-
公开(公告)号：US20220335579A1
公开(公告)日：2022-10-20
申请号：US17656734
申请日：2022-03-28
Applicant: Apple Inc.
Inventor： Jianping Zhou , Ali-Amir Aldan , Sebastien X. Beysserie
Abstract: Devices, methods, and non-transitory program storage devices are disclosed herein to provide for improved perspective distortion correction for wide field of view (FOV) video image streams. The techniques disclosed herein may be configured, such that the distortion correction applied to requested region of interest (ROI) portions taken from individual images of the wide FOV video image stream smoothly transitions between applying different distortion correction to ROIs, depending on their respective FOVs. In particular, the techniques disclosed herein may modify the types and/or amounts of perspective distortion correction applied, based on the FOVs of the ROIs, as well as their location within the original wide FOV video image stream. In some cases, additional perspective distortion correction may also be applied to account for tilt in an image capture device as the wide FOV video image stream is being captured and/or the unwanted inclusion of “invalid” pixels from the wide FOV image.
-
公开(公告)号：US10911677B1
公开(公告)日：2021-02-02
申请号：US16564132
申请日：2019-09-09
Applicant: Apple Inc.
Inventor： Jianping Zhou , Sebastien X. Beysserie , Tao Zhang
Abstract: Various techniques are disclosed herein, which comprise obtaining a first stream of images from a first camera and a second stream of images from a second camera, wherein the first camera and second camera have different poses, and at least a portion of the image streams are captured concurrently. Next, a first stabilized trajectory and corresponding set of corrections used to stabilize the first stream of images are calculated. Based on determined differences between the poses of the first camera and second camera during the capture of the first and second streams of images, a second set of corrections to be applied to the second stream of images are derived to match the first stabilized trajectory. If desired, e.g., in response to determining that the stabilized first stream of images does not meet a stabilization criterion, the second stream of images may be stabilized using the second set of corrections.
-
公开(公告)号：US09979889B2
公开(公告)日：2018-05-22
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：US20180041707A1
公开(公告)日：2018-02-08
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
CPC classification number: H04N5/23267 , H04N5/23258
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：US09787902B1
公开(公告)日：2017-10-10
申请号：US15179680
申请日：2016-06-10
Applicant: Apple Inc.
Inventor： Sebastien X. Beysserie , Jianping Zhou , Stephane S. Ben Soussan
CPC classification number: H04N5/23267 , H04N5/23258
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.
-
Patent Agency Ranking
公开(公告)号：US09773192B2
公开(公告)日：2017-09-26
申请号：US14732738
申请日：2015-06-07
Applicant: Apple Inc.
Inventor： Xiaoxing Li , Geoffrey T. Anneheim , Jianping Zhou , Richard D. Seely , Marco Zuliani
CPC classification number: G06K9/6202 , G06T3/40 , G06T7/13 , G06T7/248 , G06T7/90 , G06T2207/10016 , G06T2207/10024
Abstract: Techniques to identify and track a pre-identified region-of-interest (ROI) through a temporal sequence of frames/images are described. In general, a down-sampled color gradient (edge map) of an arbitrary sized ROI from a prior frame may be used to generate a small template. This initial template may be used to identify a region of a new or current frame that may be overscan and used to create a current frame's edge map. By comparing the prior frame's template to the current frame's edge map, a cost value or image may be found and used to identify the current frame's ROI center. The size of the current frame's ROI may be found by varying the size of putative new ROIs and testing for their congruence with the prior frame's template. Subsequent ROI's for subsequent frames may be identified to, effectively, track an arbitrarily sized ROI through a sequence of video frames.
-
公开(公告)号：US09542585B2
公开(公告)日：2017-01-10
申请号：US13911983
申请日：2013-06-06
Applicant: Apple Inc.
Inventor： George Williams , Benjamin Olson , Sebastien Beysserie , Ethan Tira-Thompson , Jianping Zhou , Claus Molgaard , Todd Sachs , Rudolph van der Merwe , Marco Zuliani
CPC classification number: G06K7/1443 , G06K7/10722 , G06K9/3233 , G06K9/6203 , G06K2009/3291 , G06K2209/21 , G06T7/20
Abstract: A method to improve the efficiency of the detection and tracking of machine-readable objects is disclosed. The properties of image frames may be pre-evaluated to determine whether a machine-readable object, even if present in the image frames, would be likely to be detected. After it is determined that one or more image frames have properties that may enable the detection of a machine-readable object, image data may be evaluated to detect the machine-readable object. When a machine-readable object is detected, the location of the machine-readable object in a subsequent frame may be determined based on a translation metric between the image frame in which the object was identified and the subsequent frame rather than a detection of the object in the subsequent frame. The translation metric may be identified based on an evaluation of image data and/or motion sensor data associated with the image frames.
Abstract translation: 公开了一种提高机器可读对象检测和跟踪效率的方法。 可以预先评估图像帧的属性，以确定即使存在于图像帧中的机器可读对象是否可能被检测到。 在确定一个或多个图像帧具有能够检测机器可读对象的属性之后，可以评估图像数据以检测机器可读对象。 当检测到机器可读对象时，可以基于在其中识别对象的图像帧与后续帧之间的转换度量而不是对象的检测来确定随后帧中的机器可读对象的位置 在后续的框架。 可以基于与图像帧相关联的图像数据和/或运动传感器数据的评估来识别翻译度量。
-
公开(公告)号：US20140363087A1
公开(公告)日：2014-12-11
申请号：US13911740
申请日：2013-06-06
Applicant: Apple Inc.
Inventor： Marius Tico , Jianping Zhou , Anita Nariani Schulze , Rolf Toft , Paul Hubel , Wei Sun
CPC classification number: G06K9/46 , G06K9/6201 , G06T5/003 , G06T5/10 , G06T2207/10016 , G06T2207/10144 , G06T2207/20016 , G06T2207/20201 , G06T2207/20208 , G06T2207/20221 , H04N5/23267
Abstract: Systems, methods, and computer readable media to improve image stabilization operations are described. Novel approaches for fusing non-reference images with a pre-selected reference frame in a set of commonly captured images are disclosed. The fusing approach may use a soft transition by using a weighted average for ghost/non-ghost pixels to avoid sudden transition between neighborhood and almost similar pixels. Additionally, the ghost/non-ghost decision can be made based on a set of neighboring pixels rather than independently for each pixel. An alternative approach may involve performing a multi-resolution decomposition of all the captured images, using temporal fusion, spatio-temporal fusion, or combinations thereof, at each level and combining the different levels to generate an output image.
Abstract translation: 描述了用于改善图像稳定操作的系统，方法和计算机可读介质。 公开了一组用于将非参考图像与一组普通捕获图像中的预选参考帧融合的新方法。 融合方法可以通过使用重影/非重像素的加权平均值来使用软转换，以避免邻域和几乎相似像素之间的突然过渡。 此外，可以基于一组相邻像素而不是针对每个像素独立地进行重影/非重影决定。 替代方法可以包括在每个级别上使用时间融合，时空融合或其组合执行所有捕获图像的多分辨率分解，并组合不同的级别以生成输出图像。
-
公开(公告)号：US20140363044A1
公开(公告)日：2014-12-11
申请号：US13911983
申请日：2013-06-06
Applicant: Apple Inc.
Inventor： George Williams , Benjamin Olson , Sebastien Beysserie , Ethan Tira-Thompson , Jianping Zhou , Claus Molgaard , Todd Sachs , Rudolph van der Merwe , Marco Zuliani
IPC: G06K9/00
CPC classification number: G06K7/1443 , G06K7/10722 , G06K9/3233 , G06K9/6203 , G06K2009/3291 , G06K2209/21 , G06T7/20
Abstract: A method to improve the efficiency of the detection and tracking of machine-readable objects is disclosed. The properties of image frames may be pre-evaluated to determine whether a machine-readable object, even if present in the image frames, would be likely to be detected. After it is determined that one or more image frames have properties that may enable the detection of a machine-readable object, image data may be evaluated to detect the machine-readable object. When a machine-readable object is detected, the location of the machine-readable object in a subsequent frame may be determined based on a translation metric between the image frame in which the object was identified and the subsequent frame rather than a detection of the object in the subsequent frame. The translation metric may be identified based on an evaluation of image data and/or motion sensor data associated with the image frames.
Abstract translation: 公开了一种提高机器可读对象检测和跟踪效率的方法。 可以预先评估图像帧的属性，以确定即使存在于图像帧中的机器可读对象是否可能被检测到。 在确定一个或多个图像帧具有能够检测机器可读对象的属性之后，可以评估图像数据以检测机器可读对象。 当检测到机器可读对象时，可以基于在其中识别对象的图像帧与后续帧之间的转换度量而不是对象的检测来确定随后帧中的机器可读对象的位置 在后续的框架。 可以基于与图像帧相关联的图像数据和/或运动传感器数据的评估来识别翻译度量。
-
公开(公告)号：US11887283B2
公开(公告)日：2024-01-30
申请号：US17656734
申请日：2022-03-28
Applicant: Apple Inc.
Inventor： Jianping Zhou , Ali-Amir Aldan , Sebastien X. Beysserie
CPC classification number: G06T5/006 , G06T3/0093 , G06V10/25
Abstract: Devices, methods, and non-transitory program storage devices are disclosed herein to provide for improved perspective distortion correction for wide field of view (FOV) video image streams. The techniques disclosed herein may be configured, such that the distortion correction applied to requested region of interest (ROI) portions taken from individual images of the wide FOV video image stream smoothly transitions between applying different distortion correction to ROIs, depending on their respective FOVs. In particular, the techniques disclosed herein may modify the types and/or amounts of perspective distortion correction applied, based on the FOVs of the ROIs, as well as their location within the original wide FOV video image stream. In some cases, additional perspective distortion correction may also be applied to account for tilt in an image capture device as the wide FOV video image stream is being captured and/or the unwanted inclusion of “invalid” pixels from the wide FOV image.
-
-
-
-
-
-
-
-
-
Search Results
44
records
(took 0.028 seconds)
