Object recognition method, descriptor generating method for object recognition, and descriptor for object recognition
    1.
    发明授权
    Object recognition method, descriptor generating method for object recognition, and descriptor for object recognition 有权
    对象识别方法,对象识别的描述符生成方法和对象识别的描述符

    公开(公告)号:US09104944B2

    公开(公告)日:2015-08-11

    申请号:US13729739

    申请日:2012-12-28

    Abstract: An object recognition method, a descriptor generating method for object recognition, and a descriptor for object recognition capable of extracting feature points using the position relationship and color information relationship between points in a group that are sampled from an image of an object, and capable of recognizing the object using the feature points, the object recognition method including extracting feature components of a point cloud using the position information and the color information of the points that compose the point cloud of the three-dimensional (3D) image of an object, generating a descriptor configured to recognize the object using the extracted feature components; and performing the object recognition based on the descriptor.

    Abstract translation: 一种对象识别方法,用于对象识别的描述符生成方法,以及能够使用从对象的图像采样的组中的点之间的位置关系和颜色信息关系来提取特征点的对象识别的描述符,并且能够 使用特征点识别对象,所述对象识别方法包括使用位置信息提取点云的特征成分和构成对象的三维(3D)图像的点云的点的颜色信息,生成 描述符,其被配置为使用所提取的特征成分来识别对象; 以及基于描述符执行对象识别。

    Mobile apparatus and method for controlling the same
    3.
    发明授权
    Mobile apparatus and method for controlling the same 有权
    移动装置及其控制方法

    公开(公告)号:US09082016B2

    公开(公告)日:2015-07-14

    申请号:US13645860

    申请日:2012-10-05

    CPC classification number: G06K9/00664 G06K9/4671

    Abstract: A method of controlling a mobile apparatus includes acquiring a first original image and a second original image, extracting a first feature point of the first original image and a second feature point of the second original image, generating a first blurring image and a second blurring image by blurring the first original image and the second original image, respectively, calculating a similarity between at least two images of the first original image, the second original image, the first blurring image, and the second blurring image, determining a change in scale of the second original image based on the calculated similarity, and controlling at least one of an object recognition and a position recognition by matching the second feature point of the second original image to the first feature point of the first original image based on the change in scale.

    Abstract translation: 一种控制移动装置的方法包括获取第一原始图像和第二原始图像,提取第一原始图像的第一特征点和第二原始图像的第二特征点,生成第一模糊图像和第二模糊图像 通过分别模糊第一原始图像和第二原始图像,计算第一原始图像,第二原始图像,第一模糊图像和第二模糊图像的至少两个图像之间的相似度,确定第一原始图像和第二原始图像的尺度变化 基于所计算出的相似度的第二原始图像,并且基于尺度变化将第二原始图像的第二特征点与第一原始图像的第一特征点进行匹配来控制对象识别和位置识别中的至少一个 。

    MOBILE APPARATUS AND METHOD FOR CONTROLLING THE SAME
    4.
    发明申请
    MOBILE APPARATUS AND METHOD FOR CONTROLLING THE SAME 有权
    移动装置及其控制方法

    公开(公告)号:US20130089235A1

    公开(公告)日:2013-04-11

    申请号:US13645860

    申请日:2012-10-05

    CPC classification number: G06K9/00664 G06K9/4671

    Abstract: A method of controlling a mobile apparatus includes acquiring a first original image and a second original image, extracting a first feature point of the first original image and a second feature point of the second original image, generating a first blurring image and a second blurring image by blurring the first original image and the second original image, respectively, calculating a similarity between at least two images of the first original image, the second original image, the first blurring image, and the second blurring image, determining a change in scale of the second original image based on the calculated similarity, and controlling at least one of an object recognition and a position recognition by matching the second feature point of the second original image to the first feature point of the first original image based on the change in scale.

    Abstract translation: 一种控制移动装置的方法包括获取第一原始图像和第二原始图像,提取第一原始图像的第一特征点和第二原始图像的第二特征点,生成第一模糊图像和第二模糊图像 通过分别模糊第一原始图像和第二原始图像,计算第一原始图像,第二原始图像,第一模糊图像和第二模糊图像的至少两个图像之间的相似度,确定第一原始图像和第二原始图像的尺度变化 基于所计算出的相似度的第二原始图像,并且基于尺度变化将第二原始图像的第二特征点与第一原始图像的第一特征点进行匹配来控制对象识别和位置识别中的至少一个 。

    Camera assembly having a wide viewing angle and image acquisition method using the same
    6.
    发明授权
    Camera assembly having a wide viewing angle and image acquisition method using the same 有权
    具有宽视角的摄像机组件和使用其的图像采集方法

    公开(公告)号:US09219859B2

    公开(公告)日:2015-12-22

    申请号:US14020107

    申请日:2013-09-06

    CPC classification number: H04N5/23238

    Abstract: Disclosed is a camera assembly having a wide viewing angle using a variable mirror. The camera assembly includes a variable mirror located in front of an image sensor, a variable mirror controller to switch a mode of the variable mirror to one of a reflection mode to reflect light incident upon the variable mirror and a transmission mode to transmit light incident upon the variable mirror, an image sensor to sense the light reflected by the variable mirror to acquire first image data and to sense the light transmitted through the variable mirror to acquire second image data, and an image processing unit to register the first image data and the second image data acquired by the image sensor to generate a third image.

    Abstract translation: 公开了一种使用可变镜具有宽视角的相机组件。 相机组件包括位于图像传感器前面的可变镜,可变镜控制器,用于将可变镜的模式切换到反射模式中的一种,以反射入射在可变镜上的光,以及透射模式以透射入射到其上的光 可变镜,用于感测由可变镜反射的光以获取第一图像数据并感测透过可变镜来传输的光以获取第二图像数据的图像传感器,以及图像处理单元,用于将第一图像数据和 由图像传感器获取的第二图像数据以产生第三图像。

    Method of recognizing stairs in three dimensional data image
    9.
    发明授权
    Method of recognizing stairs in three dimensional data image 有权
    在三维数据图像中识别楼梯的方法

    公开(公告)号:US09552640B2

    公开(公告)日:2017-01-24

    申请号:US13669960

    申请日:2012-11-06

    Abstract: A method of recognizing stairs in a 3D data image includes an image acquirer that acquires a 3D data image of a space in which stairs are located. An image processor calculates a riser height between two consecutive treads of the stairs in the 3D data image, identifies points located between the two consecutive treads according to the calculated riser height, and detects a riser located between the two consecutive treads through the points located between the two consecutive treads. Then, the image processor calculates a tread depth between two consecutive risers of the stairs in the 3D data image, identifies points located between the two consecutive risers according to the calculated tread depth, and detects a tread located between the two consecutive risers through the points located between the two consecutive risers.

    Abstract translation: 在3D数据图像中识别楼梯的方法包括获取楼梯所在的空间的3D数据图像的图像获取器。 图像处理器计算3D数据图像中楼梯的两个连续胎面之间的提升管高度,根据计算的提升管高度识别位于两个连续胎面之间的点,并且通过位于两个连续胎面之间的位置检测位于两个连续胎面之间的提升管 连续两次。 然后,图像处理器计算3D数据图像中楼梯的两个连续梯级之间的胎面深度,根据计算的胎面深度识别位于两个连续立管之间的点,并且通过点检测位于两个连续立管之间的胎面 位于两个连续的立管之间。

    METHOD OF RECOGNIZING STAIRS IN THREE DIMENSIONAL DATA IMAGE
    10.
    发明申请
    METHOD OF RECOGNIZING STAIRS IN THREE DIMENSIONAL DATA IMAGE 有权
    在三维数据图像中识别站点的方法

    公开(公告)号:US20130127996A1

    公开(公告)日:2013-05-23

    申请号:US13669960

    申请日:2012-11-06

    Abstract: A method of recognizing stairs in a 3D data image includes an image acquirer that acquires a 3D data image of a space in which stairs are located. An image processor calculates a riser height between two consecutive treads of the stairs in the 3D data image, identifies points located between the two consecutive treads according to the calculated riser height, and detects a riser located between the two consecutive treads through the points located between the two consecutive treads. Then, the image processor calculates a tread depth between two consecutive risers of the stairs in the 3D data image, identifies points located between the two consecutive risers according to the calculated tread depth, and detects a tread located between the two consecutive risers through the points located between the two consecutive risers.

    Abstract translation: 在3D数据图像中识别楼梯的方法包括获取楼梯所在的空间的3D数据图像的图像获取器。 图像处理器计算3D数据图像中楼梯的两个连续胎面之间的提升管高度,根据计算的提升管高度识别位于两个连续胎面之间的点,并且通过位于两个连续胎面之间的位置检测位于两个连续胎面之间的提升管 连续两次。 然后,图像处理器计算3D数据图像中楼梯的两个连续梯级之间的胎面深度,根据计算的胎面深度识别位于两个连续立管之间的点,并且通过点检测位于两个连续立管之间的胎面 位于两个连续的立管之间。

Patent Agency Ranking