中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.016 seconds)

    METHOD OF COMPRESSING VIDEO FRAME USING DUAL OBJECT EXTRACTION AND OBJECT TRAJECTORY INFORMATION IN VIDEO ENCODING AND DECODING PROCESS
    3.
    发明申请
    METHOD OF COMPRESSING VIDEO FRAME USING DUAL OBJECT EXTRACTION AND OBJECT TRAJECTORY INFORMATION IN VIDEO ENCODING AND DECODING PROCESS 审中-公开
    使用双目标提取压缩视频帧的方法和视频编码和解码过程中的对象TRAJECTORY信息

    公开(公告)号：US20130251033A1

    公开(公告)日：2013-09-26

    申请号：US13742698

    申请日：2013-01-16

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Mi Kyong HAN ,  Eun Jin KO ,  Hyun Chul KANG ,  Noh-Sam PARK ,  Sang Wook PARK ,  Mi Ryong PARK ,  Jong Hyun JANG ,  Kwang Roh PARK

    IPC: H04N7/26

    CPC classification number: H04N19/543 ,  H04N19/23

    Abstract: Disclosed is a method of compressing video frame using dual object extraction and object trajectory information in a video encoding and decoding process, including: segmenting a background and a object from a reference frame in video to extract the object, extracting and encoding motion information of the object based on the object, determining whether a frame is a reference frame based on encoded video in a decoding process, if it is determined that the frame is the reference frame, generating background information of a prediction frame based on the reference frame, and generating the prediction frame by extracting an object of the reference frame and referring to header information to reflect motion information of the object.

    Abstract translation: 公开了一种在视频编码和解码过程中使用双目标提取和对象轨迹信息压缩视频帧的方法，包括：从视频中的参考帧分割背景和对象以提取对象，提取和编码对象的运动信息 对象，如果确定帧是参考帧，则基于参考帧生成预测帧的背景信息，并且生成基于帧的参考帧，并且基于所述参考帧生成预测帧的背景信息 通过提取参考帧的对象并参考头部信息来反映对象的运动信息来预测帧。

    METHOD AND APPARATUS FOR REMOVING COMPRESSED POISSON NOISE OF IMAGE BASED ON DEEP NEURAL NETWORK
    5.
    发明申请
    METHOD AND APPARATUS FOR REMOVING COMPRESSED POISSON NOISE OF IMAGE BASED ON DEEP NEURAL NETWORK 有权

    公开(公告)号：US20210042887A1

    公开(公告)日：2021-02-11

    申请号：US16987027

    申请日：2020-08-06

    Applicant: Electronics and Telecommunications Research Institute

    Inventor： Seok Bong YOO ,  Mi Kyong HAN

    IPC: G06T5/00 ,  G06T5/10 ,  G06T5/50 ,  G06N3/08 ,  G06N3/04

    Abstract: A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.

    METHOD AND APPARATUS FOR PROVIDING COPING SERVICE BASED ON CONTEXT-AWARE INFORMATION
    7.
    发明申请
    METHOD AND APPARATUS FOR PROVIDING COPING SERVICE BASED ON CONTEXT-AWARE INFORMATION 审中-公开
    基于上下文信息提供复印服务的方法和装置

    公开(公告)号：US20150026259A1

    公开(公告)日：2015-01-22

    申请号：US14169908

    申请日：2014-01-31

    Applicant: Electronics and Telecommunications Research Institute

    Inventor： Eunjin KO ,  Sangwook PARK ,  Mi Kyong HAN ,  Jong Hyun JANG

    IPC: H04L29/06 ,  H04L29/08

    CPC classification number: G06Q50/265 ,  H04L67/16 ,  H04M1/72538 ,  H04M1/72569

    Abstract: A method for providing a coping service based on context-aware information includes: recognizing a context through interworking with the devices provided in the space, and generating context-aware information; and searching for a service ID corresponding to the context-aware information from an awareness information and service mapping table in which awareness information occurrence time, occurrence place codes and service IDs are stored according to multiple awareness information IDs. Further, the method includes searching for workflow information corresponding to the searched service ID from a service workflow table in which workflow information according to service IDs is stored; and providing a service corresponding to the context awareness in accordance with the searched workflow.

    Abstract translation: 一种用于基于上下文感知信息提供应答服务的方法包括：通过与在该空间中提供的设备相互配合来识别上下文，以及生成上下文感知信息; 以及根据多个感知信息ID从识别信息和服务映射表搜索与上下文感知信息相对应的服务ID，其中，识别信息发生时间，发生地点代码和服务ID被存储。 此外，该方法包括从服务工作流表搜索与搜索到的服务ID相对应的工作流信息，其中存储根据服务ID的工作流信息; 以及根据搜索到的工作流提供与上下文感知相对应的服务。

    APPARATUS AND METHOD FOR PREDICTING ERROR OF ANNOTATION
    8.
    发明申请
    APPARATUS AND METHOD FOR PREDICTING ERROR OF ANNOTATION 审中-公开

    公开(公告)号：US20200334553A1

    公开(公告)日：2020-10-22

    申请号：US16854002

    申请日：2020-04-21

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Hyunjin YOON ,  Mi Kyong HAN

    IPC: G06N5/04 ,  G06N20/00

    Abstract: An apparatus and a method for predicting error possibility, including: generating a first annotation for input data for training by using an algorithm; performing a machine-learning for an annotation evaluation model based on the first annotation and a correction history for the first annotation; generating a second annotation for input data for evaluating by using the algorithm; and predicting the error probability of the second annotation based on the annotation evaluation model are provided.

Patent Agency Ranking