公开(公告)号：EP2776900B1

公开(公告)日：2019-09-04

申请号：EP12787227.3

申请日：2012-10-19

Applicant: Qualcomm Incorporated

Inventor： SHARMA, Piyush ,  SWAMINATHAN, Ashwin ,  BRUNNER, Christopher ,  CHARI, Murali R.

IPC: G06F1/3293 ,  G06F9/54 ,  H04W52/02 ,  H04L29/08

公开(公告)号：EP2987134A1

公开(公告)日：2016-02-24

申请号：EP14722904.1

申请日：2014-03-20

Applicant: Qualcomm Incorporated

Inventor： SHARMA, Piyush ,  SHROFF, Nitesh ,  REZAIIFAR, Ramin ,  SUNG, Chiachi

IPC: G06T5/50

CPC classification number: H04N5/23229 ,  G06T5/007 ,  G06T5/50 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20212 ,  H04N5/23238 ,  H04N5/2355

Abstract: Apparatuses and methods for reading a set of images to merge together into a high dynamic range (HDR) output image are described. Images have a respective HDR weight and a respective ghost-free weight. Images are merged together using the weighted average of the set of input images using the ghost-free weight. A difference image is determined based on a difference between each pixel within a HDR output image and each respective pixel within a reference image used to create the HDR output image.

Abstract translation: 描述用于读取一组图像以合并在一起成为高动态范围（HDR）输出图像的装置和方法。 图像具有相应的HDR重量和相应的无重影重量。 使用无重影重量的输入图像集合的加权平均值将图像合并在一起。 基于HDR输出图像内的每个像素与用于创建HDR输出图像的参考图像内的各个像素之间的差异来确定差异图像。

公开(公告)号：EP2987135B1

公开(公告)日：2019-10-30

申请号：EP14724224.2

申请日：2014-03-20

Applicant: Qualcomm Incorporated

Inventor： SHARMA, Piyush ,  SHROFF, Nitesh ,  REZAIIFAR, Ramin

IPC: G06T5/50 ,  H04N5/232 ,  H04N5/235

公开(公告)号：EP2619728B1

公开(公告)日：2019-07-17

申请号：EP11767336.8

申请日：2011-09-19

Applicant: Qualcomm Incorporated

Inventor： SWAMINATHAN, Ashwin ,  SHARMA, Piyush ,  JIANG, Bolan ,  CHARI, Murali, R. ,  SPINDOLA, Serafin, Diaz ,  BAHETI, Pawan, Kumar ,  NARAYANAN, Vidya

IPC: G06T7/73 ,  G06T7/246 ,  G06K9/00

公开(公告)号：EP2987134B1

公开(公告)日：2019-10-02

申请号：EP14722904.1

申请日：2014-03-20

Applicant: Qualcomm Incorporated

Inventor： SHARMA, Piyush ,  SHROFF, Nitesh ,  REZAIIFAR, Ramin ,  SUNG, Chiachi

IPC: G06T5/50 ,  H04N5/232 ,  H04N5/235

公开(公告)号：EP3039857A1

公开(公告)日：2016-07-06

申请号：EP14767209.1

申请日：2014-08-29

Applicant: Qualcomm Incorporated

Inventor： SHROFF, Nitesh ,  REZAIIFAR, Ramin ,  SHARMA, Piyush

IPC: H04N5/232 ,  H04N5/222 ,  G06T7/00

CPC classification number: H04N5/23212 ,  G06T5/003 ,  G06T7/571 ,  G06T2200/21 ,  G06T2207/10028 ,  H04N5/2226

Abstract: Techniques are described for generating an all-in focus image with a capability to refocus. One example includes obtaining a first depth map associated with a plurality of captured images of a scene. The plurality of captured images may include images having different focal lengths. The method further includes obtaining a second depth map associated with the plurality of captured images, generating a composite image showing different portions of the scene in focus (based on the plurality of captured images and the first depth map), and generating a refocused image showing a selected portion of the scene in focus (based on the composite image and the second depth map).

Abstract translation: 描述了用于产生具有重新聚焦能力的全焦点图像的技术。 一个示例包括获得与场景的多个捕获图像相关联的第一深度图。 多个拍摄图像可以包括具有不同焦距的图像。 该方法还包括获得与多个拍摄图像相关联的第二深度图，生成示出焦点中的场景的不同部分（基于多个拍摄图像和第一深度图）的合成图像，以及生成重新聚焦图像，其示出 对焦的场景的选定部分（基于合成图像和第二深度图）。

公开(公告)号：EP2987135A2

公开(公告)日：2016-02-24

申请号：EP14724224.2

申请日：2014-03-20

Applicant: Qualcomm Incorporated

Inventor： SHARMA, Piyush ,  SHROFF, Nitesh ,  REZAIIFAR, Ramin

IPC: G06T5/50

Abstract: Exemplary methods, apparatuses, and systems for image processing are described. One or more reference images are selected based on image quality scores. At least a portion of each reference image is merged to create an output image. An output image with motion artifacts is compared to a target to correct the motion artifacts of the output image.

Abstract translation: 描述用于读取一组图像以合并在一起成为高动态范围（HDR）输出图像的装置和方法。 图像具有相应的HDR重量和相应的无重影重量。 使用无重影重量的输入图像集合的加权平均值将图像合并在一起。 基于HDR输出图像内的每个像素与用于创建HDR输出图像的参考图像内的各个像素之间的差异来确定差异图像。

公开(公告)号：EP2941756A1

公开(公告)日：2015-11-11

申请号：EP13815262.4

申请日：2013-12-06

Applicant: QUALCOMM INCORPORATED

Inventor： SHARMA, Piyush ,  REZAIIFAR, Ramin

IPC: G06T7/00 ,  G06F3/01 ,  G06T19/00

CPC classification number: G06T19/006 ,  G06F3/017 ,  G06T7/74 ,  G06T2207/20224 ,  G06T2207/30196

Abstract: A mobile device detects a moveable foreground object in captured images, e.g., a series of video frames without depth information. The object may be one or more of the user's fingers. The object may be detected by warping one of a captured image of a scene that includes the object and a reference image of the scene without the object so they have the same view and comparing the captured image and the reference image after warping. A mask may be used to segment the object from the captured image. Pixels are detected in the extracted image of the object and the pixels are used to detect the point of interest on the foreground object. The object may then be tracked in subsequent images. Augmentations may be rendered and interacted with or temporal gestures may be detected and desired actions performed accordingly.

Abstract translation: 移动设备在捕获的图像中检测可移动的前景对象，例如，没有深度信息的一系列视频帧。 该对象可以是用户的一个或多个手指。 可以通过对包含对象的场景的拍摄图像和没有对象的场景的参考图像进行翘曲来检测对象，从而它们具有相同的视图，并且在整经之后比较所捕获的图像和参考图像。 可以使用掩码来从捕获的图像中分割对象。 在提取的对象图像中检测像素，并且使用像素来检测前景对象上的兴趣点。 然后可以在后续图像中跟踪对象。 增强可以被渲染并且与之进行交互，或者可以检测到时间手势并相应地执行期望的动作。

公开(公告)号：EP2710554A1

公开(公告)日：2014-03-26

申请号：EP12720756.1

申请日：2012-05-03

Applicant: Qualcomm Incorporated

Inventor： SHARMA, Piyush ,  SWAMINATHAN, Ashwin ,  REZAIIFAR, Ramin ,  XUE, Qi

IPC: G06T7/00 ,  G06K9/00

Abstract: A three-dimensional pose of the head of a subject is determined based on depth data captured in multiple images. The multiple images of the head are captured, e.g., by an RGBD camera. A rotation matrix and translation vector of the pose of the head relative to a reference pose is determined using the depth data. For example, arbitrary feature points on the head may be extracted in each of the multiple images and provided along with corresponding depth data to an Extended Kalman filter with states including a rotation matrix and a translation vector associated with the reference pose for the head and a current orientation and a current position. The three-dimensional pose of the head with respect to the reference pose is then determined based on the rotation matrix and the translation vector.

Abstract translation: 基于在多个图像中捕获的深度数据来确定对象的头部的三维姿势。 例如，通过RGBD照相机捕捉头部的多个图像。 使用深度数据确定头部姿态相对于参考姿态的旋转矩阵和平移向量。 例如，可以在多个图像中的每个图像中提取头部上的任意特征点，并将其与对应的深度数据一起提供给扩展卡尔曼滤波器，其中扩展卡尔曼滤波器的状态包括旋转矩阵和与用于头部的参考姿势相关联的平移矢量， 当前方向和当前位置。 然后基于旋转矩阵和平移矢量确定头部相对于参考姿势的三维姿态。

公开(公告)号：EP2619728A1

公开(公告)日：2013-07-31

申请号：EP11767336.8

申请日：2011-09-19

Applicant: Qualcomm Incorporated

Inventor： SWAMINATHAN, Ashwin ,  SHARMA, Piyush ,  JIANG, Bolan ,  CHARI, Murali, R. ,  SPINDOLA, Serafin, Diaz ,  BAHETI, Pawan, Kumar ,  NARAYANAN, Vidya

IPC: G06T7/00 ,  G06T7/20

CPC classification number: G06T7/246 ,  G06K9/00671 ,  G06T7/73 ,  G06T2207/10004

Abstract: A mobile platform efficiently processes sensor data, including image data, using distributed processing in which latency sensitive operations are performed on the mobile platform, while latency insensitive, but computationally intensive operations are performed on a remote server. The mobile platform acquires sensor data, such as image data, and determines whether there is a trigger event to transmit the sensor data to the server. The trigger event may be a change in the sensor data relative to previously acquired sensor data, e.g., a scene change in an image. When a change is present, the sensor data may be transmitted to the server for processing. The server processes the sensor data and returns information related to the sensor data, such as identification of an object in an image or a reference image or model. The mobile platform may then perform reference based tracking using the identified object or reference image or model.

Abstract translation: 移动平台使用分布式处理有效地处理传感器数据，包括图像数据，其中在移动平台上执行延迟敏感操作，而延迟不敏感，但在远程服务器上执行计算密集型操作。 移动平台获取诸如图像数据的传感器数据，并且确定是否存在将传感器数据传送到服务器的触发事件。 触发事件可以是传感器数据相对于先前获取的传感器数据的变化，例如图像中的场景变化。 当存在变化时，传感器数据可以被发送到服务器进行处理。 服务器处理传感器数据并返回与传感器数据相关的信息，例如图像或参考图像或模型中对象的识别。 然后，移动平台可以使用所识别的对象或参考图像或模型来执行基于参考的跟踪。