公开(公告)号：US08953843B1

公开(公告)日：2015-02-10

申请号：US13759855

申请日：2013-02-05

Applicant: Google Inc.

Inventor： Gavan Kwan ,  Rushabh Ashok Doshi ,  Federico Javier Lebrón

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00771

Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method including detecting positions of objects of a specific type within an ordered sequence of images. The method includes estimating one or more intermediate positions of one or more intermediate instances of an object in one or more intermediate images within the ordered sequence of images between an initial image and a subsequent image based on an initial position of an initial instance of the object in the initial image and a subsequent position of a subsequent instance of the object in the subsequent image. The method includes providing a list of the objects for presentation. The method includes receiving a selection of the object from the list. The method includes performing an operation on the initial instance, the intermediate instances, and the subsequent instance of the object.

Abstract translation: 除了别的以外，本说明书的主题可以实现包括在有序序列图像内检测特定类型的对象的位置的计算机实现的方法。 该方法包括基于对象的初始实例的初始位置来估计在初始图像和后续图像之间的有序图像序列内的一个或多个中间图像中的对象的一个​​或多个中间实例的一个或多个中间位置 在初始图像中以及后续图像中后续对象实例的后续位置。 该方法包括提供用于呈现的对象的列表。 该方法包括从列表中接收对象的选择。 该方法包括对初始实例，中间实例和后续的对象实例执行操作。

公开(公告)号：US09071814B1

公开(公告)日：2015-06-30

申请号：US13968062

申请日：2013-08-15

Applicant: Google Inc.

Inventor： Zihong Fan ,  Gavan Kwan ,  Bosun Adeoti

IPC: H04N5/783 ,  H04N5/93 ,  H04N9/808 ,  H04N19/177 ,  G11B27/00

CPC classification number: H04N5/91 ,  H04N9/8045 ,  H04N19/177

Abstract: Systems and methods for automatically detecting scenes in a video based on parameters employed to encode the video are presented. In one or more aspects, a system is provided that includes a scene identification component configured to analyze a video comprising a plurality of sequential frames, including a plurality of intra-frames (I-frames) and a plurality of predictive frames (P-frames), and identify N groups of adjacent frames constituting N scenes of the video based in part on respective locations of the I-frames throughout the plurality of sequential frames, where N is an integer. The system further includes a video clip generation component configured to generate one or more video clips from one or more of the N scenes of the video, respectively, using portions of frames respectively associated with the one or more scenes of the N scenes of the video.

Abstract translation: 提出了基于用于编码视频的参数来自动检测视频场景的系统和方法。 在一个或多个方面，提供了一种系统，其包括场景识别组件，其被配置为分析包括多个连续帧的视频，包括多个帧内（I帧）和多个预测帧（P帧） ），并且部分地基于多个连续帧中的I帧的各个位置来识别构成视频的N个场景的N组相邻帧，其中N是整数。 该系统还包括视频剪辑生成组件，其被配置为分别使用分别与视频的N个场景中的一个或多个场景相关联的帧的部分来生成来自视频的N个场景中的一个或多个的一个或多个视频剪辑 。