公开(公告)号：US08477246B2

公开(公告)日：2013-07-02

申请号：US12500416

申请日：2009-07-09

Applicant: Ashutosh Saxena ,  Siddharth Batra ,  Andrew Y. Ng

Inventor： Ashutosh Saxena ,  Siddharth Batra ,  Andrew Y. Ng

IPC: H04N5/272

CPC classification number: G06T7/246 ,  G06T7/207 ,  G06T2207/10016 ,  G06T2207/20016 ,  G11B27/034 ,  G11B27/28 ,  H04N5/272

Abstract: Methods, systems, products and devices are implemented for editing video image frames. According to one such method, image content is embedded into video. A selection input is received for a candidate location in a video frame of the video. The candidate location is traced in subsequent video frames of the video by approximating three-dimensional camera motion between two frames using a model that compensates for camera rotations, camera translations and zooming, and by optimizing the approximation using statistical modeling of three-dimensional camera motion between video frames. Image content is embedded in the candidate location in the subsequent video frames of the video based upon the tracking thereof.

Abstract translation: 实现了编辑视频图像帧的方法，系统，产品和设备。 根据一种这样的方法，将图像内容嵌入到视频中。 为视频的视频帧中的候选位置接收选择输入。 通过使用补偿相机旋转，相机平移和缩放的模型以及通过使用三维相机运动的统计建模优化近似来逼近视频的后续视频帧中的候选位置，通过近似两帧之间的三维相机运动 在视频帧之间。 基于其跟踪，图像内容嵌入视频的后续视频帧中的候选位置。

公开(公告)号：US20100067865A1

公开(公告)日：2010-03-18

申请号：US12500416

申请日：2009-07-09

Applicant: Ashutosh Saxena ,  Siddharth Batra ,  Andrew Y. Ng

Inventor： Ashutosh Saxena ,  Siddharth Batra ,  Andrew Y. Ng

IPC: G11B27/00

CPC classification number: G06T7/246 ,  G06T7/207 ,  G06T2207/10016 ,  G06T2207/20016 ,  G11B27/034 ,  G11B27/28 ,  H04N5/272

Abstract: Methods, systems, products and devices are implemented for editing video image frames. According to one such method, image content is embedded into video. A selection input is received for a candidate location in a video frame of the video. The candidate location is traced in subsequent video frames of the video by approximating three-dimensional camera motion between two frames using a model that compensates for camera rotations, camera translations and zooming, and by optimizing the approximation using statistical modeling of three-dimensional camera motion between video frames. Image content is embedded in the candidate location in the subsequent video frames of the video based upon the tracking thereof.

Abstract translation: 实现了编辑视频图像帧的方法，系统，产品和设备。 根据一种这样的方法，将图像内容嵌入到视频中。 为视频的视频帧中的候选位置接收选择输入。 通过使用补偿相机旋转，相机平移和缩放的模型以及通过使用三维相机运动的统计建模优化近似来逼近视频的后续视频帧中的候选位置，通过近似两帧之间的三维相机运动 在视频帧之间。 基于其跟踪，图像内容嵌入视频的后续视频帧中的候选位置。