法结果相加到由相对链接引用的相应输出数据点。

    Method for classifying data using an analytic manifold
    8.
    发明申请
    Method for classifying data using an analytic manifold 有权
    使用分析歧管对数据进行分类的方法

    公开(公告)号：US20080063264A1

    公开(公告)日：2008-03-13

    申请号：US11517645

    申请日：2006-09-08

    申请人： Fatih M. Porikli ,  Oncel C. Tuzel

    发明人： Fatih M. Porikli ,  Oncel C. Tuzel

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6256 ,  G06K9/00369 ,  G06K9/4642

    摘要： A computer implemented method constructs a classifier for classifying test data. High-level features are generated from low-level features extracted from training data. The high level features are positive definite matrices in a form of an analytical manifold. A subset of the high-level features is selected. An intrinsic mean matrix is determined from the subset of the selected high-level features. Each high-level feature is mapped to a feature vector onto a tangent space of the analytical manifold using the intrinsic mean matrix. Then, an untrained classifier model can be trained with the feature vectors to obtain a trained classifier. Subsequently, the trained classifier can classify unknown test data.

    摘要翻译： 计算机实现的方法构建用于分类测试数据的分类器。 高级功能是从训练数据中提取的低级功能产生的。 高级特征是分析歧管形式的正定矩阵。 选择高级功能的子集。 从所选择的高级特征的子集确定固有均值矩阵。 使用内在平均矩阵将每个高级特征映射到分析歧管的切线空间上的特征向量。 然后，可以使用特征向量来训练未经训练的分类器模型以获得训练有素的分类器。 随后，经过训练的分类器可以对未知的测试数据进行分类。

    Image simplification using a robust reconstruction filter
    9.
    发明授权
    Image simplification using a robust reconstruction filter 有权

    公开(公告)号：US07103229B2

    公开(公告)日：2006-09-05

    申请号：US10012915

    申请日：2001-11-19

    申请人： Fatih M. Porikli

    发明人： Fatih M. Porikli

    IPC分类号： G06K9/40 ,  G06K9/36

    CPC分类号： G06T7/11 ,  G06T2207/10016

    摘要： A method simplifies a data structure representing physical measurements of a real-world phenomena, such as an image of a scene of an object. Input data are first acquired, sensed, or measured. If the data are acquired with a camera, then measurement errors for data points in the data structure are not normally distributed. Therefore, an error term for each data point is constructed according to a Lorentzian estimator. The error term can be determined by taking a difference between the value of the data point, and the value at the data point when a model is fitted to the data structure. The error term is then minimized using a downhill simplex minimization process. Finally, each data point is adjusted by the minimized error term to produce a simplified data structure of the real-world phenomena.