中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

59 records (took 0.02 seconds)

    Large margin high-order deep learning with auxiliary tasks for video-based anomaly detection
    4.
    发明授权
    Large margin high-order deep learning with auxiliary tasks for video-based anomaly detection 有权

    公开(公告)号：US10402653B2

    公开(公告)日：2019-09-03

    申请号：US15380014

    申请日：2016-12-15

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Dongjin Song ,  Eric Cosatto

    IPC: G06K9/00 ,  H04N5/21 ,  G06N3/04 ,  G06N3/08 ,  G06K9/46 ,  G06K9/66 ,  G06K9/62

    Abstract: A computer-implemented method and system are provided for video-based anomaly detection. The method includes forming, by a processor, a Deep High-Order Convolutional Neural Network (DHOCNN)-based model having a one-class Support Vector Machine (SVM) as a loss layer of the DHOCNN-based model. An objective of the SVM is configured to perform the video-based anomaly detection. The method further includes generating, by the processor, one or more predictions of an impending anomaly based on the high-order deep learning based model applied to an input image. The method also includes initiating, by the processor, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

    RECONSTRUCTOR AND CONTRASTOR FOR ANOMALY DETECTION
    5.
    发明申请
    RECONSTRUCTOR AND CONTRASTOR FOR ANOMALY DETECTION 审中-公开

    公开(公告)号：US20180374207A1

    公开(公告)日：2018-12-27

    申请号：US15983342

    申请日：2018-05-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Alexandru Niculescu-Mizil ,  Eric Cosatto ,  Felix Wu

    IPC: G06T7/00 ,  H04N19/17 ,  H04N19/132

    Abstract: Systems and methods for detecting and correcting defective products include capturing at least one image of a product with at least one image sensor to generate an original image of the product. An encoder encodes portions of an image extracted from the original image to generate feature space vectors. A decoder decodes the feature space vectors to reconstruct the portions of the image into reconstructed portions by predicting defect-free structural features in each of the portions according to hidden layers trained to predict defect-free products. Each of the reconstructed portions are merged into a reconstructed image of a defect-free representation of the product. The reconstructed image is communicated to a contrastor to detect anomalies indicating defects in the product.

    Long Term Driving Danger Prediction System
    6.
    发明申请
    Long Term Driving Danger Prediction System 有权
    长期驾驶危险预警系统

    公开(公告)号：US20160297433A1

    公开(公告)日：2016-10-13

    申请号：US15088494

    申请日：2016-04-01

    Applicant: NEC Laboratories America, Inc.

    Inventor： Eric Cosatto

    IPC: B60W30/095 ,  B60Q9/00 ,  B60W10/30 ,  B60W40/09 ,  B60W10/18 ,  B60W10/04

    CPC classification number: B60Q9/008 ,  B60Q5/006 ,  B60Q9/00 ,  B60W10/04 ,  B60W10/18 ,  B60W10/30 ,  B60W30/0953 ,  B60W30/0956 ,  B60W40/04 ,  B60W40/06 ,  B60W40/09 ,  B60W50/14 ,  B60W50/16 ,  B60W2040/0827 ,  B60W2050/143 ,  B60W2050/146 ,  B60W2420/42 ,  B60W2420/52 ,  B60W2540/22 ,  B60W2540/26 ,  B60W2540/30 ,  B60W2550/12 ,  B60W2550/20 ,  B60W2550/402 ,  B60W2710/18 ,  B60W2710/30 ,  B60W2720/106

    Abstract: Systems and methods are disclosed to assist a driver with a dangerous condition by creating a graph representation where traffic participants and static elements are the vertices and the edges are relations between pairs of vertices; adding attributes to the vertices and edges of the graph based on information obtained on the driving vehicle, the traffic participants and additional information; creating a codebook of dangerous driving situations, each represented as graphs; performing subgraph matching between the graphs in the codebook and the graph representing a current driving situation to select a set of matching graphs from the codebook; determining a distance metric between each selected codebook graphs and the matching subgraph of the current driving situation; from codebook graphs with a low distance, determining potential dangers; and generating an alert if one or more of the codebook dangers are imminent.

    Abstract translation: 公开了系统和方法，以通过创建图形表示来帮助驾驶员处于危险状态，其中交通参与者和静态元素是顶点，并且边缘是顶点对之间的关​​系; 根据驾驶车辆上获得的信息，交通参与者和附加信息，向图形的顶点和边缘添加属性; 制作危险驾驶状况的码本，每个代表图表; 执行代码本中的图表和表示当前驾驶状况的图形之间的子图匹配，以从码本中选择一组匹配图; 确定每个所选码本图和当前驾驶状况的匹配子图之间的距离度量; 从距离较小的码本图，确定潜在的危险; 并且如果迫切需要一个或多个码本危险，则生成警报。

    Detecting dangerous driving situations by parsing a scene graph of radar detections
    7.
    发明授权
    Detecting dangerous driving situations by parsing a scene graph of radar detections 有权

    公开(公告)号：US11055605B2

    公开(公告)日：2021-07-06

    申请号：US15785796

    申请日：2017-10-17

    Applicant: NEC Laboratories America, Inc.

    Inventor： Hans Peter Graf ,  Eric Cosatto ,  Iain Melvin

    IPC: G06N3/08 ,  G06N3/04 ,  G01S7/41 ,  G01S13/931

    Abstract: A computer-implemented method executed by a processor for training a neural network to recognize driving scenes from sensor data received from vehicle radar is presented. The computer-implemented method includes extracting substructures from the sensor data received from the vehicle radar to define a graph having a plurality of nodes and a plurality of edges, constructing a neural network for each extracted substructure, combining the outputs of each of the constructed neural networks for each of the plurality of edges into a single vector describing a driving scene of a vehicle, and classifying the single vector into a set of one or more dangerous situations involving the vehicle.

    Machine learning based classification of higher-order spatial modes
    8.
    发明授权
    Machine learning based classification of higher-order spatial modes 有权

    公开(公告)号：US10763989B2

    公开(公告)日：2020-09-01

    申请号：US16655103

    申请日：2019-10-16

    Applicant: NEC Laboratories America, Inc.

    Inventor： Giovanni Milione ,  Philip Ji ,  Eric Cosatto

    IPC: H04B10/00 ,  H04J14/04 ,  G06N3/02 ,  G06N20/00 ,  G06K9/62 ,  H04J14/00

    Abstract: Aspects of the present disclosure describe systems, methods and structures for classification of higher-order spatial modes using machine learning systems and methods in which the classification of high-order spatial modes emitted from a multimode optical fiber does not require indirect measurement of the complex amplitude of a light beam's electric field using interferometry or, holographic techniques via unconventional optical devices/elements, which have prohibitive cost and efficacy; classification of high-order spatial modes emitted from a multimode optical fiber is not dependent on a light beam's alignment, size, wave front (e.g. curvature, etc.), polarization, or wavelength, which has prohibitive cost and efficacy; classification of higher-order spatial modes from a multimode optical fiber does not require a prohibitive amount of experimentally generated training examples, which, in turn, has prohibitive efficacy; and the light beam from a multimode optical fiber can be advantageously separated into two orthogonal polarization components, such that, the different linear combination of higher order spatial modes comprising each polarization component can be classified.

Patent Agency Ranking