中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.016 seconds)

    Polarized gaze tracking
    6.
    发明授权
    Polarized gaze tracking 有权
    极化注视跟踪

    公开(公告)号：US09330302B2

    公开(公告)日：2016-05-03

    申请号：US14191305

    申请日：2014-02-26

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Vaibhav Thukral ,  Sudipta Sinha ,  Vivek Pradeep ,  Timothy Andrew Large ,  Nigel Stuart Keam ,  David Nister

    IPC: H04N5/235 ,  G06K9/00 ,  H04N5/232 ,  G06F3/01 ,  G06K9/20

    CPC classification number: G06K9/00335 ,  G06F3/013 ,  G06K9/00604 ,  G06K9/2027 ,  H04N5/23219 ,  H04N5/2354

    Abstract: Embodiments that relate to determining gaze locations are disclosed. In one embodiment a method includes shining light along an outbound light path to the eyes of the user wearing glasses. Upon detecting the glasses, the light is dynamically polarized in a polarization pattern that switches between a random polarization phase and a single polarization phase, wherein the random polarization phase includes a first polarization along an outbound light path and a second polarization orthogonal to the first polarization along a reflected light path. The single polarization phase has a single polarization. During the random polarization phases, glares reflected from the glasses are filtered out and pupil images are captured. Glint images are captured during the single polarization phase. Based on pupil characteristics and glint characteristics, gaze locations are repeatedly detected.

    Abstract translation: 公开了与确定凝视位置有关的实施例。 在一个实施例中，一种方法包括沿着出射光路将光照射到佩戴眼镜的用户的眼睛。 在检测到眼镜时，光以在随机偏振相位和单极化相位之间切换的偏振图案中被动态偏振，其中随机偏振相位包括沿着出射光路的第一偏振和与第一偏振正交的第二偏振 沿反射光路。 单极化相具有单极化。 在随机极化阶段期间，从眼镜反射的眩光被滤出并且捕获瞳孔图像。 在单极化阶段期间捕获闪烁图像。 基于瞳孔特征和闪光特征，重复检测注视位置。

    OBJECT IDENTIFICATION USING 3-D CURVE MATCHING
    9.
    发明申请
    OBJECT IDENTIFICATION USING 3-D CURVE MATCHING 有权
    使用三维曲线匹配的对象标识

    公开(公告)号：US20150310257A1

    公开(公告)日：2015-10-29

    申请号：US14794608

    申请日：2015-07-08

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Richard Szeliski ,  Edward Hsiao ,  Sudipta Sinha ,  Krishnan Ramnath ,  Charles Zitnick ,  Simon Baker

    IPC: G06K9/00 ,  G06T7/00

    CPC classification number: G06K9/00214 ,  G06K9/00785 ,  G06T7/564 ,  G06T2207/30236

    Abstract: The claimed subject matter provides for systems and/or methods for identification of instances of an object of interest in 2D images by creating a database of 3D curve models of each desired instance and comparing an image of an object of interest against such 3D curve models of instances. The present application describes identifying and verifying the make and model of a car from a possibly single image—after the models have been populated with training data of test images of many makes and models of cars. In one embodiment, an identification system may be constructed by generating a 3D curve model by back-projecting edge points onto a visual hull reconstruction from silhouettes of an instance. The system and methods employ chamfer distance and orientation distance provides reasonable verification performance, as well as an appearance model for the taillights of the car to increase the robustness of the system.

    Abstract translation: 所要求保护的主题提供用于通过创建每个期望实例的3D曲线模型的数据库来识别2D图像中感兴趣对象的实例的系统和/或方法，并将感兴趣对象的图像与3D图像的3D曲线模型进行比较 实例。 本申请描述了从可能单个图像中识别和验证汽车的品牌和型号 - 在模型已经填充有许多车型和车型的测试图像的训练数据之后。 在一个实施例中，识别系统可以通过通过将边缘点反向投影到实例的轮廓的视觉船体重建上来生成3D曲线模型来构造。 系统和方法采用倒角距离和取向距离提供合理的验证性能，以及汽车尾灯的外观模型，以提高系统的鲁棒性。

    Generating real-time sensor maps from videos and in-ground sensor data
    10.
    发明授权
    Generating real-time sensor maps from videos and in-ground sensor data 有权

    公开(公告)号：US10262396B1

    公开(公告)日：2019-04-16

    申请号：US16129462

    申请日：2018-09-12

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ranveer Chandra ,  Ashish Kapoor ,  Sudipta Sinha ,  Deepak Vasisht

    IPC: G06T3/40 ,  G06K9/00 ,  A01B79/00 ,  G06T3/00 ,  G06T7/73 ,  G01C11/02 ,  G06K9/62 ,  B64C39/02

    Abstract: An apparatus for generating precision maps of an area is disclosed. The apparatus receives sensor data, where the sensor data includes sensor readings each indicating a level of a parameter in one of a plurality of first portions of an area, and video data representing an aerial view of the area. The sensor data may be received from sensors that are each deployed in one of the first portions of the area. The video data may be received from an aerial vehicle. An orthomosaic may be generated from the video data, and the orthomosaic and the sensor data used to generate a predication model. The prediction model may then be used to extrapolate the sensor data to determine a level of the parameter in each of a plurality of second portions of the area. A precision map of the area may be generated using the extrapolated sensor readings.

Patent Agency Ranking