-
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：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。
-
33.发明申请Object-Of-Interest Detection And Recognition With Split, Full-Resolution Image Processing Pipeline 有权利用分割，全分辨率图像处理流水线的感兴趣的检测和识别公开(公告)号：US20150347861A1
公开(公告)日：2015-12-03
申请号：US14292776
申请日：2014-05-30
Applicant: APPLE INC.
Inventor： Frank Doepke , Kevin Hunter
CPC classification number: H04N5/23245 , G06K9/00449 , G06K9/00463 , G06K9/4604 , G06K2009/363
Abstract: Differing embodiments of this disclosure may employ one or all of the several techniques described herein to utilize a “split” image processing pipeline, wherein one part of the “split” image processing pipeline runs an object-of-interest recognition algorithm on scaled down (also referred to herein as “low-resolution”) frames received from a camera of a computing device, while the second part of the “split” image processing pipeline concurrently runs an object-of-interest detector in the background on full resolution (also referred to herein as “high-resolution”) image frames received from the camera. If the object-of-interest detector detects an object-of-interest that can be read, it then crops the object-of-interest out of the “high-resolution” camera buffer, optionally performs a perspective correction, and/or scaling on the object-of-interest to make it the desired size needed by the object-of-interest recognition algorithm, and then sends the scaled, high-resolution representation of the object-of-interest to the object-of-interest recognition algorithm for further processing.
Abstract translation: 本公开的不同实施例可以使用本文所描述的几种技术中的一种或全部来利用“分割”图像处理流水线，其中“分割”图像处理流水线的一部分按缩小的方式运行兴趣对象识别算法（ 这里也称为“低分辨率”）帧，而“分割”图像处理流水线的第二部分同时在全分辨率的背景下运行感兴趣的检测器（也称为“低分辨率”） 这里称为“高分辨率”）从相机接收的图像帧。 如果感兴趣的感兴趣的检测器检测到可以读取的感兴趣的物体，那么它然后将感兴趣的物体从“高分辨率”相机缓冲器中进行裁剪，可选地执行透视校正和/或缩放 利益感兴趣的目标，使其成为目标感兴趣识别算法所需的大小，然后将感兴趣的目标的缩放的高分辨率表示发送到感兴趣的对象识别算法 进一步处理。
-
公开(公告)号：US20140126819A1
公开(公告)日：2014-05-08
申请号：US13670080
申请日：2012-11-06
Applicant: APPLE INC.
Inventor： Frank Doepke , Marius Tico
IPC: G06K9/34
CPC classification number: G06T7/0028 , G06T7/30 , G06T7/33 , G06T2207/20012 , G06T2207/20021 , G06T2207/20104 , G06T2207/30201
Abstract: Techniques for registering images based on an identified region of interest (ROI) are described. In general, the disclosed techniques identify a region of ROI within an image and assign areas within the image corresponding to those regions more importance during the registration process. More particularly, the disclosed techniques may employ user-input or image content information to identify the ROI. Once identified, features within the ROI may be given more weight or significance during registration operations than other areas of the image having high-feature content but which are not as important to the individual capturing the image.
Abstract translation: 描述了基于所识别的感兴趣区域（ROI）来注册图像的技术。 通常，所公开的技术识别图像内的ROI的区域，并且在注册过程期间分配对应于那些区域的图像中的区域更重要。 更具体地，所公开的技术可以采用用户输入或图像内容信息来识别ROI。 一旦被识别，ROI中的特征可以在注册操作期间比具有高特征内容的图像的其他区域给予更多的权重或重要性，但对于捕获图像的个体而言并不重要。
-
-
-
Search Results
34
records
(took 0.013 seconds)
