利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

168 records (took 0.035 seconds)

    System, apparatus, and method for determining physical dimensions in digital images
    5.
    发明授权
    System, apparatus, and method for determining physical dimensions in digital images 有权

    公开(公告)号：US09881235B1

    公开(公告)日：2018-01-30

    申请号：US14948076

    申请日：2015-11-20

    Applicant: Mahmoud Narimanzadeh

    Inventor： Mahmoud Narimanzadeh

    IPC: G06K9/00 ,  G06K9/36 ,  G01B11/30 ,  G06K9/62 ,  G06K9/38

    CPC classification number: G06K9/624 ,  G06K9/38 ,  G06K9/6249

    Abstract: A system and method is provided for generating a digital image configured to facilitate measuring at least one physical dimension in the digital image. At least one light source is configured to project a plurality of substantially parallel light beams onto at least one physical object spaced away from the at least one light source. The light beams form a reference pattern on the at least one physical object. The reference pattern includes at least one feature defining a physical dimension having a predetermined magnitude. A digital camera is configured to store a digital image of at least a portion of the at least one physical object and the at least one feature. The digital image includes an image data file having a plurality of pixels and metadata. At least a portion of the metadata is indicative of a conversion factor relating the predetermined magnitude of the physical dimension with a pixel distance corresponding to the predetermined magnitude of the physical dimension.

    Methods and apparatuses for detecting anomalies using transform based compressed sensing matrices
    8.
    发明授权
    Methods and apparatuses for detecting anomalies using transform based compressed sensing matrices 有权
    使用基于变换的压缩感测矩阵来检测异常的方法和装置

    公开(公告)号：US09563806B2

    公开(公告)日：2017-02-07

    申请号：US14136803

    申请日：2013-12-20

    Applicant: Alcatel-Lucent USA Inc.

    Inventor： Raziel Haimi-Cohen ,  Hong Jiang

    IPC: G06K9/00 ,  G06K9/62

    CPC classification number: G06K9/00771 ,  G06K9/00536 ,  G06K9/00778 ,  G06K9/6249 ,  G06K9/6284

    Abstract: A measurement vector of compressive measurements is received. The measurement vector may be derived by applying a sensing matrix to a source signal. The sensing matrix may be derived from a frequency domain transform. At least one first feature vector is generated from the measurement vector. The first feature vector is an estimate of a second feature vector. The second feature vector is a feature vector that corresponds to a translation of the source signal. An anomaly is detected to in the source signal based on the first feature vector.

    Abstract translation: 接收压缩测量的测量矢量。 可以通过将感测矩阵应用于源信号来导出测量矢量。 感测矩阵可以从频域变换导出。 从测量向量生成至少一个第一特征向量。 第一特征向量是第二特征向量的估计。 第二特征向量是对应于源信号的平移的特征向量。 基于第一特征向量在源信号中检测到异常。

    Low power surveillance camera system for intruder detection
    9.
    发明授权
    Low power surveillance camera system for intruder detection 有权
    用于入侵者检测的低功率监控摄像系统

    公开(公告)号：US09544550B1

    公开(公告)日：2017-01-10

    申请号：US14209136

    申请日：2014-03-13

    Applicant: HRL Laboratories, LLC

    Inventor： Kang-Yu Ni ,  Shankar R. Rao ,  Yuri Owechko

    IPC: H04N7/18

    CPC classification number: G06K9/6249 ,  G06K9/00771 ,  G08B13/19604

    Abstract: Described is a low power surveillance camera system for intruder detection. The system observes a scene with a known camera motion to generate images with various viewing angles. Next, a background learning mode is employed to generate a low rank matrix for the background in the images. Background null space projections are then learned, which provide a foreground detection kernel. A new scene with known viewing angles is then obtained. Based on the foreground detection kernel and the new input image frame, low power foreground detection is performed to detect foreground potential regions of interest (ROIs), such as intruders. To filter out minimal foreground activity, the system identifies contiguous ROIs to generate the foreground ROI. Focus measures are then employed on the ROIs using foveated compressed sensing to generate foveated measurements. Based on the foveated measurements, the foreground is reconstructed for presentation to a user.

    Abstract translation: 描述了一种用于入侵者检测的低功率监控摄像机系统。 该系统观察具有已知摄像机运动的场景以产生具有各种视角的图像。 接下来，使用背景学习模式来生成图像中的背景的低秩矩阵。 然后学习背景零空间投影，其提供前景检测内核。 然后获得具有已知视角的新场景。 基于前景检测核心和新的输入图像帧，执行低功率前景检测，以检测诸如入侵者的感兴趣的前景潜在区域（ROI）。 为了过滤掉最小的前景活动，系统识别连续的ROI以生成前景ROI。 然后，利用移动压缩感测对ROI进行聚焦，以产生移动测量。 基于移动测量，重建前景以呈现给用户。

    Blur object tracker using group lasso method and apparatus
    10.
    发明授权
    Blur object tracker using group lasso method and apparatus 有权
    模糊对象跟踪器使用组套索方法和装置

    公开(公告)号：US09355320B2

    公开(公告)日：2016-05-31

    申请号：US14528528

    申请日：2014-10-30

    Applicant: Toyota Motor Engineering & Manufacturing North America, Inc.

    Inventor： Xue Mei ,  Yi Wu ,  Danil V. Prokhorov ,  Haibin Ling

    IPC: G06K9/00 ,  G06K9/46 ,  G06T5/00

    CPC classification number: G06K9/00791 ,  G06K9/00805 ,  G06K9/4642 ,  G06K9/6249 ,  G06K2209/21 ,  G06T7/277 ,  G06T2207/30252

    Abstract: A method and apparatus for tracking an object across a plurality of sequential images, where certain of the images contain motion blur. A plurality of normal templates of a clear target object image and a plurality of blur templates of the target object are generated. In the next subsequent image frame, a plurality of bounding boxes are generated of potential object tracking positions about the target object location in the preceding image frame. For each bounding box image frame, a reconstruction error is generated that one bounding box has a maximum probability that it is the object tracking result in the subsequent image frame.

    Abstract translation: 一种用于在多个顺序图像中跟踪对象的方法和装置，其中某些图像包含运动模糊。 产生清晰目标对象图像的多个正常模板和目标对象的多个模糊模板。 在接下来的后续图像帧中，生成关于前一图像帧中的目标对象位置的潜在对象跟踪位置的多个边界框。 对于每个边界框图像帧，产生重建误差，一个边界框具有在随后的图像帧中作为对象跟踪结果的最大概率。

Patent Agency Ranking