-
公开(公告)号：US20240242358A1
公开(公告)日：2024-07-18
申请号：US18563254
申请日：2021-07-07
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Wei-Chih LIU , Mian LI , Ruocheng JIANG
CPC classification number: G06T7/20 , G06V10/25 , H04N23/6812 , H04N23/682
Abstract: Techniques and systems are provided for improving one or more image capture operations. In some examples, a system determines, based on data from one or more sensors, a movement of an image capture device associated with a capture of a plurality of image frames. The systems adjust a position of at least one object in each of the plurality of image frames based on the movement of the image capture device. The system determines a motion of the at least one object based on a difference in the adjusted position among the plurality of image frames. The system selects a value for at least one image capture parameter associated with the plurality of image frames based on the motion of the at least one object.
-
公开(公告)号：US20230342889A1
公开(公告)日：2023-10-26
申请号：US17729561
申请日：2022-04-26
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Hsuan-Ying LIAO , Hsin Yueh CHANG , Yu-Ren LAI , Shizhong LIU , Weiliang LIU
CPC classification number: G06T5/003 , G06T5/50 , G06T7/337 , G06T3/0093 , G06T2207/20021 , G06T2207/20208 , G06T2207/20192 , G06T2207/20221
Abstract: Systems, methods, and non-transitory media are provided for frequency domain edge enhancement of multi-exposure high dynamic range (HDR) images. An example method can include determining an alignment between an HDR frame and a frame having an exposure time above a threshold; adjusting the frame based on the alignment; determining a gradient estimation map representing differences between image blocks in the HDR frame and image blocks in the frame; and generating, based on the gradient estimation map, a merged frame that includes a combination of at least some image data from the HDR frame and at least some image data from the frame.
-
公开(公告)号：US20250097589A1
公开(公告)日：2025-03-20
申请号：US18729679
申请日：2022-03-24
Applicant: QUALCOMM Incorporated
Inventor： Po-Chi HO , Wei-Te CHANG , Lei LI , Yawen CHI , Wei-Chih LIU , Wen-Chun FENG
IPC: H04N23/741 , H04N23/67 , H04N23/73 , H04N23/76
Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media for processing image data. One illustrative method of processing image data includes: capturing a first image of a subject using a variable aperture lens configured with a first aperture and a first exposure value; capturing a second image of the subject using the variable aperture lens configured with a second aperture and a second exposure value, wherein the second aperture is smaller than the first aperture and the second exposure value is smaller than the first exposure value; and generating a high dynamic range (HDR) image at least in part by fusing the first image and the second image fusing the first image and the second image.
-
公开(公告)号：US20230319401A1
公开(公告)日：2023-10-05
申请号：US17710774
申请日：2022-03-31
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Su-Chin CHIU , Yu-Ren LAI , Hang-Wei LIAW , Jian-Jia SU
CPC classification number: H04N5/23212 , G06T7/50 , G06T5/50 , G06T7/20 , G06T5/003 , G06T2207/20081 , G06T2207/30201
Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media to capture images with subjects at different depths of fields. A method of processing image data includes determining, based on a depth map of a previously captured image, a first distance to a first object and a second distance to a second object; identifying a focal point of a camera lens at least in part using the first distance and the second distance; capturing an image using the focal point as a basis for the capture, the image including a first region corresponding to the first object and a second region corresponding to the second object; and generating a second image from the image at least in part by enhancing at least one of the first region or the second region using a point spread function (PSF).
-
公开(公告)号：US20230156301A1
公开(公告)日：2023-05-18
申请号：US17627261
申请日：2019-11-06
Applicant: QUALCOMM INCORPORATED
Inventor： Wen-Chun FENG , Mian LI
CPC classification number: H04N23/45 , H04N23/69 , H04N23/673
Abstract: Aspects of the present disclosure relate to systems and methods for image focusing for devices including multiple cameras. An example method includes estimating a focus distance associated with an image captured by a first camera, determining, based at least in part on the estimated focus distance, to switch from the first camera to a second camera, switching from the first camera to the second camera, completing a focusing operation using the second camera and presenting an updated image captured by the second camera.
-
Patent Agency Ranking
公开(公告)号：US20230021016A1
公开(公告)日：2023-01-19
申请号：US17647558
申请日：2022-01-10
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Hui Shan KAO , Jian-Jia SU
Abstract: Systems and techniques described herein relate to techniques for improving image detection. In some examples, aspects relate to systems and techniques for improving image detection by performing tracking of objects within captured image frames. A process can include obtaining, from an image capture device, a first image frame including an object. The process can further include determining, using an object detector, an object validation score associated with detection of the object in the first image frame, and determining the object validation score is less than a validation threshold. Based on the object validation score being less than the validation threshold, the process can include tracking the object for one or more image frames received subsequent to the first image frame.
-
公开(公告)号：US20210390747A1
公开(公告)日：2021-12-16
申请号：US17343640
申请日：2021-06-09
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Yu-Chen HSU , Yu-Ren LAI
Abstract: Techniques and systems are provided for processing image data. A first image having a first resolution can be obtained. In some aspects, the first image is generated based on a pixel binning process. A second image can be obtained having a second resolution that is greater than the first resolution. In some aspects, the second image is generated based on a remosaicing process. One or more weight maps can be generated based on characteristics determined based on pixels of the first image, pixels of the second image, or pixels of both the first image and the second image. A fused image can be generated based on the one or more weight maps that includes a first set of pixels from the first image and a second set of pixels from the second image.
-
公开(公告)号：US20250097575A1
公开(公告)日：2025-03-20
申请号：US18729665
申请日：2022-03-24
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Hsuan-Ming LIU , Mian LI
IPC: H04N23/67 , H04N25/704
Abstract: Imaging systems and techniques are described. An imaging system receives image data captured by an image sensor according to one or more image capture settings, for instance according to an aperture size, temperature, lux, lens position, and/or region of interest. The image data includes image pixel data and focus pixel data. The imaging system determines a first focus setting based on phase detection using the focus pixel data. The imaging system determines a focus offset based on use of the one or more image capture settings as inputs to a trained model (e.g., decision tree, random forest, neural network). The imaging system determines a second focus setting at least in part by adjusting the first focus setting according to the focus offset, and causes a focus control mechanism to set a focus parameter to the second focus setting.
-
公开(公告)号：US20240249423A1
公开(公告)日：2024-07-25
申请号：US18561271
申请日：2021-07-07
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Mian LI , Hui Shan KAO
Abstract: Systems and techniques are provided for processing one or more images. For instance, aspects include a process that can include determining a first region of interest corresponding to a first object depicted in an image obtained using at least one camera. The first region of interest is associated with at least one element of a multi-point grid associated with a multi-point depth sensing system. The process can include determining a first extended region of interest for the first object. The first extended region of interest is associated with a plurality of elements including the at least one element and one or more additional elements of the multi-point grid. The process can further include, based on the plurality of elements associated with the first extended region of interest, determining representative depth information representing a first distance between the at least one camera and the first object depicted in the image.
-
公开(公告)号：US20240144717A1
公开(公告)日：2024-05-02
申请号：US18049897
申请日：2022-10-26
Applicant: QUALCOMM Incorporated
Inventor： Wen-Chun FENG , Kai LIU , Su-Chin CHIU , Chung-Yan CHIH , Yu-Ren LAI
CPC classification number: G06V40/165 , G06T3/40 , G06V10/245 , G06V10/25 , G06V40/166
Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media to capture images. A method of processing image data includes determining a first region of interest (ROI) in an image. The first ROI is associated with a first object. The method can include determining one or more image characteristics of the first ROI. The method can further include determining whether to perform an upsampling process on image data in the first ROI based on the one or more image characteristics of the first ROI.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.015 seconds)
