公开(公告)号：US09412034B1

公开(公告)日：2016-08-09

申请号：US14609371

申请日：2015-01-29

Applicant: QUALCOMM Incorporated

Inventor： Youngmin Park ,  Daniel Wagner

IPC: G06K9/00 ,  G06K9/46 ,  G06T7/00 ,  G06T7/60

CPC classification number: G06K9/46 ,  G06K9/00624 ,  G06K2009/4666 ,  G06T7/246 ,  G06T7/50 ,  G06T7/60 ,  G06T2207/10028 ,  G06T2207/20021

Abstract: Disclosed are a system, apparatus, and method for performing occlusion handling for simultaneous localization and mapping. Occluded map points may be detected according to a depth-mask created according to an image keyframe. Dividing a scene into sections may optimize the depth-mask. Size of depth-mask points may be adjusted according to intensity. Visibility may be verified with an optimized subset of possible map points. Visibility may be propagated to nearby points in response to determining an initial visibility of a first point's surrounding image patch. Visibility may also be organized and optimized according to a grid.

Abstract translation: 公开了一种用于执行同时定位和映射的遮挡处理的系统，装置和方法。 可以根据根据图像关键帧创建的深度掩模来检测闭合的地图点。 将场景划分为多个部分可以优化深度掩码。 深度屏蔽点的大小可以根据强度进行调整。 可以通过可能的地图点的优化子集验证可见性。 响应于确定第一点的周围图像块的初始可视性，可见性可以传播到附近点。 还可以根据网格组织和优化可见性。

公开(公告)号：US20160098600A1

公开(公告)日：2016-04-07

申请号：US14967189

申请日：2015-12-11

Applicant: QUALCOMM Incorporated

Inventor： Daniel Wagner ,  Zsolt Szabolcs Szalavari

IPC: G06K9/00 ,  G06T7/40 ,  G06K9/46 ,  G06T7/00

CPC classification number: G06K9/00624 ,  G06K9/46 ,  G06K2009/4666 ,  G06T7/0004 ,  G06T7/248 ,  G06T7/40 ,  G06T2207/10016 ,  G06T2207/30108

Abstract: A mobile platform visually detects and/or tracks a target that includes a dynamically changing portion, or otherwise undesirable portion, using a feature dataset for the target that excludes the undesirable portion. The feature dataset is created by providing an image of the target and identifying the undesirable portion of the target. The identification of the undesirable portion may be automatic or by user selection. An image mask is generated for the undesirable portion. The image mask is used to exclude the undesirable portion in the creation of the feature dataset for the target. For example, the image mask may be overlaid on the image and features are extracted only from unmasked areas of the image of the target. Alternatively, features may be extracted from all areas of the image and the image mask used to remove features extracted from the undesirable portion.

Abstract translation: 移动平台使用排除不想要的部分的目标的特征数据集来目视地检测和/或跟踪包括动态变化部分或其他不期望的部分的目标。 通过提供目标的图像并识别目标的不期望的部分来创建要素数据集。 不期望的部分的识别可以是自动的或通过用户选择。 为不希望的部分生成图像掩模。 图像掩码用于在目标的要素数据集的创建中排除不需要的部分。 例如，图像掩模可以覆盖在图像上，并且仅从目标图像的未屏蔽区域提取特征。 或者，可以从图像的所有区域提取特征，以及用于去除从不期望的部分提取的特征的图像掩模。

公开(公告)号：US09152874B2

公开(公告)日：2015-10-06

申请号：US13801601

申请日：2013-03-13

Applicant: QUALCOMM Incorporated

Inventor： Daniel Wagner ,  Youngmin Park ,  Qi Pan

IPC: G06T7/00 ,  G06T19/00 ,  G06T7/20 ,  G06K9/32

CPC classification number: G06K9/3241 ,  G06T7/20 ,  G06T7/74 ,  G06T19/006 ,  G06T2207/10016 ,  G06T2207/20201

Abstract: Various methods, apparatuses and/or articles of manufacture are provided which may be implemented for use by an electronic device to track objects across two or more digital images. For example, an electronic device may generate a plurality of warped patches corresponding to a reference patch of a reference image, and combine two or more warped patches to form a blurred warped patch corresponding to the reference patch with a motion blur effect applied to a digital representation corresponding to a keypoint of an object to be tracked.

Abstract translation: 提供了各种方法，装置和/或制造品，其可以被实现为由电子设备用于跟踪跨越两个或更多个数字图像的物体。 例如，电子设备可以生成与参考图像的参考图像相对应的多个翘曲的斑块，并且组合两个或更多个扭曲的斑块以形成与参考斑块相对应的模糊的弯曲斑块，其中运动模糊效应被应用于数字 对应于要跟踪的对象的关键点的表示。

公开(公告)号：US20140108466A1

公开(公告)日：2014-04-17

申请号：US13793629

申请日：2013-03-11

Applicant: QUALCOMM INCORPORATED

Inventor： Daniel Wagner ,  Slawomir K. Grzechnik ,  Qi Pan

IPC: G06K9/32 ,  G06F17/30

CPC classification number: G06K9/3241 ,  G06F17/30244 ,  G06K9/4671

Abstract: Systems, apparatus and methods to create a database by a device (such as a server) and to use the database by a mobile device for detecting a planar target are presented. The database allows recognition of a planar target by a mobile device from steeper angles with minimum impact on runtime. The database is created from at least one warped view of the planar target. For example, a database may contain keypoints and descriptors from a non-warped view and also from one or more warped views. The database may be pruned by removing keypoints and corresponding descriptors of one image (e.g., a warped image) overlapping with similar or identical keypoints and descriptors of another image (e.g., a non-warped image).

Abstract translation: 呈现了由设备（例如服务器）创建数据库并通过移动设备使用数据库来检测平面目标的系统，设备和方法。 数据库允许移动设备从较陡的角度识别平面目标，对运行时间的影响最小。 数据库是从平面目标的至少一个翘曲视图创建的。 例如，数据库可以包含来自非翘曲视图以及来自一个或多个翘曲视图的关键点和描述符。 可以通过去除与另一图像（例如，非翘曲图像）的类似或相同关键点和描述符重叠的一个图像（例如，翘曲图像）的关键点和对应描述符来修剪数据库。