-
公开(公告)号：US12177567B2
公开(公告)日：2024-12-24
申请号：US17805399
申请日：2022-06-03
Applicant: Apple Inc.
Inventor： Ahmed T. Kamal , Feng Li , Florian Ciurea , Jianping Zhou , Saeed Izadi , Sebastien X. Beysserie , Stephane S. Ben Soussan
Abstract: Devices, methods, and non-transitory computer readable media are disclosed herein to repair or mitigate the appearance of unwanted reflection artifacts in captured video image streams. These unwanted reflection artifacts often present themselves as brightly-colored spots, circles, rings, or halos that reflect the shape of a bright light source in the captured image. These artifacts, also referred to herein as “ghosts” or “green ghosts” (due to often having a greenish tint), are typically located in regions of the captured images where there is not actually a bright light source located in the image. In fact, such unwanted reflection artifacts often present themselves on the image sensor across the principal point of the lens from where the actual bright light source in the captured image is located. Such devices, methods and computer readable media may be configured to detect, track, and repair such unwanted reflection artifacts in an intelligent and efficient fashion.
-
公开(公告)号：US20160337589A1
公开(公告)日：2016-11-17
申请号：US15218405
申请日：2016-07-25
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Damien J. Thivent , Jianping Zhou , Rudolph van der Merwe , Jason Klivington , Xiaoxing Li , Anders Holtsberg , Martin Lindberg , George E. Williams
IPC: H04N5/232
CPC classification number: H04N5/23267 , G06T5/003 , G06T2207/10016 , G06T2207/20201 , H04N5/23254
Abstract: Techniques to permit a digital image capture device to stabilize a video stream in real-time (during video capture operations) are presented. In general, techniques are disclosed for stabilizing video images using an overscan region and a look-ahead technique enabled by buffering a number of video input frames before generating a first stabilized video output frame. (Capturing a larger image than is displayed creates a buffer of pixels around the edge of an image; overscan is the term given to this buffer of pixels.) More particularly, techniques are disclosed for buffering an initial number of input frames so that a “current” frame can use motion data from both “past” and “future” frames to adjust the strength of a stabilization metric value so as to keep the current frame within its overscan. This look-ahead and look-behind capability permits a smoother stabilizing regime with fewer abrupt adjustments.
-
公开(公告)号：US09426409B2
公开(公告)日：2016-08-23
申请号：US14613133
申请日：2015-02-03
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Jason Klivington , Rolf Toft , Frank Doepke
Abstract: Traditionally, time-lapse videos are constructed from images captured at time intervals called “temporal points of interests” or “temporal POIs.” Disclosed herein are systems and methods of constructing improved, motion-stabilized time-lapse videos using temporal points of interest and image similarity comparisons. According to some embodiments, a “burst” of images may be captured, centered around the aforementioned temporal points of interest. Then, each burst sequence of images may be analyzed, e.g., by performing an image similarity comparison between each image in the burst sequence and the image selected at the previous temporal point of interest. Selecting the image from a given burst that is most similar to the previous selected image, while minimizing the amount of motion with the previous selected image, allows the system to improve the quality of the resultant time-lapse video by discarding “outlier” or other undesirable images captured in the burst sequence and motion stabilizing the selected image.
Abstract translation: 传统上，延时视频是从被称为“时间兴趣点”或“时间POI”的时间间隔捕获的图像构成的。这里公开了使用时间兴趣点构建改进的，运动稳定的延时视频的系统和方法， 图像相似性比较。 根据一些实施例，可以以上述时间兴趣点为中心捕获图像的“突发”。 然后，可以例如通过在突发序列中的每个图像和在先前的时间点选择的图像之间执行图像相似性比较来分析图像的每个突发序列。 选择与先前选择的图像最相似的给定脉冲串中的图像，同时使用先前选择的图像最小化运动量，允许系统通过丢弃“异常值”或其他信号来提高合成的延时视频的质量 在突发序列中捕获的不期望的图像和稳定所选择的图像的运动。
-
公开(公告)号：US09413963B2
公开(公告)日：2016-08-09
申请号：US14467987
申请日：2014-08-25
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Damien J. Thivent , Jianping Zhou , Rudolph van der Merwe , Jason Klivington , Xiaoxing Li , Anders Holtsberg , Martin Lindberg , George E. Williams
CPC classification number: H04N5/23267 , G06T5/003 , G06T2207/10016 , G06T2207/20201 , H04N5/23254
Abstract: Techniques to permit a digital image capture device to stabilize a video stream in real-time (during video capture operations) are presented. In general, techniques are disclosed for stabilizing video images using an overscan region and a look-ahead technique enabled by buffering a number of video input frames before generating a first stabilized video output frame. (Capturing a larger image than is displayed creates a buffer of pixels around the edge of an image; overscan is the term given to this buffer of pixels.) More particularly, techniques are disclosed for buffering an initial number of input frames so that a “current” frame can use motion data from both “past” and “future” frames to adjust the strength of a stabilization metric value so as to keep the current frame within its overscan. This look-ahead and look-behind capability permits a smoother stabilizing regime with fewer abrupt adjustments.
Abstract translation: 呈现允许数字图像捕获设备实时（视频捕获操作期间）稳定视频流的技术。 通常，公开了用于使用过扫描区域稳定视频图像的技术，以及通过在生成第一稳定视频输出帧之前缓冲多个视频输入帧而启用的先行技术。 （捕获比所显示的图像更大的图像在图像的边缘周围产生像素的缓冲器;过扫描是给予该像素缓冲器的术语。）更具体地，公开了用于缓冲初始数量的输入帧的技术， 当前“帧可以使用来自”过去“和”未来“帧的运动数据来调整稳定度量值的强度，以便将当前帧保持在其过扫描内。 这种前瞻性和后仰能力允许更平稳的稳定方案，具有较少的突然调整。
-
公开(公告)号：US20160094801A1
公开(公告)日：2016-03-31
申请号：US14613133
申请日：2015-02-03
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Jason Klivington , Rolf Toft , Frank Doepke
Abstract: Traditionally, time-lapse videos are constructed from images captured at time intervals called “temporal points of interests” or “temporal POIs.” Disclosed herein are systems and methods of constructing improved, motion-stabilized time-lapse videos using temporal points of interest and image similarity comparisons. According to some embodiments, a “burst” of images may be captured, centered around the aforementioned temporal points of interest. Then, each burst sequence of images may be analyzed, e.g., by performing an image similarity comparison between each image in the burst sequence and the image selected at the previous temporal point of interest. Selecting the image from a given burst that is most similar to the previous selected image, while minimizing the amount of motion with the previous selected image, allows the system to improve the quality of the resultant time-lapse video by discarding “outlier” or other undesirable images captured in the burst sequence and motion stabilizing the selected image.
Abstract translation: 传统上，延时视频是从被称为“时间兴趣点”或“时间POI”的时间间隔捕获的图像构成的。这里公开了使用时间兴趣点构建改进的，运动稳定的延时视频的系统和方法， 图像相似性比较。 根据一些实施例，可以以上述时间兴趣点为中心捕获图像的“突发”。 然后，可以例如通过在突发序列中的每个图像和在先前的时间点选择的图像之间执行图像相似性比较来分析图像的每个突发序列。 选择与先前选择的图像最相似的给定脉冲串中的图像，同时使用先前选择的图像最小化运动量，允许系统通过丢弃“异常值”或其他信号来提高合成的延时视频的质量 在突发序列中捕获的不期望的图像和稳定所选择的图像的运动。
-
Patent Agency Ranking
公开(公告)号：US20230396883A1
公开(公告)日：2023-12-07
申请号：US17805399
申请日：2022-06-03
Applicant: Apple Inc.
Inventor： Ahmed T. Kamal , Feng Li , Florian Ciurea , Jianping Zhou , Saeed Izadi , Sebastien X. Beysserie , Stephane S. Ben Soussan
CPC classification number: H04N5/23267 , H04N5/23212 , H04N5/23296 , G06V10/60 , G06V10/751
Abstract: Devices, methods, and non-transitory computer readable media are disclosed herein to repair or mitigate the appearance of unwanted reflection artifacts in captured video image streams. These unwanted reflection artifacts often present themselves as brightly-colored spots, circles, rings, or halos that reflect the shape of a bright light source in the captured image. These artifacts, also referred to herein as “ghosts” or “green ghosts” (due to often having a greenish tint), are typically located in regions of the captured images where there is not actually a bright light source located in the image. In fact, such unwanted reflection artifacts often present themselves on the image sensor across the principal point of the lens from where the actual bright light source in the captured image is located. Such devices, methods and computer readable media may be configured to detect, track, and repair such unwanted reflection artifacts in an intelligent and efficient fashion.
-
公开(公告)号：US10148881B2
公开(公告)日：2018-12-04
申请号：US15728038
申请日：2017-10-09
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Jianping Zhou , Stephane S. Ben Soussan
IPC: H04N5/232
Abstract: Techniques to improve a digital image capture device's ability to stabilize a video stream—while enforcing desired stabilization constraints on particular images in the video stream—are presented that utilize an overscan region and a look-ahead technique enabled by buffering a number of video input frames before generating a first stabilized video output frame. More particularly, techniques are disclosed for buffering an initial number of input frames so that a “current” frame can use motion data from both “past” and “future” frames to adjust the value of a stabilization strength parameter and/or the weighted contribution of particular frames from the buffer in the determination of stabilization motion values for the current frame. Such techniques keep the current frame within its overscan and ensure that the stabilization constraints are enforced, while maintaining desired smoothness in the video stream. In some embodiments, the stabilization constraint may comprise a maximum allowed frame displacement.
-
公开(公告)号：US20170280059A1
公开(公告)日：2017-09-28
申请号：US15457377
申请日：2017-03-13
Applicant: Apple Inc.
Inventor： Damien J. Thivent , George E. Williams , Jianping Zhou , Richard L. Baer , Rolf Toft , Sebastien X. Beysserie
CPC classification number: H04N5/23287 , G06T5/20 , H04N5/2254 , H04N5/23254 , H04N5/23258 , H04N5/23267 , H04N5/2328
Abstract: Techniques to improve a digital image capture device's ability to stabilize a video stream are presented. According to some embodiments, improved stabilization of captured video frames is provided by intelligently harnessing the complementary effects of both optical image stabilization (OIS) and electronic image stabilization (EIS). In particular, OIS may be used to remove intra-frame motion blur that is typically lower in amplitude and dominates with longer integration times, while EIS may be used to remove residual unwanted frame-to-frame motion that is typically larger in amplitude. The techniques disclosed herein may also leverage information provided from the image capture device's OIS system to perform improved motion blur-aware video stabilization strength modulation, which permits better video stabilization performance in low light conditions, where integration times tend to be longer, thus leading to a greater amount of motion blurring in the output stabilized video.
-
公开(公告)号：US20160006935A1
公开(公告)日：2016-01-07
申请号：US14467998
申请日：2014-08-25
Applicant: Apple Inc.
Inventor： Jianping Zhou , Sebastien X. Beysserie
IPC: H04N5/232
CPC classification number: H04N5/23254 , H04N5/23258 , H04N5/23267
Abstract: Techniques to improve a digital image capture device's ability to stabilize a video stream in low light capture conditions are presented. In general, techniques are disclosed for stabilizing video images using an overscan region and a look-ahead technique enabled by buffering a number of video input frames before generating a first stabilized video output frame. More particularly, techniques are disclosed for buffering an initial number of input frames so that a “current” frame can use time stamped image capture device motion data from both “past” and “future” frames to adjust the strength of a stabilization metric value so as to keep the current frame within its overscan. The calculated adjustments to the strength of the stabilization metric value for a particular frame may be limited to a target max strength value that is determined based, at least in part, on an estimated amount of motion blur in the current frame.
Abstract translation: 介绍了提高数字图像采集设备在低光捕获条件下稳定视频流的能力的技术。 通常，公开了用于使用过扫描区域稳定视频图像的技术，以及通过在生成第一稳定视频输出帧之前缓冲多个视频输入帧而启用的先行技术。 更具体地，公开了用于缓冲初始数量的输入帧的技术，使得“当前”帧可以使用来自“过去”和“未来”帧的时间戳图像捕获设备运动数据来调整稳定度量值的强度 以将当前帧保持在其过扫描内。 对特定帧的稳定度量值的强度的计算的调整可以被限制为至少部分地基于当前帧中的估计的运动模糊量确定的目标最大强度值。
-
公开(公告)号：US20150350548A1
公开(公告)日：2015-12-03
申请号：US14467987
申请日：2014-08-25
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Damien J. Thivent , Jianping Zhou , Rudolph van der Merwe , Jason Klivington , Xiaoxing Li , Anders Holtsberg , Martin Lindberg , George E. Williams
CPC classification number: H04N5/23267 , G06T5/003 , G06T2207/10016 , G06T2207/20201 , H04N5/23254
Abstract: Techniques to permit a digital image capture device to stabilize a video stream in real-time (during video capture operations) are presented. In general, techniques are disclosed for stabilizing video images using an overscan region and a look-ahead technique enabled by buffering a number of video input frames before generating a first stabilized video output frame. (Capturing a larger image than is displayed creates a buffer of pixels around the edge of an image; overscan is the term given to this buffer of pixels.) More particularly, techniques are disclosed for buffering an initial number of input frames so that a “current” frame can use motion data from both “past” and “future” frames to adjust the strength of a stabilization metric value so as to keep the current frame within its overscan. This look-ahead and look-behind capability permits a smoother stabilizing regime with fewer abrupt adjustments.
Abstract translation: 呈现允许数字图像捕获设备实时（视频捕获操作期间）稳定视频流的技术。 通常，公开了用于使用过扫描区域稳定视频图像的技术，以及通过在生成第一稳定视频输出帧之前缓冲多个视频输入帧而启用的先行技术。 （捕获比所显示的图像更大的图像在图像的边缘周围产生像素的缓冲器;过扫描是给予该像素缓冲器的术语。）更具体地，公开了用于缓冲初始数量的输入帧的技术， 当前“帧可以使用来自”过去“和”未来“帧的运动数据来调整稳定度量值的强度，以便将当前帧保持在其过扫描内。 这种前瞻性和后仰能力允许更平稳的稳定方案，具有较少的突然调整。
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.021 seconds)
