-
公开(公告)号:US20130128064A1
公开(公告)日:2013-05-23
申请号:US13368284
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
IPC分类号: H04N5/228
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
-
公开(公告)号:US08929610B2
公开(公告)日:2015-01-06
申请号:US13368279
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
摘要翻译: 稳健视频稳定的方法和装置。 视频稳定技术将特征跟踪技术应用于输入视频序列以产生特征轨迹。 该技术应用视频分割技术将输入视频序列分解为分解窗口和转换窗口。 该技术顺序地平滑每个窗口中的轨迹。 对于分解窗口,可以使用基于子空间的优化技术。 对于转换窗口,可以使用使用相似度运动模型的直接跟踪优化技术。 该技术然后确定并应用翘曲模型到视频序列中的帧。 在至少一些实施例中,翘曲模型可以包括内容保留翘曲模型,单应性模型,相似度变换模型和全帧翻译模型。 然后可以根据裁剪技术裁剪翘曲的框架。
-
公开(公告)号:US08675918B2
公开(公告)日:2014-03-18
申请号:US13368282
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
-
公开(公告)号:US20130128065A1
公开(公告)日:2013-05-23
申请号:US13368279
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
IPC分类号: H04N5/228
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
-
公开(公告)号:US08885880B2
公开(公告)日:2014-11-11
申请号:US13367994
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
摘要翻译: 稳健视频稳定的方法和装置。 视频稳定技术将特征跟踪技术应用于输入视频序列以产生特征轨迹。 该技术应用视频分割技术将输入视频序列分解为分解窗口和转换窗口。 该技术顺序地平滑每个窗口中的轨迹。 对于分解窗口,可以使用基于子空间的优化技术。 对于转换窗口,可以使用使用相似度运动模型的直接跟踪优化技术。 该技术然后确定并应用翘曲模型到视频序列中的帧。 在至少一些实施例中,翘曲模型可以包括内容保留翘曲模型,单应性模型,相似度变换模型和全帧翻译模型。 然后可以根据裁剪技术裁剪翘曲的框架。
-
公开(公告)号:US08611602B2
公开(公告)日:2013-12-17
申请号:US13368284
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
摘要翻译: 稳健视频稳定的方法和装置。 视频稳定技术将特征跟踪技术应用于输入视频序列以产生特征轨迹。 该技术应用视频分割技术将输入视频序列分解为分解窗口和转换窗口。 该技术顺序地平滑每个窗口中的轨迹。 对于分解窗口,可以使用基于子空间的优化技术。 对于转换窗口,可以使用使用相似度运动模型的直接跟踪优化技术。 该技术然后确定并应用翘曲模型到视频序列中的帧。 在至少一些实施例中,翘曲模型可以包括内容保留翘曲模型,单应性模型,相似度变换模型和全帧翻译模型。 然后可以根据裁剪技术裁剪翘曲的框架。
-
公开(公告)号:US20130128063A1
公开(公告)日:2013-05-23
申请号:US13368282
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
IPC分类号: H04N5/228
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
-
公开(公告)号:US20130128062A1
公开(公告)日:2013-05-23
申请号:US13367994
申请日:2012-02-07
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang
IPC分类号: H04N5/228
CPC分类号: G06T7/33 , G06T7/246 , G06T2207/10016 , G06T2207/20028 , G06T2207/30241
摘要: Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique.
摘要翻译: 稳健视频稳定的方法和装置。 视频稳定技术将特征跟踪技术应用于输入视频序列以产生特征轨迹。 该技术应用视频分割技术将输入视频序列分解为分解窗口和转换窗口。 该技术顺序地平滑每个窗口中的轨迹。 对于分解窗口,可以使用基于子空间的优化技术。 对于转换窗口,可以使用使用相似度运动模型的直接跟踪优化技术。 该技术然后确定并应用翘曲模型到视频序列中的帧。 在至少一些实施例中,翘曲模型可以包括内容保留翘曲模型,单应性模型,相似度变换模型和全帧翻译模型。 然后可以根据裁剪技术裁剪翘曲的框架。
-
公开(公告)号:US20130120600A1
公开(公告)日:2013-05-16
申请号:US12953703
申请日:2010-11-24
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang , Michael L. Gleicher , Feng Liu
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang , Michael L. Gleicher , Feng Liu
IPC分类号: H04N5/228
CPC分类号: G06T7/262 , H04N5/23254 , H04N5/23267
摘要: Methods, apparatus, and computer-readable storage media for subspace video stabilization. A subspace video stabilization technique may provide a robust and efficient approach to video stabilization that achieves high-quality camera motion for a wide range of videos. The technique may transform a set of input two-dimensional (2D) motion trajectories so that they are both smooth and resemble visually plausible views of the imaged scene; this may be achieved by enforcing subspace constraints on feature trajectories while smoothing them. The technique may assemble tracked features in the video into a trajectory matrix, factor the trajectory matrix into two low-rank matrices, and perform filtering or curve fitting in a low-dimensional linear space. The technique may employ a moving factorization technique that is both efficient and streamable.
摘要翻译: 用于子空间视频稳定的方法,装置和计算机可读存储介质。 子空间视频稳定技术可以提供用于视频稳定的鲁棒且有效的方法,其实现针对各种视频的高质量相机运动。 该技术可以转换一组输入二维(2D)运动轨迹,使得它们是平滑的,并且类似于成像场景的视觉上合理的视图; 这可以通过对特征轨迹执行子空间约束来实现,同时平滑它们。 该技术可以将视频中的跟踪特征组合成轨迹矩阵,将轨迹矩阵归因为两个低阶矩阵,并在低维线性空间中执行滤波或曲线拟合。 该技术可以采用既有效又可流动的移动因式分解技术。
-
公开(公告)号:US08872928B2
公开(公告)日:2014-10-28
申请号:US12953703
申请日:2010-11-24
申请人: Hailin Jin , Aseem O. Agarwala , Jue Wang , Michael L. Gleicher , Feng Liu
发明人: Hailin Jin , Aseem O. Agarwala , Jue Wang , Michael L. Gleicher , Feng Liu
CPC分类号: G06T7/262 , H04N5/23254 , H04N5/23267
摘要: Methods, apparatus, and computer-readable storage media for subspace video stabilization. A subspace video stabilization technique may provide a robust and efficient approach to video stabilization that achieves high-quality camera motion for a wide range of videos. The technique may transform a set of input two-dimensional (2D) motion trajectories so that they are both smooth and resemble visually plausible views of the imaged scene; this may be achieved by enforcing subspace constraints on feature trajectories while smoothing them. The technique may assemble tracked features in the video into a trajectory matrix, factor the trajectory matrix into two low-rank matrices, and perform filtering or curve fitting in a low-dimensional linear space. The technique may employ a moving factorization technique that is both efficient and streamable.
摘要翻译: 用于子空间视频稳定的方法,装置和计算机可读存储介质。 子空间视频稳定技术可以提供用于视频稳定的鲁棒且有效的方法,其实现针对各种视频的高质量相机运动。 该技术可以转换一组输入二维(2D)运动轨迹,使得它们是平滑的,并且类似于成像场景的视觉上合理的视图; 这可以通过对特征轨迹执行子空间约束来实现,同时平滑它们。 该技术可以将视频中的跟踪特征组合成轨迹矩阵,将轨迹矩阵归因为两个低阶矩阵,并在低维线性空间中执行滤波或曲线拟合。 该技术可以采用既有效又可流动的移动因式分解技术。
-
-
-
-
-
-
-
-
-