公开(公告)号：US08867789B2

公开(公告)日：2014-10-21

申请号：US13740376

申请日：2013-01-14

Applicant: Cyberlink Corp.

Inventor： Huan-Wen Hsiao ,  Chung-Yi Weng

IPC: G06K9/00 ,  G06T7/20 ,  H04N5/228

CPC classification number: G06T7/20 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20096 ,  G06T2207/30196

Abstract: Disclosed are various embodiments for tracking an object shown as moving in a video. One embodiment is a method for tracking an object in a video that comprises tracking in a first temporal direction an object in a plurality of video frames and generating a first tracking result, evaluating the first tracking result corresponding to tracking of the object in the first temporal direction, and stopping tracking in the first temporal direction upon the occurrence of a predefined event, wherein the predefined event is based on an evaluated tracking result. The method further comprises obtaining data identifying an object outline of the object upon stopping the tracking in the first temporal direction, tracking in a second temporal direction the object based on the data identifying the object outline of the object to generate a second tracking result, and generating a refined tracking result based on at least on one of the first tracking result, the second tracking result, or a combination thereof.

Abstract translation: 公开了用于跟踪在视频中显示为移动的对象的各种实施例。 一个实施例是用于跟踪视频中的对象的方法，其包括在第一时间方向上跟踪多个视频帧中的对象并生成第一跟踪结果，评估与第一时间中的对象的跟踪相对应的第一跟踪结果 方向，并且在发生预定义事件时在第一时间方向停止跟踪，其中预定事件基于所评估的跟踪结果。 该方法还包括：在停止第一时间方向的跟踪时，获取识别对象轮廓的数据，基于标识对象的对象轮廓的数据，在第二时间方向跟踪对象以产生第二跟踪结果，以及 基于第一跟踪结果，第二跟踪结果或其组合中的至少一个，生成精细跟踪结果。

公开(公告)号：US09336583B2

公开(公告)日：2016-05-10

申请号：US14258261

申请日：2014-04-22

Applicant: Cyberlink Corp.

Inventor： Ho-Chao Huang ,  Huan-Wen Hsiao ,  Chung-Yi Weng ,  Cheng-da Chung

IPC: G06T5/50 ,  G06K9/00 ,  G06T5/00 ,  G06T11/60

CPC classification number: G06T5/50 ,  G06K9/00281 ,  G06K9/00315 ,  G06T5/005 ,  G06T11/60 ,  G06T2207/10016 ,  G06T2207/20212 ,  G06T2207/30201

Abstract: Various embodiments are disclosed for image editing. A frame is obtained from a frame sequence depicting at least one individual, and facial characteristics in the frame are analyzed. A utilization score is assigned to the frame based on the detected facial characteristics, and a determination of whether to utilize the frame is made based on the utilization score. A completeness value is assigned, and a determination is made based on the completeness value of whether to repeat the steps above for an additional frame in the frame sequence based on the completeness value. Regions from the frames are combined to generate a composite image.

Abstract translation: 公开了用于图像编辑的各种实施例。 从描绘至少一个个体的帧序列获得帧，并且分析帧中的面部特征。 基于检测到的面部特征将利用分数分配给该帧，并且基于利用分数来确定是否利用该帧。 分配完整性值，并基于完整性值，基于是否对帧序列中的附加帧重复上述步骤的完整性来进行确定。 来自帧的区域被组合以生成合成图像。

公开(公告)号：US20140369627A1

公开(公告)日：2014-12-18

申请号：US14258261

申请日：2014-04-22

Applicant: Cyberlink Corp.

Inventor： Ho-Chao Huang ,  Huan-Wen Hsiao ,  Chung-Yi Weng ,  Cheng-da Chung

IPC: G06T5/50 ,  G06K9/00

CPC classification number: G06T5/50 ,  G06K9/00281 ,  G06K9/00315 ,  G06T5/005 ,  G06T11/60 ,  G06T2207/10016 ,  G06T2207/20212 ,  G06T2207/30201

Abstract: Various embodiments are disclosed for image editing. A frame is obtained from a frame sequence depicting at least one individual, and facial characteristics in the frame are analyzed. A utilization score is assigned to the frame based on the detected facial characteristics, and a determination of whether to utilize the frame is made based on the utilization score. A completeness value is assigned, and a determination is made based on the completeness value of whether to repeat the steps above for an additional frame in the frame sequence based on the completeness value. Regions from the frames are combined to generate a composite image.

Abstract translation: 公开了用于图像编辑的各种实施例。 从描绘至少一个个体的帧序列获得帧，并且分析帧中的面部特征。 基于检测到的面部特征将利用分数分配给该帧，并且基于利用分数来确定是否利用该帧。 分配完整性值，并基于完整性值，基于是否对帧序列中的附加帧重复上述步骤的完整性来进行确定。 来自帧的区域被组合以生成合成图像。

公开(公告)号：US20140198945A1

公开(公告)日：2014-07-17

申请号：US13740376

申请日：2013-01-14

Applicant: CYBERLINK CORP.

Inventor： Huan-Wen Hsiao ,  Chung-Yi Weng

IPC: G06T7/20

CPC classification number: G06T7/20 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20096 ,  G06T2207/30196

Abstract: Disclosed are various embodiments for tracking an object shown as moving in a video. One embodiment is a method for tracking an object in a video that comprises tracking in a first temporal direction an object in a plurality of video frames and generating a first tracking result, evaluating the first tracking result corresponding to tracking of the object in the first temporal direction, and stopping tracking in the first temporal direction upon the occurrence of a predefined event, wherein the predefined event is based on an evaluated tracking result. The method further comprises obtaining data identifying an object outline of the object upon stopping the tracking in the first temporal direction, tracking in a second temporal direction the object based on the data identifying the object outline of the object to generate a second tracking result, and generating a refined tracking result based on at least on one of the first tracking result, the second tracking result, or a combination thereof.

Abstract translation: 公开了用于跟踪被显示为在视频中移动的对象的各种实施例。 一个实施例是用于跟踪视频中的对象的方法，其包括在第一时间方向上跟踪多个视频帧中的对象并生成第一跟踪结果，评估与第一时间中的对象的跟踪相对应的第一跟踪结果 方向，并且在发生预定义事件时在第一时间方向停止跟踪，其中预定事件基于所评估的跟踪结果。 该方法还包括：在停止第一时间方向的跟踪时，获取识别对象轮廓的数据，基于标识对象的对象轮廓的数据，在第二时间方向跟踪对象以产生第二跟踪结果，以及 基于第一跟踪结果，第二跟踪结果或其组合中的至少一个，生成精细跟踪结果。