公开(公告)号：US20170109940A1

公开(公告)日：2017-04-20

申请号：US14883406

申请日：2015-10-14

Applicant: QUALCOMM Incorporated

Inventor： Feng Guo ,  Ning Bi ,  Bijan Forutanpour ,  Tao Zhang ,  Jianfeng Ren

IPC: G06T19/20 ,  G02B27/01 ,  G06T7/20 ,  H04N7/18 ,  G06T19/00 ,  G06T7/00

CPC classification number: G06T19/20 ,  G02B27/0172 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0147 ,  G06T3/00 ,  G06T7/30 ,  G06T19/006 ,  G06T2200/32 ,  G06T2207/10028 ,  G06T2207/20221 ,  H04N7/183

Abstract: A method performed by an electronic device is described. The method includes obtaining a combined image. The combined image includes a combination of images captured from one or more image sensors. The method also includes obtaining depth information. The depth information is based on a distance measurement between a depth sensor and at least one object in the combined image. The method further includes adjusting a combined image visualization based on the depth information.

公开(公告)号：US20170105005A1

公开(公告)日：2017-04-13

申请号：US15131574

申请日：2016-04-18

Applicant: QUALCOMM Incorporated

Inventor： Ying Chen ,  Xuerui Zhang ,  Mayank Tiwari ,  Ning Bi ,  Prasanjit Panda

IPC: H04N19/159 ,  H04N19/169 ,  H04N19/172 ,  H04N19/58 ,  H04N19/105

CPC classification number: H04N19/159 ,  H04N19/105 ,  H04N19/162 ,  H04N19/172 ,  H04N19/176 ,  H04N19/188 ,  H04N19/46 ,  H04N19/58 ,  H04N19/70

Abstract: Techniques and systems are provided for performing predictive random access using a background picture. For example, a method of decoding video data includes obtaining an encoded video bitstream comprising a plurality of pictures. The plurality of pictures include a plurality of predictive random access pictures. A predictive random access picture is at least partially encoded using inter-prediction based on at least one background picture. The method further includes determining, for a time instance of the video bitstream, a predictive random access picture of the plurality of predictive random access pictures with a time stamp closest in time to the time instance. The method further includes determining a background picture associated with the predictive random access picture, and decoding at least a portion of the predictive random access picture using inter-prediction based on the background picture.

公开(公告)号：US09466121B2

公开(公告)日：2016-10-11

申请号：US13651098

申请日：2012-10-12

Applicant: QUALCOMM Incorporated

Inventor： Ruiduo Yang ,  Ning Bi

IPC: H04N13/02 ,  G06T1/00 ,  G06T7/20

CPC classification number: H04N13/204 ,  G06T7/194 ,  G06T7/254 ,  G06T7/50 ,  G06T7/73 ,  G06T19/006 ,  G06T2207/10028

Abstract: In a particular embodiment, a method includes evaluating, at a mobile device, a first area of pixels to generate a first result. The method further includes evaluating, at the mobile device, a second area of pixels to generate a second result. Based on comparing a threshold with a difference between the first result and the second result, a determination is made that the second area of pixels corresponds to a background portion of a scene or a foreground portion of the scene.

Abstract translation: 在特定实施例中，一种方法包括在移动设备处评估第一区域的像素以产生第一结果。 该方法还包括在移动设备处评估第二区域的像素以产生第二结果。 基于将阈值与第一结果与第二结果之间的差进行比较，确定第二区域像素对应于场景的背景部分或场景的前景部分。

公开(公告)号：US20160210525A1

公开(公告)日：2016-07-21

申请号：US14598892

申请日：2015-01-16

Applicant: QUALCOMM INCORPORATED

Inventor： Ruiduo Yang ,  Ning Bi ,  Sichao Yang ,  Xinzhou Wu ,  Feng Guo ,  Jianfeng Ren

IPC: G06K9/20 ,  G06K9/00

CPC classification number: G06K9/2054 ,  G06K9/00369 ,  G06K9/0063 ,  G06K9/00791 ,  G06K9/00805 ,  G06K9/3233 ,  G06K9/42 ,  G06K9/6857

Abstract: An apparatus includes an object detector configured to receive image data of a scene viewed from the apparatus and including an object. The image data is associated with multiple scale space representations of the scene. The object detector is configured to detect the object responsive to location data and a first scale space representation of the multiple scale space representations.

Abstract translation: 一种装置，包括物体检测器，被配置为接收从该装置观看并包括物体的场景的图像数据。 图像数据与场景的多个尺度空间表示相关联。 对象检测器被配置为响应于位置数据和多尺度空间表示的第一尺度空间表示来检测对象。

公开(公告)号：US20160063705A1

公开(公告)日：2016-03-03

申请号：US14811489

申请日：2015-07-28

Applicant: QUALCOMM Incorporated

Inventor： Lei Xu ,  Yunke Pan ,  Shuxue Quan ,  Yingen Xiong ,  Ning Bi

IPC: G06T7/00 ,  H04N5/232 ,  G06T5/50 ,  G06T7/20

CPC classification number: G06T7/33 ,  G06T3/4038 ,  G06T5/50 ,  G06T7/181 ,  G06T2200/32 ,  G06T2207/10016 ,  G06T2207/10024 ,  H04N5/23238 ,  H04N5/2624

Abstract: A method performed by an electronic device is described. The method includes determining overlapping areas from neighboring images. The method also includes determining a difference measure between the overlapping areas. The method further includes determining a constraint measure corresponding to at least one of the overlapping areas. The method additionally includes determining a seam based on a combination of the difference measure and the constraint measure.

Abstract translation: 描述由电子设备执行的方法。 该方法包括确定相邻图像的重叠区域。 该方法还包括确定重叠区域之间的差异度量。 该方法还包括确定对应于重叠区域中的至少一个的约束测量。 该方法还包括基于差异度量和约束测量的组合确定接缝。

公开(公告)号：US20160011769A1

公开(公告)日：2016-01-14

申请号：US14764149

申请日：2013-02-23

Applicant: QUALCOMM INCORPORATED

Inventor： Xuan Zou ,  Fan Ling ,  Ning Bi ,  Lei Zhang

IPC: G06F3/0488 ,  G06T11/60 ,  G06F3/0484 ,  G06T17/20

CPC classification number: G06F3/04883 ,  G06F3/04845 ,  G06F2203/04808 ,  G06T11/00 ,  G06T11/60 ,  G06T17/20

Abstract: A method for interactive image caricaturing by an electronic device is described. The method includes detecting at least one feature location of an image. The method further includes generating, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line. The method additionally includes obtaining a gesture input. The method also includes determining at least one caricature action based on the at least one gesture input. The method further includes generating a caricature image based on the image mesh, the at least one caricature action and the image.

Abstract translation: 描述了一种通过电子设备进行交互式图像变形的方法。 该方法包括检测图像的至少一个特征位置。 该方法还包括基于至少一个特征位置生成包括至少一条水平线和至少一条垂直线的网格的图像网格。 该方法还包括获得手势输入。 该方法还包括基于至少一个手势输入来确定至少一个漫画动作。 该方法还包括基于图像网格，至少一个漫画动作和图像生成漫画图像。

公开(公告)号：US20140050372A1

公开(公告)日：2014-02-20

申请号：US13744906

申请日：2013-01-18

Applicant: QUALCOMM INCORPORATED

Inventor： Yingyong Qi ,  Ning Bi ,  Feng Guo

IPC: G06K9/00

CPC classification number: G06K9/00221 ,  G06K9/00288 ,  G06K9/6232 ,  G06K9/6255 ,  G06K2009/4666

Abstract: Apparatus and methods for facial detection are disclosed. A plurality of images of an observed face is received for identification. Based at least on two or more selected images of the plurality of images, a template of the observed face is generated. In some embodiments, the template is a subspace generated based on feature vectors of the plurality of received images. A database of identities and corresponding facial data of known persons is searched based at least on the template of the observed face and the facial data of the known persons. One or more identities of the known persons are selected based at least on the search.

Abstract translation: 公开了用于面部检测的装置和方法。 接收观察面的多张图像进行识别。 至少基于多个图像中的两个或更多个所选择的图像，生成观察到的面部的模板。 在一些实施例中，模板是基于多个接收图像的特征向量生成的子空间。 至少基于所观察到的面部的模板和已知人的面部数据来搜索已知人的身份和对应面部数据的数据库。 至少基于搜索来选择已知人的一个或多个身份。

公开(公告)号：US20140029807A1

公开(公告)日：2014-01-30

申请号：US14045158

申请日：2013-10-03

Applicant: QUALCOMM Incorporated

Inventor： Yingyong Qi ,  Ning Bi ,  Xuerui Zhang

IPC: G06T7/20

CPC classification number: G06K9/00536 ,  G06T7/20 ,  G06T2207/20012

Abstract: Embodiments include methods and systems for context-adaptive pixel processing based, in part, on a respective weighting-value for each pixel or a group of pixels. The weighting-values provide an indication as to which pixels are more pertinent to pixel processing computations. Computational resources and effort can be focused on pixels with higher weights, which are generally more pertinent for certain pixel processing determinations.

公开(公告)号：US11636694B2

公开(公告)日：2023-04-25

申请号：US17185800

申请日：2021-02-25

Applicant: QUALCOMM Incorporated

Inventor： Xin Li ,  Chun-Ting Huang ,  Lei Wang ,  Ning Bi

IPC: G06K9/62 ,  G06V20/59 ,  G06V20/40 ,  G06F18/214 ,  G06F18/20

Abstract: Systems and techniques are provided for performing video-based activity recognition. For example, a process can include extracting, using a first machine learning model, first one or more features from a first frame and second one or more features from a second frame. The first one or more features and the second one or more features are associated with a person driving a vehicle. The process can include processing, using a second machine learning model, the first one or more features and the second one or more features. The process can include determining, based on processing of the first one or more features and the second one or more features using the second machine learning model, at least one activity associated with the person driving the vehicle.

公开(公告)号：US11526272B2

公开(公告)日：2022-12-13

申请号：US16986238

申请日：2020-08-05

Applicant: QUALCOMM Incorporated

Inventor： Xuan Zou ,  Fan Ling ,  Ning Bi ,  Lei Zhang

IPC: G06K9/00 ,  G06F3/04883 ,  G06T11/00 ,  G06F3/04845 ,  G06T11/60 ,  G06T17/20

Abstract: A method for interactive image caricaturing by an electronic device is described. The method includes detecting at least one feature location of an image. The method further includes generating, based on the at least one feature location, an image mesh that comprises a grid of at least one horizontal line and at least one vertical line. The method additionally includes obtaining a gesture input. The method also includes determining at least one caricature action based on the at least one gesture input. The method further includes generating a caricature image based on the image mesh, the at least one caricature action and the image.