公开(公告)号：US20150049113A1

公开(公告)日：2015-02-19

申请号：US14151664

申请日：2014-01-09

Applicant: QUALCOMM INCORPORATED

Inventor： Md Sazzadur RAHMAN ,  Kexi LIU ,  Martin H. RENSCHLER

IPC: G06F17/30 ,  G06T19/00

CPC classification number: G06F17/30277 ,  G02B27/017 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0187 ,  G06F3/013 ,  G06F3/017 ,  G06F17/30247 ,  G06F17/30637 ,  G06F17/30864 ,  G06F17/30879 ,  G06T19/006

Abstract: A method, an apparatus, and a computer program product conduct online visual searches through an augmented reality (AR) device having an optical see-through head mounted display (HMD). An apparatus identifies a portion of an object in a field of view of the HMD based on user interaction with the HMD. The portion includes searchable content, such as a barcode. The user interaction may be an eye gaze or a gesture. A user interaction point in relation to the HMD screen is tracked to locate a region of the object that includes the portion and the portion is detected within the region. The apparatus captures an image of the portion. The identified portion of the object does not encompass the entirety of the object. Accordingly, the size of the image is less than the size of the object in the field of view. The apparatus transmits the image to a visual search engine.

Abstract translation: 一种方法，装置和计算机程序产品通过具有光学透视头安装显示器（HMD）的增强现实（AR）装置进行在线视觉搜索。 一种装置基于与HMD的用户交互来识别HMD的视场中的对象的一部分。 该部分包括可搜索的内容，例如条形码。 用户交互可以是眼睛注视或手势。 跟踪与HMD屏幕相关的用户交互点，以定位包含该部分的对象的区域，并且在该区域内检测该部分。 该装置捕获该部分的图像。 对象的识别部分不包含对象的整体。 因此，图像的尺寸小于在视野中的对象的尺寸。 该装置将图像发送到视觉搜索引擎。

公开(公告)号：US20140198129A1

公开(公告)日：2014-07-17

申请号：US13740256

申请日：2013-01-13

Applicant: QUALCOMM INCORPORATED

Inventor： Kexi LIU ,  Frederick D. KIM ,  Martin H. RESCHLER

IPC: G06F3/01

CPC classification number: G06F3/013 ,  G02B27/017 ,  G02B2027/0127 ,  G02B2027/014 ,  G02B2027/0178 ,  G02B2027/0187 ,  G06F3/04815 ,  G06T19/006

Abstract: An apparatus, a method, and a computer program product are provided. The apparatus detects an eye gaze on a first region in a real world scene, sets a boundary that surrounds the first region, the boundary excluding at least a second region in the real world scene, performs an object recognition procedure on the first region within the boundary, and refrains from performing an object recognition procedure on the at least the second region.

Abstract translation: 提供了一种装置，方法和计算机程序产品。 设备检测现实世界场景中的第一区域上的眼睛注视，设置围绕第一区域的边界，排除现实世界场景中的至少第二区域的边界，在第一区域内的第一区域内执行对象识别过程 边界，并且禁止在至少第二区域上执行对象识别过程。