Patents by Inventor Yu-Ren Lai
Yu-Ren Lai has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240144717Abstract: 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.Type: ApplicationFiled: October 26, 2022Publication date: May 2, 2024Inventors: Wen-Chun FENG, Kai LIU, Su-Chin CHIU, Chung-Yan CHIH, Yu-Ren LAI
-
Patent number: 11863881Abstract: The present disclosure provides systems, apparatus, methods, and computer-readable media that support multi-frame depth-of-field (MF-DOF) for deblurring background regions of interest (ROIs), such as background faces, that may be blurred due to a large aperture size or other characteristics of the camera used to capture the image frame. The processing may include the use of two image frames obtained at two different focus points corresponding to the multiple ROIs in the image frame. The corrected image frame may be determined by deblurring one or more ROIs of the first image frame using an AI-based model and/or local gradient information. The MF-DOF may allow selectively increasing a depth-of-field (DOF) of an image to provide focused capture of multiple regions of interest, without causing a reduction in aperture (and subsequently an amount of light available for photography) or background blur that may be desired for photography.Type: GrantFiled: December 22, 2021Date of Patent: January 2, 2024Assignee: QUALCOMM IncorporatedInventors: Wen-Chun Feng, Yu-Ren Lai, Hsin Yueh Chang
-
Publication number: 20230342889Abstract: 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.Type: ApplicationFiled: April 26, 2022Publication date: October 26, 2023Inventors: Wen-Chun FENG, Hsuan-Ying LIAO, Hsin Yueh CHANG, Yu-Ren LAI, Shizhong LIU, Weiliang LIU
-
Patent number: 11792505Abstract: Systems and techniques are provided for processing image data. According to some aspects, a process can include obtaining a frame captured using an image sensor of a device. The process can include detecting an orientation of the device using a position sensor. The process can further include determining, based on the orientation, a transform to be applied to a region of interest in the frame. The process can include applying the transform to the region of interest. The process can further include providing the transformed region of interest to the object detection algorithm.Type: GrantFiled: February 2, 2022Date of Patent: October 17, 2023Assignee: QUALCOMM IncorporatedInventors: Wen-Chun Feng, Yu-Ren Lai, Hsin Yueh Chang
-
Publication number: 20230319401Abstract: 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).Type: ApplicationFiled: March 31, 2022Publication date: October 5, 2023Inventors: Wen-Chun FENG, Su-Chin CHIU, Yu-Ren LAI, Hang-Wei LIAW, Jian-Jia SU
-
Patent number: 11756221Abstract: Image processing performed on images captured with image capture devices may be used to improve upon some of the problems with images captured from devices, including images captured from devices with larger aperture lenses, and, in some particular examples, mobile devices with larger aperture lenses. Multiple images may be captured by the capture device and processing applied to generate a single image through fusing of the multiple images. One potential benefit obtained with fusion of multiple images is a single image with an effective depth of focus (DOF) larger than that available in a single image obtained from the capture device. The DOF of the fused image may be larger than a single image and/or may include multiple distinct in-focus focal distances, whereas a single image from a single capture device has only a single in-focus focal distance.Type: GrantFiled: January 28, 2021Date of Patent: September 12, 2023Assignee: QUALCOMM IncorporatedInventors: Wen-Chun Feng, Hsuan-Ming Liu, Yu-Ren Lai
-
Publication number: 20230012219Abstract: The present disclosure provides systems, apparatus, methods, and computer-readable media that support multi-frame depth-of-field (MF-DOF) for deblurring background regions of interest (ROIs), such as background faces, that may be blurred due to a large aperture size or other characteristics of the camera used to capture the image frame. The processing may include the use of two image frames obtained at two different focus points corresponding to the multiple ROIs in the image frame. The corrected image frame may be determined by deblurring one or more ROIs of the first image frame using an AI-based model and/or local gradient information. The MF-DOF may allow selectively increasing a depth-of-field (DOF) of an image to provide focused capture of multiple regions of interest, without causing a reduction in aperture (and subsequently an amount of light available for photography) or background blur that may be desired for photography.Type: ApplicationFiled: December 22, 2021Publication date: January 12, 2023Inventors: Wen-Chun Feng, Yu-Ren Lai, Hsin Yueh Chang
-
Publication number: 20230011950Abstract: Systems and techniques are provided for processing image data. According to some aspects, a process can include obtaining a frame captured using an image sensor of a device. The process can include detecting an orientation of the device using a position sensor. The process can further include determining, based on the orientation, a transform to be applied to a region of interest in the frame. The process can include applying the transform to the region of interest. The process can further include providing the transformed region of interest to the object detection algorithm.Type: ApplicationFiled: February 2, 2022Publication date: January 12, 2023Inventors: Wen-Chun FENG, Yu-Ren LAI, Hsin Yueh CHANG
-
Publication number: 20220237813Abstract: Image processing performed on images captured with image capture devices may be used to improve upon some of the problems with images captured from devices, including images captured from devices with larger aperture lenses, and, in some particular examples, mobile devices with larger aperture lenses. Multiple images may be captured by the capture device and processing applied to generate a single image through fusing of the multiple images. One potential benefit obtained with fusion of multiple images is a single image with an effective depth of focus (DOF) larger than that available in a single image obtained from the capture device. The DOF of the fused image may be larger than a single image and/or may include multiple distinct in-focus focal distances, whereas a single image from a single capture device has only a single in-focus focal distance.Type: ApplicationFiled: January 28, 2021Publication date: July 28, 2022Inventors: Wen-Chun Feng, Hsuan-Ming Liu, Yu-Ren Lai
-
Publication number: 20210390747Abstract: 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.Type: ApplicationFiled: June 9, 2021Publication date: December 16, 2021Inventors: Wen-Chun FENG, Yu-Chen HSU, Yu-Ren LAI
-
Patent number: 10699107Abstract: An image detection method for determining the postures of a user includes: obtaining a plurality of images of a user; determining whether the user moves; and when the user is determined to be moving, calculating whether the amount of images is greater than a first predetermined value or not, calculating whether or not the amount of images of the user in the region of interest (ROI) is greater than a second predetermined value, and calculating whether or not the amount of images of the user not in the ROI is greater than a third predetermined value, in order to determine the postures of the user.Type: GrantFiled: March 13, 2018Date of Patent: June 30, 2020Assignee: Wistron Corp.Inventors: Po Chun Chen, Yu-Ren Lai, Ching-An Cho, Kuo Ting Huang, Yu-Yen Chen
-
Patent number: 10685220Abstract: An image detection method for determining the posture of a user includes: obtaining a reference image of the user in a region of interest (ROI); obtaining a test image of user at the ROI; executing a feature matching analysis of the test image which compares the feature parameter of the test image and the feature parameter of the reference image to determine the similarity information of the test image and the reference image; and executing a pixel distribution analysis of the test image to obtain user pixel distribution information; and determining the posture of the user based on the user similarity information and the user pixel distribution information.Type: GrantFiled: February 23, 2018Date of Patent: June 16, 2020Assignee: Wistron Corp.Inventors: Yu-Ren Lai, Po Chun Chen, Ching-An Cho, Kuo Ting Huang, Yu-Yen Chen
-
Patent number: 10383531Abstract: A method for measuring a physiological signal is provided, including the steps of: receiving a video and performing face detection for each image frame thereof; performing photo-plethysmography (PPG) calculation and analysis on first face image for first image frame to obtain first PPG information of first regions and second PPG information of corresponding second regions; determining at least one region-of-interest (ROI) and one noise reference region according to the first PPG information and the second PPG information; generating ROI information and noise reference region information based on the ROI and the noise reference region; and performing the PPG calculation and analysis on the ROI and the noise reference region of the second face image of each subsequent second image frame and generating corresponding third PPG information; and counting the PPG information of all the image frames to calculate a measured value of a physiological signal.Type: GrantFiled: December 19, 2017Date of Patent: August 20, 2019Assignee: WISTRON CORP.Inventors: Yu-Ren Lai, Yu-Yen Chen
-
Publication number: 20190122038Abstract: An image detection method for determining the posture of a user includes: obtaining a reference image of the user in a region of interest (ROI); obtaining a test image of user at the ROI; executing a feature matching analysis of the test image which compares the feature parameter of the test image and the feature parameter of the reference image to determine the similarity information of the test image and the reference image; and executing a pixel distribution analysis of the test image to obtain user pixel distribution information; and determining the posture of the user based on the user similarity information and the user pixel distribution information.Type: ApplicationFiled: February 23, 2018Publication date: April 25, 2019Inventors: Yu-Ren LAI, Po Chun CHEN, Ching-An CHO, Kuo Ting HUANG, Yu-Yen CHEN
-
Publication number: 20190122039Abstract: An image detection method for determining the postures of a user includes: obtaining a plurality of images of a user; determining whether the user moves; and when the user is determined to be moving, calculating whether the amount of images is greater than a first predetermined value or not, calculating whether or not the amount of images of the user in the region of interest (ROI) is greater than a second predetermined value, and calculating whether or not the amount of images of the user not in the ROI is greater than a third predetermined value, in order to determine the postures of the user.Type: ApplicationFiled: March 13, 2018Publication date: April 25, 2019Inventors: Po Chun CHEN, Yu-Ren LAI, Ching-An CHO, Kuo Ting HUANG, Yu-Yen CHEN
-
Publication number: 20190046057Abstract: A method for measuring a physiological signal is provided, including the steps of: receiving a video and performing face detection for each image frame thereof; performing photo-plethysmography (PPG) calculation and analysis on first face image for first image frame to obtain first PPG information of first regions and second PPG information of corresponding second regions; determining at least one region-of-interest (ROI) and one noise reference region according to the first PPG information and the second PPG information; generating ROI information and noise reference region information based on the ROI and the noise reference region; and performing the PPG calculation and analysis on the ROI and the noise reference region of the second face image of each subsequent second image frame and generating corresponding third PPG information; and counting the PPG information of all the image frames to calculate a measured value of a physiological signal.Type: ApplicationFiled: December 19, 2017Publication date: February 14, 2019Inventors: Yu-Ren Lai, Yu-Yen Chen