中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

82 records (took 0.021 seconds)

    Programmable annular led illumination-based high efficiency quantitative phase microscopy imaging method
    41.
    发明授权
    Programmable annular led illumination-based high efficiency quantitative phase microscopy imaging method 有权

    公开(公告)号：US11555992B2

    公开(公告)日：2023-01-17

    申请号：US16633037

    申请日：2018-02-26

    Applicant: NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Qian Chen ,  Chao Zuo ,  Jiasong Sun ,  Shijie Feng ,  Yuzhen Zhang ,  Guohua Gu

    IPC: G02B21/06 ,  G02B21/36 ,  G02B21/00

    Abstract: The invention discloses a programmable annular LED illumination-based high efficiency quantitative phase microscopy imaging method, the proposed method comprising the following steps: the derivation of system optical transfer function in a partially coherent illumination imaging system; the derivation of phase transfer function with the weak object approximation under the illumination of tilted axially symmetric coherent point illumination source; the extension of illumination from an axially symmetric coherence point source to a discrete annular point source, and the optical transfer function can be treated as an incoherent superposition of each pair of tilted axially symmetric coherent point sources. The acquisition of raw intensity dataset; the implementation of deconvolution for quantitative phase reconstruction. The invention derives the system phase transfer function under the tilted axially symmetric point light source in the case of partially coherent illumination, and promotes the optical phase transfer function of the discrete annular point light source. The programmability characteristic of LED array enables the annular illumination aperture to be flexibly adjustable, being applicable to different microscopic objects with different numerical apertures, and improving the compatibility and flexibility of the system.

    Intrusion detection method and system for internet of vehicles based on spark and combined deep learning
    43.
    发明授权
    Intrusion detection method and system for internet of vehicles based on spark and combined deep learning 有权

    公开(公告)号：US11503057B2

    公开(公告)日：2022-11-15

    申请号：US17506607

    申请日：2021-10-20

    Applicant: Nanjing University of Science and Technology

    Inventor： Yong Qi ,  Jianye Yu

    IPC: H04L9/40 ,  G06N3/08 ,  H04L67/12

    Abstract: An intrusion detection method and system for Internet of Vehicles based on Spark and combined deep learning are provided. The method includes the following steps: S1: setting up Spark distributed cluster; S2: initializing the Spark distributed cluster, constructing a convolutional neural network (CNN) and long short-term memory (LSTM) combined deep learning algorithm model, initializing parameters, and uploading collected data to a Hadoop distributed file system (HDFS); S3: reading the data from the HDFS for processing, and inputting the data to the CNN-LSTM combined deep learning algorithm model, for recognizing the data; and S4: dividing the data into multiple resilient distributed datasets (RDDs) for batch training with a preset number of iterations.

    WEAKLY SUPERVISED VIDEO ACTIVITY DETECTION METHOD AND SYSTEM BASED ON ITERATIVE LEARNING
    45.
    发明申请
    WEAKLY SUPERVISED VIDEO ACTIVITY DETECTION METHOD AND SYSTEM BASED ON ITERATIVE LEARNING 有权

    公开(公告)号：US20220189209A1

    公开(公告)日：2022-06-16

    申请号：US17425653

    申请日：2020-09-16

    Applicant: Nanjing University of Science and Technology

    Inventor： Yan Song ,  Rong Zou ,  Xiangbo Shu

    IPC: G06V40/20 ,  G06V10/82 ,  G06V10/40

    Abstract: The present disclosure relates to a weakly supervised video activity detection method and system based on iterative learning. The method includes: extracting spatial-temporal features of a video that contains actions; constructing a neural network model group; training a first neural network model according to the class label of the video, a class activation sequence output by the first neural network model, and a video feature output by the first neural network model; training the next neural network model according to the class label of the video, a pseudo temporal label output by the current neural network model, a class activation sequence output by the next neural network model, and a video feature output by the next neural network model; and performing action detection on the test video according to the neural network model corresponding to the highest detection accuracy value.

    Super-rapid three-dimensional topography measurement method and system based on improved fourier transform contour technique
    46.
    发明授权
    Super-rapid three-dimensional topography measurement method and system based on improved fourier transform contour technique 有权

    公开(公告)号：US11029144B2

    公开(公告)日：2021-06-08

    申请号：US16496815

    申请日：2018-02-26

    Applicant: NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Qian Chen ,  Chao Zuo ,  Shijie Feng ,  Jiasong Sun ,  Yuzhen Zhang ,  Guohua Gu

    IPC: G01B11/25

    Abstract: A super-rapid three-dimensional measurement method and system based on an improved Fourier transform contour technique is disclosed. The method comprises: firstly calibrating a measurement system to obtain calibration parameters, then cyclically projecting 2n patterns into a measured scene using a projector, wherein n patterns are binary sinusoidal fringes with different high frequency, and the other n patterns are all-white images with the values of 1, and projecting the all-white images between every two binary high-frequency sinusoidal fringes, and synchronously acquiring images using a camera; and then performing phase unwrapping on wrapped phases to obtain initial absolute phases, and correcting the initial absolute phases, and finally reconstructing a three-dimensional topography of the measured scene by exploiting the corrected absolute phases and the calibration parameters to obtain 3D spatial coordinates of the measured scene in a world coordinate system, thereby accomplishing three-dimensional topography measurement of an object. In this way, the precision of three-dimensional topography measurement is ensured, and the speed of three-dimensional topography measurement is improved.

    ANNULAR-IRRADIATION HIGH-RESOLUTION QUANTITATIVE PHASE MICROIMAGING METHOD BASED ON LIGHT INTENSITY TRANSFER EQUATION
    48.
    发明申请
    ANNULAR-IRRADIATION HIGH-RESOLUTION QUANTITATIVE PHASE MICROIMAGING METHOD BASED ON LIGHT INTENSITY TRANSFER EQUATION 有权

    公开(公告)号：US20210103135A1

    公开(公告)日：2021-04-08

    申请号：US16496548

    申请日：2018-02-26

    Applicant: NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： Qian CHEN ,  Chao ZUO ,  Jiasong SUN ,  Shijie FENG ,  Yuzhen ZHANG ,  Guohua GU

    IPC: G02B21/36 ,  G02B21/06 ,  G06T5/50 ,  G06T5/10

    Abstract: Annular-irradiation high-resolution quantitative phase microimaging based on light intensity transfer equation is proposed here. First, an annular aperture is designed for the imaging system illumination. And then, by invoking the weak object approximation, the parameters of annular illumination aperture and bright field microscopy are used to calculate a weak object optical transfer function (WOTF) on the basis of a partially coherent imaging theory. Finally, three intensity images are collected by a camera and the quantitative phase image of object is obtained by resolving the light intensity transfer equation with a deconvolution algorithm.
    The present method effectively resolves the tradeoff between the cloudy low-frequency noise and high-frequency fuzziness in the light intensity transfer equation, and the spatial imaging resolution of phase reconstruction is greatly increased. The achievable resolution is up to twice the objective lens numerical aperture resolution of bright field microscope with more robust of low-frequency noise. There is no need to have a complicated modification of traditional bright field microscopy, and the annular aperture enables the capability of high-resolution quantitative phase imaging with a bright field microscope.

    METHOD FOR INITIATING A GRAPHENE OXIDE THROUGH REDUCTION BY A REDUCTANT TO CONTROLLABLY RELEASE ORGANIC COMPOUNDS
    49.
    发明申请
    METHOD FOR INITIATING A GRAPHENE OXIDE THROUGH REDUCTION BY A REDUCTANT TO CONTROLLABLY RELEASE ORGANIC COMPOUNDS 审中-公开

    公开(公告)号：US20190389743A1

    公开(公告)日：2019-12-26

    申请号：US16155212

    申请日：2018-10-09

    Applicant: PEKING UNIVERSITY ,  NANJING UNIVERSITY OF SCIENCE AND TECHNOLOGY

    Inventor： DONGQIANG ZHU ,  BINGYU WANG ,  CHENHUI WEI

    IPC: C02F1/28 ,  B01J20/20 ,  B01J20/34 ,  G01N30/14

    Abstract: The present invention discloses a method for initiating a graphene oxide (GO) through reduction by a reductant to controllably release organic compounds, comprising the following steps: (1) mixing GO and a buffer solution; (2) further mixing with a sewage containing organic contaminants; (3) conducting solid-liquid separation, mixing the solid phase and the pure, introducing and N2; (4) further adding the reductant; (5) conducting sequential batch kinetics experiment. The present invention utilizes the size effect and polarity control of GO to selectively adsorb aromatic organic contaminants in sewage and fully transfer the selectively adsorbed organic contaminants from a large amount of sewage to a small amount of pure water by initiating using the reductant, and no extraction of the organic phase is required, the time for purification is reduced, and the energy consumption for purification is also reduced.

Patent Agency Ranking