利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

45 条记录 (耗时 0.021 秒)

    DISTRIBUTED NETWORK CENTER AND AREA ESTIMATION
    25.
    发明申请
    DISTRIBUTED NETWORK CENTER AND AREA ESTIMATION 审中-公开

    公开(公告)号：US20180352414A1

    公开(公告)日：2018-12-06

    申请号：US15995433

    申请日：2018-06-01

    申请人： Sai Zhang ,  Cihan Tepedelenlioglu ,  Andreas Spanias

    发明人： Sai Zhang ,  Cihan Tepedelenlioglu ,  Andreas Spanias

    IPC分类号： H04W8/00 ,  H04W8/14 ,  H04L29/08

    CPC分类号： H04W8/005 ,  H04L67/12 ,  H04W4/38 ,  H04W8/14 ,  H04W24/02 ,  H04W84/18

    摘要： Some embodiments include a wireless sensor network including a plurality of sensor nodes each comprising: a signal receiver configured to receive intermediate information from at least one of one or more neighboring nodes of the plurality of sensor nodes, one or more processors configured to receive the intermediate information and update the intermediate information based on a soft-max approximation function, and a transmitter configured to send the intermediate information, as updated, to at least one of the one or more neighboring nodes of the plurality of sensor nodes. For each sensor node of the plurality of sensor nodes: the sensor node can store local location coordinates for the sensor node, and the sensor node can be devoid of receiving location coordinates for any other of the plurality of sensor nodes. The plurality of sensor nodes can be configured to communicate in a distributed manner for a first plurality of iterations until a final iteration of the first plurality of iterations when a predetermined stopping condition is satisfied. The plurality of sensor nodes can be further configured to generate an estimated center of the wireless sensor network based on the intermediate information updated in the final iteration of the first plurality of iterations. The wireless sensor network can be devoid of a fusion center. Other embodiments are disclosed.

    TRACKING-BASED MOTION DEBLURRING VIA CODED EXPOSURE
    28.
    发明申请
    TRACKING-BASED MOTION DEBLURRING VIA CODED EXPOSURE 有权

    公开(公告)号：US20210390669A1

    公开(公告)日：2021-12-16

    申请号：US17348392

    申请日：2021-06-15

    申请人： Suren Jayasuriya ,  Odrika Iqbal ,  Andreas Spanias

    发明人： Suren Jayasuriya ,  Odrika Iqbal ,  Andreas Spanias

    IPC分类号： G06T5/00 ,  G06T7/20 ,  G06K9/32 ,  H04N5/235

    摘要： Tracking-based motion deblurring via coded exposure is provided. Fast object tracking is useful for a variety of applications in surveillance, autonomous vehicles, and remote sensing. In particular, there is a need to have these algorithms embedded on specialized hardware, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs), to ensure energy-efficient operation while saving on latency, bandwidth, and memory access/storage. In an exemplary aspect, an object tracker is used to track motion of one or more objects in a scene captured by an image sensor. The object tracker is coupled with coded exposure of the image sensor, which modulates photodiodes in the image sensor with a known exposure function (e.g., based on the object tracking). This allows for motion blur to be encoded in a characteristic manner in image data captured by the image sensor. Then, in post-processing, deblurring is performed using a computational algorithm.

    KERNEL SPARSE MODELS FOR AUTOMATED TUMOR SEGMENTATION
    30.
    发明申请
    KERNEL SPARSE MODELS FOR AUTOMATED TUMOR SEGMENTATION 有权
    用于自动肿瘤分期的KERNEL SPARSE模型

    公开(公告)号：US20160005183A1

    公开(公告)日：2016-01-07

    申请号：US14853617

    申请日：2015-09-14

    申请人： Jayaraman Jayaraman Thiagarajan ,  Karthikeyan Ramamurthy ,  Andreas Spanias ,  David Frakes

    发明人： Jayaraman Jayaraman Thiagarajan ,  Karthikeyan Ramamurthy ,  Andreas Spanias ,  David Frakes

    IPC分类号： G06T7/00 ,  A61B5/055

    CPC分类号： G06T7/0012 ,  A61B5/055 ,  A61B2576/026 ,  G06T7/11 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/30096

    摘要： A robust method to automatically segment and identify tumor regions in medical images is extremely valuable for clinical diagnosis and disease modeling. In various embodiments, an efficient algorithm uses sparse models in feature spaces to identify pixels belonging to tumorous regions. By fusing both intensity and spatial location information of the pixels, this technique can automatically localize tumor regions without user intervention. Using a few expert-segmented training images, a sparse coding-based classifier is learned. For a new test image, the sparse code obtained from every pixel is tested with the classifier to determine if it belongs to a tumor region. Particular embodiments also provide a highly accurate, low-complexity procedure for cases when the user can provide an initial estimate of the tumor in a test image.

    摘要翻译： 在医学图像中自动分割和识别肿瘤区域的有力方法对于临床诊断和疾病建模非常有价值。 在各种实施例中，有效算法使用特征空间中的稀疏模型来识别属于肿瘤区域的像素。 通过融合像素的强度和空间位置信息，该技术可以自动定位肿瘤区域而无需用户干预。 使用几个专家分割的训练图像，学习了一种基于稀疏编码的分类器。 对于新的测试图像，用分类器测试从每个像素获得的稀疏码，以确定它是否属于肿瘤区域。 当用户可以在测试图像中提供肿瘤的初始估计时，特定实施例还提供了高精度，低复杂度的程序。