公开(公告)号：US20140267770A1

公开(公告)日：2014-09-18

申请号：US13804643

申请日：2013-03-14

Applicant: QUALCOMM INCORPORATED

Inventor： Michael GERVAUTZ ,  Gerald V. WRIGHT, JR. ,  Roy LAWRENCE ASHOK INIGO

IPC: H04N5/232

CPC classification number: H04N5/23296 ,  G06F8/61 ,  G06F17/30244 ,  H04L67/32

Abstract: Techniques for managing applications associated with a mobile device are provided. The techniques disclosed herein include techniques for obtaining an image of an object in the view of a camera associated with a mobile device, identifying the object in the image based on attributes of the object extracted from the image, and determining whether one or more applications are associated with the object. If there are one or more applications associated with the real-world object, an application associated with the object can be automatically launched on the mobile device. The association between a real-world object and an application may be identified by a visual indicator, such as an icon, symbol, or other markings on the object that indicates that the object is associated with one or more applications.

Abstract translation: 提供了用于管理与移动设备相关联的应用的技术。 本文公开的技术包括用于在与移动设备相关联的摄像机的视图中获得对象的图像的技术，基于从图像提取的对象的属性来识别图像中的对象，以及确定一个或多个应用是否是 与对象相关联。 如果存在与真实世界对象相关联的一个或多个应用，则可以在移动设备上自动启动与该对象相关联的应用。 真实世界对象和应用之间的关联可以通过视觉指示符来标识，诸如图标，符号或对象上的其它指示对象与一个或多个应用相关联的标记。

公开(公告)号：US20140192210A1

公开(公告)日：2014-07-10

申请号：US14021337

申请日：2013-09-09

Applicant: QUALCOMM Incorporated

Inventor： Michael GERVAUTZ ,  Jieun KIM ,  Per O. NIELSEN ,  Roy LAWRENCE ASHOK INIGO ,  Qi PAN ,  Romain TALLONNEAU

IPC: G06K9/18 ,  G06F3/00 ,  H04N1/00

CPC classification number: G06K9/18 ,  G06F3/005 ,  G06K9/228 ,  G06T7/246 ,  G06T7/74 ,  G06T2207/30244 ,  G10L13/00 ,  H04N1/00204

Abstract: Embodiments disclosed pertain to mobile device based text detection and tracking. In some embodiments, a first reference frame is obtained by performing Optical Character Recognition (OCR) on an image frame captured by a camera to locate and recognize a first text block. A subsequent image frame may be selected from a set of subsequent image frames based on parameters associated with the selected subsequent image and a second reference frame may be obtained by performing OCR on the selected subsequent image frame to recognize a second text block. A geometric relationship between the first and second text blocks is determined based on a position of the first text block in the second reference frame and a pose associated with the second reference frame.

Abstract translation: 所公开的实施例涉及基于移动设备的文本检测和跟踪。 在一些实施例中，通过在由相机拍摄的图像帧上执行光学字符识别（OCR）来定位和识别第一文本块来获得第一参考帧。 可以基于与所选择的后续图像相关联的参数从一组后续图像帧中选择后续图像帧，并且可以通过在所选择的后续图像帧上执行OCR以识别第二文本块来获得第二参考帧。 基于第二参考帧中的第一文本块的位置和与第二参考帧相关联的姿势来确定第一和第二文本块之间的几何关系。

公开(公告)号：US20160239986A1

公开(公告)日：2016-08-18

申请号：US14625380

申请日：2015-02-18

Applicant: QUALCOMM Incorporated

Inventor： Erick MENDEZ MENDEZ ,  Daniel WAGNER ,  Michael GERVAUTZ

IPC: G06T11/00 ,  G06T19/00 ,  G06T3/40

CPC classification number: G06T11/001 ,  G06T19/006

Abstract: Disclosed is a method and apparatus for using color measurement features at multiple scales for a Color Transfer technique. In one embodiment, the functions implemented include: resizing a ground truth image target frame to a plurality of different scales; selecting one or more color measurement features from the ground truth image target frame at each of the plurality of different scales; making a color measurement for each color measurement feature in the ground truth image target frame; and adjusting colors of a virtual object in an augmented frame based at least in part on the color measurements.

Abstract translation: 公开了一种用于在彩色传输技术中使用多尺度的色彩测量特征的方法和装置。 在一个实施例中，所实现的功能包括：将地面真实图像目标帧的大小调整到多个不同的尺度; 在所述多个不同尺度的每一个上从所述地面真实图像目标帧中选择一个或多个颜色测量特征; 对地面真实图像目标帧中的每个颜色测量特征进行颜色测量; 以及至少部分地基于所述颜色测量来调整增强帧中的虚拟对象的颜色。

公开(公告)号：US20150279047A1

公开(公告)日：2015-10-01

申请号：US14538732

申请日：2014-11-11

Applicant: QUALCOMM INCORPORATED

Inventor： Zeeshan ZIA ,  Emilio MAGGIO ,  Qi PAN ,  Michael GERVAUTZ ,  Zsolt SZALAVARI

IPC: G06T7/00 ,  G06T7/40

CPC classification number: G06T7/90 ,  G06F16/5838 ,  G06K9/4661 ,  G06T2207/10024

Abstract: Disclosed is a method and apparatus for exemplars-based color classification. In one embodiment, the functions implemented include: processing an image captured by a camera to identify a first color profile that most closely matches colors of the image, wherein the first color profile is selected from a plurality of color profiles each color profile encoding data related to how two or more component colors appear under a different lighting condition.

Abstract translation: 公开了一种用于基于示例的颜色分类的方法和装置。 在一个实施例中，所实现的功能包括：处理由相机拍摄的图像，以识别与图像的颜色最接近匹配的第一颜色特征，其中，从多个颜色分布中选择每个颜色配置文件编码数据相关 如何在不同的照明条件下显示两个或多个分量颜色。

公开(公告)号：US20160117822A1

公开(公告)日：2016-04-28

申请号：US14522233

申请日：2014-10-23

Applicant: QUALCOMM Incorporated

Inventor： Winston YII ,  Gerhard REITMAYR ,  Peter H. RAUBER ,  Qi PAN ,  Zsolt SZALAVARI ,  Michael GERVAUTZ

IPC: G06T7/00

CPC classification number: G06T7/0038 ,  G06T7/35 ,  G06T7/38 ,  G06T7/55 ,  G06T7/77 ,  G06T2207/10016 ,  G06T2207/20076 ,  G06T2207/30241 ,  G06T2207/30244

Abstract: Disclosed is a method and apparatus for selecting a part of SLAM map information of a first device for transmission to a second device in a collaborative SLAM environment. In one embodiment, the functions implemented include: determining whether a 3D registration transformation between a map of the first device and a map of the second device is available; and transmitting a part of map information of the first device to the second device according to one of a first strategy or a second strategy based on whether or not a 3D registration transformation between the map of the first device and the map of the second device is available.

Abstract translation: 公开了一种用于在协作SLAM环境中选择用于传输到第二设备的第一设备的SLAM映射信息的一部分的方法和装置。 在一个实施例中，所实现的功能包括：确定第一设备的地图和第二设备的地图之间的3D注册变换是否可用; 以及基于第一设备的映射与第二设备的映射之间的3D注册变换是否是第一策略或第二策略中的一个，将第一设备的映射信息的一部分发送到第二设备 可用。

公开(公告)号：US20150098614A1

公开(公告)日：2015-04-09

申请号：US14494947

申请日：2014-09-24

Applicant: QUALCOMM Incorporated

Inventor： Andrew GEE ,  Qi PAN ,  Michael GERVAUTZ

IPC: G06K9/00 ,  G06T19/00

CPC classification number: G06K9/00624 ,  G06K9/00671 ,  G06T19/006

Abstract: A computer-implemented method of tracking a target object in an object recognition system includes acquiring a plurality of images with a camera. The method further includes simultaneously tracking the target object and dynamically building environment map data from the plurality of images. The tracking of the target object includes attempting to estimate a target pose of the target object with respect to the camera based on at least one of the plurality of images and based on target map data. Next, the method determines whether the tracking of the target object with respect to the camera is successful. If not, then the method includes inferring the target pose with respect to the camera based on the dynamically built environment map data. In one aspect the method includes fusing the inferred target pose with the actual target pose even if tracking is successful to improve robustness.

Abstract translation: 在物体识别系统中跟踪目标对象的计算机实现的方法包括用相机获取多个图像。 该方法还包括同时跟踪目标对象并从多个图像动态构建环境地图数据。 目标对象的跟踪包括基于多个图像中的至少一个并且基于目标地图数据来尝试估计目标物体相对于照相机的目标姿态。 接下来，该方法确定目标对象相对于照相机的跟踪是否成功。 如果不是，则该方法包括基于动态构建的环境地图数据推测相对于摄像机的目标姿态。 在一个方面，该方法包括将所推断的目标姿态与实际目标姿态进行融合，即使跟踪成功以提高鲁棒性。