-
公开(公告)号：US09635246B2
公开(公告)日：2017-04-25
申请号：US14309551
申请日：2014-06-19
Applicant: QUALCOMM Incorporated
Inventor： Nitesh Shroff , Ramin Rezaiifar , Chiachi Sung
CPC classification number: H04N5/23216 , G06T3/4053 , G06T5/00
Abstract: Systems, devices, and methods are described for efficiently super resolving a portion of an image. One embodiment involves capturing, using a camera module of a device, at least one image of a scene, and creating a higher resolution image of a user-selected region of interest. The super resolution of the region of interest may be performed by matching a high resolution grid with a grid that is at the resolution of a device camera, populating the high resolution grid with information from an image from the camera, and then populating the remaining points of the grid that are not yet populated.
-
公开(公告)号：US09338349B2
公开(公告)日：2016-05-10
申请号：US14012534
申请日：2013-08-28
Applicant: QUALCOMM Incorporated
Inventor： Piyush Sharma , Nitesh Shroff , Ramin Rezaiifar , Chiachi Sung
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将其合并成高动态范围（HDR）输出图像的装置和方法。 图像具有相应的HDR权重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中的每个相应像素之间的差异来确定差异图像。
-
3.发明申请公开(公告)号：US20140375865A1
公开(公告)日：2014-12-25
申请号：US14309551
申请日：2014-06-19
Applicant: QUALCOMM Incorporated
Inventor： Nitesh SHROFF , Ramin Rezaiifar , Chiachi Sung
CPC classification number: H04N5/23216 , G06T3/4053 , G06T5/00
Abstract: Systems, devices, and methods are described for efficiently super resolving a portion of an image. One embodiment involves capturing, using a camera module of a device, at least one image of a scene, and creating a higher resolution image of a user-selected region of interest. The super resolution of the region of interest may be performed by matching a high resolution grid with a grid that is at the resolution of a device camera, populating the high resolution grid with information from an image from the camera, and then populating the remaining points of the grid that are not yet populated.
Abstract translation: 描述了用于有效地超分辨图像的一部分的系统，设备和方法。 一个实施例涉及使用设备的相机模块来捕获场景的至少一个图像，以及创建用户选择的感兴趣区域的较高分辨率图像。 感兴趣区域的超分辨率可以通过将高分辨率网格与处于设备相机的分辨率的网格进行匹配来进行，使用来自相机的图像的信息填充高分辨率网格，然后填充剩余点 的网格尚未填充。
-
公开(公告)号：US11205283B2
公开(公告)日：2021-12-21
申请号：US15641510
申请日：2017-07-05
Applicant: QUALCOMM Incorporated
Inventor： Chiachi Sung , Gary Mcgrath , Christopher Brunner
Abstract: Embodiments include devices and methods for automatically calibrating a camera. In various embodiments, an image sensor may capture an image. Locations of one or more points including in the captured image frames may be predicted and detected. Calibration parameters may be calculated based on differences between predicted locations of a selected point within an image frame and observed locations of the selected point within the captured image frame. The automatic camera calibration method may be repeated until the calibration parameters satisfy a calibration quality threshold.
-
公开(公告)号：US10341543B2
公开(公告)日：2019-07-02
申请号：US15269067
申请日：2016-09-19
Applicant: QUALCOMM Incorporated
Inventor： William Mantzel , Ramin Rezaiifar , Chiachi Sung
IPC: G06T3/00 , G06T7/30 , H04N9/04 , H04N1/387 , H04N1/407 , H04N13/25 , H04N5/225 , H04N5/232 , H04N5/235 , H04N5/247 , H04N9/093 , H04N13/133
Abstract: In general, techniques are described that facilitate processing of color image data using both a mono image data and a color image data. A device comprising a monochrome camera, a color camera, and a processor may be configured to perform the techniques. The monochrome camera may capture monochrome image data of a scene. The color camera may capture color image data of the scene. A processor may determine a parallax value indicative of a level of parallax between the monochrome image data and the color image data and determine that the parallax is greater than the parallax threshold. The processor may further combine, in response to the determination that the parallax is greater than the parallax threshold, a luma component of the color image data with a luma component of the monochrome image data to generate a luma component of enhanced color image data.
-
Patent Agency Ranking
公开(公告)号：US20170318273A1
公开(公告)日：2017-11-02
申请号：US15269129
申请日：2016-09-19
Applicant: QUALCOMM Incorporated
Inventor： William Mantzel , Ramin Rezaiifar , Chiachi Sung
CPC classification number: H04N5/2258 , G06T3/0068 , G06T7/30 , G06T2207/20208 , G06T2207/20221 , H04N1/3871 , H04N1/407 , H04N5/2257 , H04N5/23229 , H04N5/2355 , H04N5/247 , H04N9/045 , H04N9/093 , H04N13/133 , H04N13/25
Abstract: In general, techniques are described that facilitate processing of color image data using both a mono image data and a color image data. A device comprising a monochrome camera, a color camera, and a processor may be configured to perform the techniques. The monochrome camera may be configured to capture monochrome image data of a scene. The color camera may be configured to capture color image data of the scene. A processor may be configured to match features of the color image data to features of the monochrome image data, and compute a finite number of shift values based on the matched features of the color image data and the monochrome image data. The processor may further be configured to shift the color image data based on the finite number of shift values to generate enhanced color image data.
-
公开(公告)号：US20170318222A1
公开(公告)日：2017-11-02
申请号：US15268978
申请日：2016-09-19
Applicant: QUALCOMM Incorporated
Inventor： William Mantzel , Ramin Rezaiifar , Chiachi Sung
CPC classification number: H04N5/2258 , G06T3/0068 , G06T7/30 , G06T2207/20208 , G06T2207/20221 , H04N1/3871 , H04N1/407 , H04N5/2257 , H04N5/23229 , H04N5/2355 , H04N5/247 , H04N9/045 , H04N9/093 , H04N13/133 , H04N13/25
Abstract: In general, techniques are described that facilitate processing of color image data using both a mono image data and a color image data. A device comprising a monochrome camera, a color camera and a processor may be configured to perform the techniques. The monochrome camera may be configured to capture monochrome image data of a scene. The color camera may be configured to capture color image data of the scene. The processor may be configured to perform intensity equalization with respect to a luma component of either the color image data or the monochrome image data to correct for differences in intensity between the color camera and the monochrome camera.
-
公开(公告)号：US10362205B2
公开(公告)日：2019-07-23
申请号：US15268978
申请日：2016-09-19
Applicant: QUALCOMM Incorporated
Inventor： William Mantzel , Ramin Rezaiifar , Chiachi Sung
IPC: G06T3/00 , G06T7/30 , H04N9/04 , H04N1/387 , H04N1/407 , H04N13/25 , H04N5/225 , H04N5/232 , H04N5/247 , H04N9/093 , H04N13/133
Abstract: In general, techniques are described that facilitate processing of color image data using both a mono image data and a color image data. A device comprising a monochrome camera, a color camera and a processor may be configured to perform the techniques. The monochrome camera may be configured to capture monochrome image data of a scene. The color camera may be configured to capture color image data of the scene. The processor may be configured to perform intensity equalization with respect to a luma component of either the color image data or the monochrome image data to correct for differences in intensity between the color camera and the monochrome camera.
-
公开(公告)号：US20170318272A1
公开(公告)日：2017-11-02
申请号：US15269067
申请日：2016-09-19
Applicant: QUALCOMM Incorporated
Inventor： William Mantzel , Ramin Rezaiifar , Chiachi Sung
CPC classification number: H04N5/2258 , G06T3/0068 , G06T7/30 , G06T2207/20208 , G06T2207/20221 , H04N1/3871 , H04N1/407 , H04N5/2257 , H04N5/23229 , H04N5/2355 , H04N5/247 , H04N9/045 , H04N9/093 , H04N13/133 , H04N13/25
Abstract: In general, techniques are described that facilitate processing of color image data using both a mono image data and a color image data. A device comprising a monochrome camera, a color camera, and a processor may be configured to perform the techniques. The monochrome camera may capture monochrome image data of a scene. The color camera may capture color image data of the scene. A processor may determine a parallax value indicative of a level of parallax between the monochrome image data and the color image data and determine that the parallax is greater than the parallax threshold. The processor may further combine, in response to the determination that the parallax is greater than the parallax threshold, a luma component of the color image data with a luma component of the monochrome image data to generate a luma component of enhanced color image data.
-
10.发明授权公开(公告)号：US09495762B2
公开(公告)日：2016-11-15
申请号：US14710474
申请日：2015-05-12
Applicant: QUALCOMM Incorporated
Inventor： Nitesh Shroff , Ramin Rezaiifar , Chiachi Sung , Piyush Sharma
CPC classification number: H04N1/6086 , G06K9/00771 , G06K2209/21 , G06T7/246 , G06T2207/10016 , G06T2207/10152 , G06T2207/30196 , G06T2207/30232 , H04N1/3871 , H04N1/407 , H04N1/60 , H04N5/144 , H04N5/145 , H04N5/147 , H04N5/23254 , H04N5/235 , H04N2209/044
Abstract: Techniques disclosed herein involve determining motion occurring in a scene between the capture of two successively-captured images of the scene using intensity gradients of pixels within the images. These techniques can be used alone or with other motion-detection techniques to identify where motion has occurred in the scene, which can be further used to reduce artifacts that may be generated when images are combined.
Abstract translation: 本文公开的技术涉及使用图像内的像素的强度梯度来确定拍摄场景的两个相继拍摄的图像之间在场景中发生的运动。 这些技术可以单独使用或与其他运动检测技术一起使用，以识别场景中发生的运动位置，这可以进一步用于减少当图像组合时可能产生的伪影。
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.017 seconds)
