中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

606 records (took 0.027 seconds)

    FULLY CONVOLUTIONAL INSTANCE-AWARE SEMANTIC SEGMENTATION
    1.
    发明申请
    FULLY CONVOLUTIONAL INSTANCE-AWARE SEMANTIC SEGMENTATION 审中-公开

    公开(公告)号：WO2018232592A1

    公开(公告)日：2018-12-27

    申请号：PCT/CN2017/089189

    申请日：2017-06-20

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC. ,  WEI, Yichen

    Inventor： WEI, Yichen ,  DAI, Jifeng ,  HU, Han

    IPC: G06T7/12

    CPC classification number: G06T7/11 ,  G06K9/3233 ,  G06K9/6292 ,  G06T7/143 ,  G06T7/194

    Abstract: Embodiments herein present a fully convolutional approach for instance-aware semantic segmentation. Embodiments herein, for a given visual image, locate predefined categories of objects therein and produce pixel masks for each object instance. One method embodiment includes receiving an image and generating a pixel-wise score map for a given region of interest within the received image for each pixel cell present therein. For each pixel cell within the region of interest, the method may detect whether the pixel cell belongs to an object to obtain a detection result and determine whether the pixel cell is inside an object instance boundary to obtain a segmentation result. The method may then fuse the results to obtain a result of inside or outside for each pixel cell and form at least one mask based on those values.

    논리적 화면 표시장치 생성 시스템 및 방법
    2.
    发明申请
    논리적 화면 표시장치 생성 시스템 및 방법 审中-公开

    公开(公告)号：WO2018110800A1

    公开(公告)日：2018-06-21

    申请号：PCT/KR2017/009907

    申请日：2017-09-08

    Applicant: 전자부품연구원

    Inventor： 박종빈 ,  정종진 ,  임태범 ,  김경원 ,  금승우 ,  문재원

    IPC: G06T7/11 ,  G06T7/194 ,  G06T11/60 ,  G06T19/20

    CPC classification number: G06T7/11 ,  G06T7/194 ,  G06T11/60 ,  G06T19/20

    Abstract: 본 발명에 따른 논리적 화면 표시장치를 생성하는 시스템은 하나 이상의 콘텐츠를 하나 이상의 디바이스로부터 수신하는 통신모듈, 상기 콘텐츠를 상기 논리적 화면 표시장치에 출력시키기 위한 프로그램이 저장된 메모리 및 상기 메모리에 저장된 프로그램을 실행시키는 프로세서를 포함한다. 이때, 상기 프로세서는 상기 프로그램을 실행시킴에 따라, 물리적 화면 표시장치의 출력 범위 내의 2차원 또는 3차원의 사물공간에 대하여 하나 이상의 논리적 화면 표시객체의 영역을 설정하고, 상기 설정된 논리적 화면 표시객체의 영역에 상기 수신한 콘텐츠를 출력시키는 하나 이상의 논리적 화면 표시장치를 생성하되, 상기 물리적 화면 표시장치와 상기 논리적 화면 표시객체는 L 대 M(L, M≥1)의 상호 관계를 갖고, 상기 논리적 화면 표시객체와 상기 논리적 화면 표시장치는 M 대 N(M, N≥1)의 상호 관계를 갖는다.

    COMBINATION VIDEO SURVEILLANCE SYSTEM AND PHYSICAL DETERRENT DEVICE
    3.
    发明申请
    COMBINATION VIDEO SURVEILLANCE SYSTEM AND PHYSICAL DETERRENT DEVICE 审中-公开
    组合视频监视系统和物理防御设备

    公开(公告)号：WO2018064773A1

    公开(公告)日：2018-04-12

    申请号：PCT/CA2017/051193

    申请日：2017-10-05

    Applicant: AVIGILON CORPORATION

    Inventor： BOONYASIRIWAT, Waris ,  BUZAS, Levente ,  FERNANDES, Alexander ,  GEDDERT, Joel ,  LITTLE, Eric ,  LIU, Joseph ,  OKRAINETZ, Christopher James Cullington ,  SAPTHARISHI, Mahesh ,  WANG, Yang

    IPC: G08B15/00 ,  G08B13/196

    CPC classification number: H04N7/181 ,  G06K9/00771 ,  G06T7/11 ,  G06T7/194 ,  G06T7/292 ,  G06T7/70 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/30232

    Abstract: A combination video surveillance system and physical deterrent device is disclosed. At least one camera module of the video surveillance system defines a first field of view and is operable to generate image data corresponding to the first field of view. A video analytics module is configured to detect a foreground visual object falling within the first field of view, classify the visual object, and determine an appearance of the visual object. A positioning module is configured to determine a physical location of the visual object. A deterrence device controller is configured to receive the determined physical location of the visual object, to control a deterrence device to be aimed at the physical location of the visual object, and to control the deterrence device to selectively emit the physical effect.

    Abstract translation: 公开了一种组合视频监视系统和物理威慑装置。 视频监视系统的至少一个相机模块定义第一视野并且可操作以生成对应于第一视野的图像数据。 视频分析模块被配置为检测落入第一视野内的前景视觉对象，分类视觉对象并确定视觉对象的外观。 定位模块被配置为确定视觉对象的物理位置。 威慑装置控制器被配置为接收所确定的视觉对象的物理位置，以控制威慑装置瞄准视觉对象的物理位置，并且控制威慑装置选择性地发出物理效果。

    LOW COMPLEXITY TAMPER DETECTION IN VIDEO ANALYTICS
    5.
    发明申请
    LOW COMPLEXITY TAMPER DETECTION IN VIDEO ANALYTICS 审中-公开
    视频分析中低复杂度篡改检测

    公开(公告)号：WO2018032270A1

    公开(公告)日：2018-02-22

    申请号：PCT/CN2016/095354

    申请日：2016-08-15

    Applicant: QUALCOMM INCORPORATED ,  CHEN, Ying ,  ZOU, Xuan ,  WANG, Lei ,  WEI, Jian ,  BI, Ning

    Inventor： CHEN, Ying ,  ZOU, Xuan ,  WANG, Lei ,  WEI, Jian ,  BI, Ning

    IPC: H04N7/18

    CPC classification number: H04N7/188 ,  G06K9/00771 ,  G06K9/346 ,  G06K9/4604 ,  G06T7/194 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/20021 ,  G06T2207/20224 ,  G06T2207/30232 ,  G08B13/19602 ,  G08B17/125 ,  G08B21/0476 ,  G08B29/046

    Abstract: Provided are methods, apparatuses, and computer-readable medium for automatic tamper detection that are both robust and low in complexity. The described methods can detect many different tamper types while also reducing false positives. In various implementations, the described methods include comparing an input frame against a background picture, using tiles of pixels taken from both the input frame and the background picture. When enough differences are detected between the tiles of pixels from the input frame and the tiles of pixels from the background picture, tamper is suspected. When tamper is suspected, further checking of the frame may be enabled, including checking for blur and/or checking a downsampled version of the whole frame. The additional checks can confirm that an actual tamper of the camera has occurred.

    Abstract translation: 提供了用于自动篡改检测的方法，装置和计算机可读介质，其既复杂又复杂。 所描述的方法可以检测许多不同的篡改类型，同时还减少误报。 在各种实现中，所描述的方法包括使用从输入帧和背景图片两者获取的像素块来比较输入帧与背景图片。 当检测到来自输入帧的像素的瓦片与来自背景图片的像素瓦片之间有足够的差异时，怀疑是篡改。 当怀疑篡改时，可以启用进一步检查帧，包括检查模糊和/或检查整个帧的下采样版本。 额外的检查可以确认相机发生了实际的篡改。

    METHODS AND SYSTEMS OF PERFORMING BLOB FILTERING IN VIDEO ANALYTICS
    6.
    发明申请
    METHODS AND SYSTEMS OF PERFORMING BLOB FILTERING IN VIDEO ANALYTICS 审中-公开
    在视频分析中执行BLOB滤波的方法和系统

    公开(公告)号：WO2018031096A1

    公开(公告)日：2018-02-15

    申请号：PCT/US2017/034572

    申请日：2017-05-25

    Applicant: QUALCOMM INCORPORATED

    Inventor： CHEN, Ying ,  REN, Jianfeng ,  WEI, Jian ,  BI, Ning

    IPC: G06K9/38 ,  G06K9/00

    CPC classification number: G06K9/00577 ,  G06K9/00771 ,  G06K9/342 ,  G06T5/20 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/20024 ,  G06T2207/20221 ,  G06T2207/30232

    Abstract: Techniques and systems are provided for processing video data. For example, techniques and systems are provided for performing content-adaptive blob filtering. A number of blobs generated for a video frame is determined. A size of a first blob from the blobs is determined, the first blob including pixels of at least a portion of a first foreground object in the video frame. The first blob is filtered from the plurality of blobs when the size of the first blob is less than a size threshold. The size threshold is determined based on the number of the plurality of blobs generated for the video frame.

    Abstract translation: 提供了用于处理视频数据的技术和系统。 例如，提供用于执行内容自适应blob过滤的技术和系统。 确定为视频帧生成的多个斑点。 确定来自斑点的第一斑点的大小，第一斑点包括视频帧中第一前景对象的至少一部分的像素。 当第一斑点的尺寸小于尺寸阈值时，从多个斑点中滤出第一斑点。 大小阈值是根据为视频帧生成的多个斑点的数量确定的。

    SYSTEM AND METHOD FOR ACHIEVING FAST AND RELIABLE TIME-TO-CONTACT ESTIMATION USING VISION AND RANGE SENSOR DATA FOR AUTONOMOUS NAVIGATION
    9.
    发明申请
    SYSTEM AND METHOD FOR ACHIEVING FAST AND RELIABLE TIME-TO-CONTACT ESTIMATION USING VISION AND RANGE SENSOR DATA FOR AUTONOMOUS NAVIGATION 审中-公开
    使用用于自主导航的视觉和范围传感器数据实现快速且可靠的接触时间估计的系统和方法

    公开(公告)号：WO2017139516A1

    公开(公告)日：2017-08-17

    申请号：PCT/US2017/017275

    申请日：2017-02-09

    Applicant: HRL LABORATORIES, LLC

    Inventor： MONTERROZA, Fredy ,  KIM, Kyungnam ,  KHOSLA, Deepark

    IPC: G05D1/00 ,  G05D1/02 ,  G06T7/11 ,  G06T7/70

    CPC classification number: G06T7/11 ,  G05D1/0246 ,  G05D1/0274 ,  G06T7/194 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20221 ,  G06T2207/30261

    Abstract: Described is a robotic system for detecting obstacles reliably with their ranges by a combination of two-dimensional and three-dimensional sensing. In operation, the system receives an image from a monocular video and range depth data from a range sensor of a scene proximate a mobile platform. The image is segmented, into multiple object regions of interest and time-to-contact (TTC) value are calculated by estimating motion field and operating on image intensities. A two-dimensional (2D) TTC map is then generated by estimating average TTC values over the multiple object regions of interest. A three-dimensional TTC map is then generated by fusing the range depth data with image. Finally, a range-fused TTC map is generated by averaging the 2D TTC map and the 3D TTC map,

    Abstract translation: 描述了一种机器人系统，用于通过二维和三维感测的组合来可靠地以其范围检测障碍物的机器人系统。 在操作中，系统接收来自单目视频的图像和来自邻近移动平台的场景的距离传感器的距离深度数据。 将图像分割成多个感兴趣的对象区域，并且通过估计运动场和对图像强度进行操作来计算接触时间（TTC）值。 然后通过估计多个感兴趣对象区域上的平均TTC值来生成二维（2D）TTC图。 然后通过将距离深度数据与图像融合来生成三维TTC地图。 最后，通过对2D TTC图和3D TTC图进行平均，生成范围融合的TTC图。

    A METHOD AND A 3D IMAGE PROCESSING SYSTEM FOR EXTRACTING OBJECT IMAGE DATA, AND A ROBOT SYSTEM COMPRISING A 3D IMAGE PROCESSING SYSTEM
    10.
    发明申请
    A METHOD AND A 3D IMAGE PROCESSING SYSTEM FOR EXTRACTING OBJECT IMAGE DATA, AND A ROBOT SYSTEM COMPRISING A 3D IMAGE PROCESSING SYSTEM 审中-公开
    用于提取对象图像数据的方法和3D图像处理系统以及包括3D图像处理系统的机器人系统

    公开(公告)号：WO2017133757A1

    公开(公告)日：2017-08-10

    申请号：PCT/EP2016/052162

    申请日：2016-02-02

    Applicant: ABB SCHWEIZ AG

    Inventor： HOLMBERG, Johnny ,  WAHLSTRÖM, Magnus

    IPC: G06T7/00

    CPC classification number: G06T7/174 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10028 ,  G06T2207/20224

    Abstract: A method for extracting object image data from a 3D image comprising the following steps: obtaining background image data in an image coordinate system (x i , y i ,Z i ) of a 3D image vision system, based on a 3D image of a background scene (100); transforming the background image data related to the image coordinate system into transformed background image data related to a fixed coordinate system (X F , y F , Z F ) (200); storing the transformed background image data and storing location data related to the fixed coordinate system, said location data being associated with the location of the 3D image vision system when obtaining the 3D image (300); placing an object in the background scene and obtaining combined image data related to the image coordinate system, based on a 3D image of the object and the background scene (400); transforming the combined image data related to the image coordinate system to transformed combined image data related to the fixed coordinate system (500), and obtaining extracted object image data by subtracting the transformed background image data from the transformed combined image data (600). Also described is a 3D image processing system (13) for extracting object image data, comprising a 3D image vision system (5), and a computer unit (15)

    Abstract translation: 一种用于从3D图像中提取物体图像数据的方法，包括以下步骤：获得图像坐标系统（x i，y i， 基于背景场景的3D图像（100），基于所述3D图像视觉系统的所述3D图像，确定所述3D图像视觉系统中的所述3D图像。 将与图像坐标系相关的背景图像数据转换为与固定坐标系（X F，Y F，Z F）有关的变换背景图像数据， （200）; 存储变换的背景图像数据并存储与固定坐标系有关的位置数据，所述位置数据在获得3D图像（300）时与3D图像视觉系统的位置相关联; 基于所述对象和所述背景场景的3D图像（400），将对象放置在所述背景场景中并且获得与所述图像坐标系统相关的组合图像数据; 将与图像坐标系相关的组合图像数据变换成与固定坐标系有关的变换后的组合图像数据（500），并且通过从变换后的组合图像数据中减去变换后的背景图像数据来获得提取的对象图像数据（600）。 还描述了用于提取对象图像数据的3D图像处理系统（13），其包括3D图像视觉系统（5）和计算机单元（15）

Patent Agency Ranking