公开(公告)号：US20180040133A1

公开(公告)日：2018-02-08

申请号：US15231370

申请日：2016-08-08

Applicant: QUALCOMM Incorporated

Inventor： Sujith Srinivasan ,  Gokce Dane

IPC: G06T7/20

CPC classification number: H04N19/56 ,  G06T7/246 ,  G06T2207/10004 ,  H04N19/43 ,  H04N19/533 ,  H04N19/54

Abstract: A method performed by an electronic device is described. The method includes obtaining a motion vector map based on at least two images. The motion vector map has fewer motion vectors than a number of pixels in each of the at least two images. The method also includes obtaining a feature point from one of the at least two images. The method further includes performing a matching operation between a template associated with the feature point and at least one search space based on the motion vector map. The method additionally includes determining a motion vector corresponding to the feature point based on the matching operation.

公开(公告)号：US10284875B2

公开(公告)日：2019-05-07

申请号：US15231370

申请日：2016-08-08

Applicant: QUALCOMM Incorporated

Inventor： Sujith Srinivasan ,  Gokce Dane

IPC: H04N19/56 ,  H04N19/43 ,  H04N19/533 ,  H04N19/54 ,  G06T7/246

Abstract: A method performed by an electronic device is described. The method includes obtaining a motion vector map based on at least two images. The motion vector map has fewer motion vectors than a number of pixels in each of the at least two images. The method also includes obtaining a feature point from one of the at least two images. The method further includes performing a matching operation between a template associated with the feature point and at least one search space based on the motion vector map. The method additionally includes determining a motion vector corresponding to the feature point based on the matching operation.

公开(公告)号：US20140192266A1

公开(公告)日：2014-07-10

申请号：US13734667

申请日：2013-01-04

Applicant: Qualcomm Incorporated

Inventor： Mainak Biswas ,  Vasudev Bhaskaran ,  Sujith Srinivasan

IPC: H04N5/21

CPC classification number: H04N5/21 ,  H04N19/117 ,  H04N19/14 ,  H04N19/176 ,  H04N19/86 ,  H04N19/865

Abstract: Method and apparatus for reducing random noise in digital video streams are described. In one innovative aspect, a device for reducing noise of a video stream is provided. The device includes a ringing noise detector configured to identify ringing noise in an image included in the video stream. The device further includes a block detector configured to identify a block pattern in the image included in the video stream, the block detector configured to identify block patterns of a predetermined size and block patterns of an arbitrary size. The device also includes a noise reducer configured to filter the image based on the identified ringing noise and the block pattern.

Abstract translation: 描述了用于减少数字视频流中随机噪声的方法和装置。 在一个创新的方面，提供了用于降低视频流的噪声的设备。 该装置包括配置成识别包含在视频流中的图像中的振铃噪声的振铃噪声检测器。 该装置还包括块检测器，其被配置为识别包括在视频流中的图像中的块图案，块检测器被配置为识别预定大小的块图案和任意大小的块图案。 该装置还包括被配置为基于所识别的振铃噪声和块图案来对图像进行滤波的降噪器。

公开(公告)号：US20180122079A1

公开(公告)日：2018-05-03

申请号：US15336558

申请日：2016-10-27

Applicant: QUALCOMM Incorporated

Inventor： Sujith Srinivasan

IPC: G06T7/00 ,  G06K9/34

CPC classification number: G06T7/11 ,  G06K9/00973 ,  G06K9/4642

Abstract: A method for determining a histogram is described. The method includes storing a plurality of histograms in a memory bank, each histogram corresponding to a group of pixels in a region of interest of an image. The method also includes initiating transfer of one or more histograms between the memory bank and a local memory. The method further includes finding, for an incoming pixel, weights of each bin for the one or more histograms stored in the local memory. The method additionally includes adding the weights to the one or more histograms stored in the local memory. The method also includes transferring one or more updated histograms from the local memory to the memory bank. The method further includes replacing a corresponding one or more histograms in the memory bank with the one or more updated histograms.

公开(公告)号：US09374506B2

公开(公告)日：2016-06-21

申请号：US13734595

申请日：2013-01-04

Applicant: Qualcomm Incorporated

Inventor： Mainak Biswas ,  Vasudev Bhaskaran ,  Sujith Srinivasan ,  Shilpi Sahu

IPC: H04N5/14 ,  G06T5/00 ,  G06T5/20 ,  G06T5/50 ,  G06T7/20

CPC classification number: H04N5/144 ,  G06T5/002 ,  G06T5/20 ,  G06T5/50 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20012 ,  G06T2207/20182 ,  G06T2207/20192 ,  G06T2207/20221 ,  G06T2207/20224

Abstract: Method and apparatus for reducing random noise in digital video streams are described. In one innovative aspect, the device includes a noise estimator. The device also includes a motion detector configured to determine a motion value indicative of motion between two frames of the video stream, the motion value based at least in part on the noise value. The device further includes a spatial noise reducer configured to filter the image data based at least in part on a blending factor and the noise value. The device also includes a temporal noise reducer configured to filter the video data based on the motion value and the noise value. The device also includes a blender configured to blend the spatial and temporal filtered values to provide a weighted composite filtered output image.

Abstract translation: 描述了用于减少数字视频流中随机噪声的方法和装置。 在一个创新方面，该装置包括噪声估计器。 该装置还包括运动检测器，其被配置为至少部分地基于噪声值来确定指示视频流的两个帧之间的运动的运动值，运动值。 该装置还包括空间噪声减少器，其被配置为至少部分地基于混合因子和噪声值来对图像数据进行滤波。 该装置还包括：时间噪声降低器，被配置为基于运动值和噪声值对视频数据进行滤波。 该装置还包括配置成混合空间和时间滤波值以提供加权复合滤波输出图像的混合器。

公开(公告)号：US20140192267A1

公开(公告)日：2014-07-10

申请号：US13734595

申请日：2013-01-04

Applicant: QUALCOMM INCORPORATED

Inventor： Mainak Biswas ,  Vasudev Bhaskaran ,  Sujith Srinivasan ,  Shilpi Sahu

IPC: H04N5/14

CPC classification number: H04N5/144 ,  G06T5/002 ,  G06T5/20 ,  G06T5/50 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20012 ,  G06T2207/20182 ,  G06T2207/20192 ,  G06T2207/20221 ,  G06T2207/20224

Abstract: Method and apparatus for reducing random noise in digital video streams are described. In one innovative aspect, the device includes a noise estimator. The device also includes a motion detector configured to determine a motion value indicative of motion between two frames of the video stream, the motion value based at least in part on the noise value. The device further includes a spatial noise reducer configured to filter the image data based at least in part on a blending factor and the noise value. The device also includes a temporal noise reducer configured to filter the video data based on the motion value and the noise value. The device also includes a blender configured to blend the spatial and temporal filtered values to provide a weighted composite filtered output image.

Abstract translation: 描述了用于减少数字视频流中随机噪声的方法和装置。 在一个创新方面，该装置包括噪声估计器。 该装置还包括运动检测器，其被配置为至少部分地基于噪声值来确定指示视频流的两个帧之间的运动的运动值，运动值。 该装置还包括空间噪声减少器，其被配置为至少部分地基于混合因子和噪声值来对图像数据进行滤波。 该装置还包括：时间噪声降低器，被配置为基于运动值和噪声值对视频数据进行滤波。 该装置还包括配置成混合空间和时间滤波值以提供加权复合滤波输出图像的混合器。

公开(公告)号：US20190266429A1

公开(公告)日：2019-08-29

申请号：US15903981

申请日：2018-02-23

Applicant: QUALCOMM Incorporated

Inventor： Sujith Srinivasan ,  Rakesh Nattoji Rajaram ,  Gokce Dane ,  Vasudev Bhaskaran

IPC: G06K9/32 ,  G06K9/62 ,  G06K9/46

Abstract: A classifier for detecting objects in images can be configured to receive features of an image from a feature extractor. The classifier can determine a feature window based on the received features, and allows access by each decision tree of the classifier to only a predetermined area of the feature window. Each decision tree of the classifier can compare a corresponding predetermined area of the feature window with one or more thresholds. The classifier can determine an object in the image based on the comparisons. In some examples, the classifier can determine objects in a feature window based on received features, where the received features are based on color information for an image.

公开(公告)号：US09165210B1

公开(公告)日：2015-10-20

申请号：US14288267

申请日：2014-05-27

Applicant: QUALCOMM Incorporated

Inventor： Sujith Srinivasan ,  Mainak Biswas

IPC: G06K9/46 ,  G06T5/40

CPC classification number: G06K9/4642 ,  G06K9/4661 ,  G06T5/008 ,  G06T5/40

Abstract: Systems and methods for improving the contrast of image frames are disclosed. In one embodiment, a system for improving the contrast of image frames includes a control module configured to create an intensity histogram for an image frame, define a set of markers on an intensity range of the histogram, assign a blend factor to each marker, calculate a blend factor for each original pixel of the image, obtain a first equalized pixel output value, calculate a final equalized pixel output value using the blend factor, the first equalized pixel output value, and an original pixel value, and output new pixel values that constitute the output image.

Abstract translation: 公开了用于改善图像帧的对比度的系统和方法。 在一个实施例中，用于改善图像帧的对比度的系统包括：控制模块，被配置为创建图像帧的强度直方图，在直方图的强度范围上定义一组标记，为每个标记分配混合因子，计算 对于图像的每个原始像素的混合因子，获得第一均衡像素输出值，使用混合因子，第一均衡像素输出值和原始像素值计算最终均衡像素输出值，并输出新像素值， 构成输出图像。