专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20150063786A1 Systems and Methods for Object Tracking Based on User Refinement Input 有权
标题翻译：基于用户优化输入的对象跟踪系统与方法
公开(公告)号：US20150063786A1
公开(公告)日：2015-03-05
申请号：US14337509
申请日：2014-07-22
申请人： Cyberlink Corp.
发明人： Chih-Chao Ma , Ho-Chao Huang
IPC分类号： G11B27/031 , G06K9/46 , G06F3/0484 , G06K9/00
CPC分类号： G06F3/04845 , G06F3/0488 , G06K9/00711 , G06K9/48
摘要： A method for tracking an object in a plurality of frames includes obtaining a contour of an object in a frame. For each remaining frame among the plurality of frames, the following steps are performed. A probability map generator generates a plurality of probability maps containing probability values for one or more pixels for a current frame. A contour is estimated for the current frame based on the plurality of probability maps. User input is obtained for refining the estimated contour. Based on the user input, one or more local regions to be added and/or removed are identified and recorded in a local region list. The local region list is maintained and updated during the tracking process and is used together with the probability map generator.
摘要翻译：用于跟踪多个帧中的对象的方法包括获得帧中的对象的轮廓。对于多个帧中的每个剩余帧，执行以下步骤。概率图生成器生成包含当前帧的一个或多个像素的概率值的多个概率图。基于多个概率图对当前帧估计轮廓。获得用户输入用于改进估计轮廓。基于用户输入，将要添加和/或移除的一个或多个局部区域被识别并记录在本地区域列表中。在跟踪过程中维护和更新本地区域列表，并与概率图生成器一起使用。

2. 发明申请

US20140219580A1 Systems and Methods for Performing Object Selection 有权
标题翻译：执行对象选择的系统和方法
公开(公告)号：US20140219580A1
公开(公告)日：2014-08-07
申请号：US13756974
申请日：2013-02-01
申请人： CYBERLINK CORP.
发明人： Wei-Hsin Tseng , Ho-Chao Huang , Chih-Chao Ma
IPC分类号： G06T5/00
CPC分类号： G06F3/048 , G06F3/04845 , G06T7/11 , G06T11/60 , G06T2207/20096
摘要： Various embodiments are disclosed for selecting a region of interest within an object. One embodiment is a method for editing a digital image in an image editing device. The method comprises obtaining a first position within a digital image, the first position being specified by a pointer. The method further comprises defining a first selection region based on the first position and obtaining a second position within the digital image, the second position being specified by the pointer. The method further comprises determining movement of the pointer between the first position and the second position and predicting future movement by the pointer based on the determined movement. Based on the determined movement and the predicted future movement, the first selection region is expanded to define a second selection region.
摘要翻译：公开了用于选择对象内的感兴趣区域的各种实施例。一个实施例是用于在图像编辑装置中编辑数字图像的方法。该方法包括获得数字图像内的第一位置，第一位置由指针指定。该方法还包括基于第一位置定义第一选择区域并获得数字图像内的第二位置，第二位置由指针指定。该方法还包括确定指针在第一位置和第二位置之间的移动，并且基于所确定的移动来预测指针的未来移动。基于确定的运动和预测的未来运动，第一选择区域被扩展以限定第二选择区域。

3. 发明申请

US20140133701A1 Systems and Methods for Tracking Objects 有权
标题翻译：跟踪对象的系统和方法
公开(公告)号：US20140133701A1
公开(公告)日：2014-05-15
申请号：US14071899
申请日：2013-11-05
申请人： Cyberlink Corp.
发明人： Chih-Chao Ma
IPC分类号： G06T7/00
CPC分类号： G06T7/2033 , G06T7/246
摘要： Various embodiments are disclosed for performing object tracking. One embodiment is a method for tracking an object in a plurality of frames, comprising obtaining a reference contour of an object in a reference frame and estimating, for a current frame after the reference frame, a contour of the object. The method further comprises comparing the reference contour with the estimated contour and determining at least one local region of the reference contour in the reference frame based on a difference between the reference contour and the estimated contour. Based on the difference, at least one corresponding region of the current frame is determined. The method further comprises computing a degree of similarity between the at least one corresponding region in the current frame and the at least one local region in the reference frame, adjusting the estimated contour in the current frame according to the degree of similarity, and designating the current frame as a new reference frame and a frame after the new reference as a new current frame.
摘要翻译：公开了用于执行对象跟踪的各种实施例。一个实施例是用于跟踪多个帧中的对象的方法，包括获得参考帧中的对象的参考轮廓，并且对于参考帧之后的当前帧估计对象的轮廓。该方法还包括将参考轮廓与估计轮廓进行比较，并且基于参考轮廓和估计轮廓之间的差异来确定参考系中参考轮廓的至少一个局部区域。基于该差异，确定当前帧的至少一个对应区域。该方法还包括计算当前帧中的至少一个对应区域和参考帧中的至少一个局部区域之间的相似度，根据相似度调整当前帧中的估计轮廓，并指定当前帧作为新的参考帧，新参考后的帧作为新的当前帧。

4. 发明申请

US20140146997A1 Systems and Methods for Tracking Objects 有权
标题翻译：跟踪对象的系统和方法
公开(公告)号：US20140146997A1
公开(公告)日：2014-05-29
申请号：US13684451
申请日：2012-11-23
申请人： CYBERLINK CORP.
发明人： Ming-Hsiu Chang , Chih-Chao Ma
IPC分类号： G06T7/20
CPC分类号： G06T7/2046 , G06T7/251 , G06T7/277 , G06T2207/10016 , G06T2207/20076
摘要： Various embodiments are disclosed for performing object tracking. One embodiment is a system for tracking an object in a plurality of frames, comprising a probability map generator configured to generate a probability map by estimating probability values of pixels in the frame, wherein the probability of each pixel corresponds to a likelihood of the pixel being located within the object. The system further comprises a contour model generator configured to identify a contour model of the object based on a temporal prediction method, a contour weighting map generator configured to derive a contour weighting map based on thickness characteristics of the contour model, a tracking refinement module configured to refine the probability map according to weight values specified in the contour weighting map, and an object tracker configured to track a location of the object within the plurality of frames based on the refined probability map.
摘要翻译：公开了用于执行对象跟踪的各种实施例。一个实施例是用于跟踪多个帧中的对象的系统，包括概率图生成器，其被配置为通过估计帧中的像素的概率值来生成概率图，其中每个像素的概率对应于像素的可能性位于对象内。该系统还包括轮廓模型发生器，其被配置为基于时间预测方法来识别对象的轮廓模型;轮廓加权映射发生器，被配置为基于轮廓模型的厚度特征导出轮廓加权图;跟踪细化模块，根据轮廓加权图中指定的权重值来细化概率图，以及对象跟踪器，被配置为基于精确的概率图来跟踪多个帧内的对象的位置。

5. 发明授权

US09075494B2 Systems and methods for performing object selection 有权
标题翻译：用于执行对象选择的系统和方法
公开(公告)号：US09075494B2
公开(公告)日：2015-07-07
申请号：US13756974
申请日：2013-02-01
申请人： Cyberlink Corp.
发明人： Wei-Hsin Tseng , Ho-Chao Huang , Chih-Chao Ma
IPC分类号： G06T5/00 , G06F3/048 , G06T11/60 , G06T7/00
CPC分类号： G06F3/048 , G06F3/04845 , G06T7/11 , G06T11/60 , G06T2207/20096
摘要： Various embodiments are disclosed for selecting a region of interest within an object. One embodiment is a method for editing a digital image in an image editing device. The method comprises obtaining a first position within a digital image, the first position being specified by a pointer. The method further comprises defining a first selection region based on the first position and obtaining a second position within the digital image, the second position being specified by the pointer. The method further comprises determining movement of the pointer between the first position and the second position and predicting future movement by the pointer based on the determined movement. Based on the determined movement and the predicted future movement, the first selection region is expanded to define a second selection region.
摘要翻译：公开了用于选择对象内的感兴趣区域的各种实施例。一个实施例是用于在图像编辑装置中编辑数字图像的方法。该方法包括获得数字图像内的第一位置，第一位置由指针指定。该方法还包括基于第一位置定义第一选择区域并获得数字图像内的第二位置，第二位置由指针指定。该方法还包括确定指针在第一位置和第二位置之间的移动，并且基于所确定的移动来预测指针的未来移动。基于确定的运动和预测的未来运动，第一选择区域被扩展以限定第二选择区域。

6. 发明授权

US08971575B2 Systems and methods for tracking objects 有权
标题翻译：跟踪对象的系统和方法
公开(公告)号：US08971575B2
公开(公告)日：2015-03-03
申请号：US13684451
申请日：2012-11-23
申请人： Cyberlink Corp.
发明人： Ming-Hsiu Chang , Chih-Chao Ma
IPC分类号： G06K9/00 , G06T7/20
CPC分类号： G06T7/2046 , G06T7/251 , G06T7/277 , G06T2207/10016 , G06T2207/20076
摘要： Various embodiments are disclosed for performing object tracking. One embodiment is a system for tracking an object in a plurality of frames, comprising a probability map generator configured to generate a probability map by estimating probability values of pixels in the frame, wherein the probability of each pixel corresponds to a likelihood of the pixel being located within the object. The system further comprises a contour model generator configured to identify a contour model of the object based on a temporal prediction method, a contour weighting map generator configured to derive a contour weighting map based on thickness characteristics of the contour model, a tracking refinement module configured to refine the probability map according to weight values specified in the contour weighting map, and an object tracker configured to track a location of the object within the plurality of frames based on the refined probability map.
摘要翻译：公开了用于执行对象跟踪的各种实施例。一个实施例是用于跟踪多个帧中的对象的系统，包括概率图生成器，其被配置为通过估计帧中的像素的概率值来生成概率图，其中每个像素的概率对应于像素的可能性位于对象内。该系统还包括轮廓模型发生器，其被配置为基于时间预测方法来识别对象的轮廓模型;轮廓加权映射发生器，被配置为基于轮廓模型的厚度特征导出轮廓加权图;跟踪细化模块，根据轮廓加权图中指定的权重值来细化概率图，以及对象跟踪器，被配置为基于精确的概率图来跟踪多个帧内的对象的位置。

7. 发明授权

US09389767B2 Systems and methods for object tracking based on user refinement input 有权
标题翻译：基于用户细化输入的对象跟踪系统和方法
公开(公告)号：US09389767B2
公开(公告)日：2016-07-12
申请号：US14337509
申请日：2014-07-22
申请人： Cyberlink Corp.
发明人： Chih-Chao Ma , Ho-Chao Huang
IPC分类号： G11B27/00 , H04N5/93 , G06F3/0484 , G06F3/0488 , G06K9/00 , G06K9/48
CPC分类号： G06F3/04845 , G06F3/0488 , G06K9/00711 , G06K9/48
摘要： A method for tracking an object in a plurality of frames includes obtaining a contour of an object in a frame. For each remaining frame among the plurality of frames, the following steps are performed. A probability map generator generates a plurality of probability maps containing probability values for one or more pixels for a current frame. A contour is estimated for the current frame based on the plurality of probability maps. User input is obtained for refining the estimated contour. Based on the user input, one or more local regions to be added and/or removed are identified and recorded in a local region list. The local region list is maintained and updated during the tracking process and is used together with the probability map generator.
摘要翻译：用于跟踪多个帧中的对象的方法包括获得帧中的对象的轮廓。对于多个帧中的每个剩余帧，执行以下步骤。概率图生成器生成包含当前帧的一个或多个像素的概率值的多个概率图。基于多个概率图对当前帧估计轮廓。获得用户输入用于改进估计轮廓。基于用户输入，将要添加和/或移除的一个或多个局部区域被识别并记录在本地区域列表中。在跟踪过程中维护和更新本地区域列表，并与概率图生成器一起使用。

8. 发明授权

US09299159B2 Systems and methods for tracking objects 有权
标题翻译：跟踪对象的系统和方法
公开(公告)号：US09299159B2
公开(公告)日：2016-03-29
申请号：US14071899
申请日：2013-11-05
申请人： Cyberlink Corp.
发明人： Chih-Chao Ma
IPC分类号： G06K9/00 , G06T7/20
CPC分类号： G06T7/2033 , G06T7/246
摘要： Various embodiments are disclosed for performing object tracking. One embodiment is a method for tracking an object in a plurality of frames, comprising obtaining a reference contour of an object in a reference frame and estimating, for a current frame after the reference frame, a contour of the object. The method further comprises comparing the reference contour with the estimated contour and determining at least one local region of the reference contour in the reference frame based on a difference between the reference contour and the estimated contour. Based on the difference, at least one corresponding region of the current frame is determined. The method further comprises computing a degree of similarity between the at least one corresponding region in the current frame and the at least one local region in the reference frame, adjusting the estimated contour in the current frame according to the degree of similarity, and designating the current frame as a new reference frame and a frame after the new reference as a new current frame.
摘要翻译：公开了用于执行对象跟踪的各种实施例。一个实施例是用于跟踪多个帧中的对象的方法，包括获得参考帧中的对象的参考轮廓，并且对于参考帧之后的当前帧估计对象的轮廓。该方法还包括将参考轮廓与估计轮廓进行比较，并且基于参考轮廓和估计轮廓之间的差异来确定参考系中参考轮廓的至少一个局部区域。基于该差异，确定当前帧的至少一个对应区域。该方法还包括计算当前帧中的至少一个对应区域和参考帧中的至少一个局部区域之间的相似度，根据相似度调整当前帧中的估计轮廓，并指定当前帧作为新的参考帧，新参考后的帧作为新的当前帧。

9. 发明申请

US20140270412A1 LIVENESS DETECTION SYSTEM BASED ON FACE BEHAVIOR 审中-公开
标题翻译：基于面部行为的生物检测系统
公开(公告)号：US20140270412A1
公开(公告)日：2014-09-18
申请号：US14289872
申请日：2014-05-29
申请人： Cyberlink Corp.
发明人： Chih-Chao Ma , Yi-Hsin Liu
IPC分类号： G06K9/00
CPC分类号： G06K9/00261 , G06K9/00221 , G06K9/00906
摘要： A liveness detection method comprising: receiving plural pictures of a video stream comprising a face and an adjacent background; determining motion of the face and the background, the motion determined over the plural pictures; comparing the motion between the face and the background; and determining whether the face corresponds to an actual, live user or an image of the user based on the comparison, the determinations performed by a processor.
摘要翻译：一种活力检测方法，包括：接收包括脸部和相邻背景的视频流的多个图像; 确定脸部和背景的运动，确定在多个图像上的运动; 比较脸部和背景之间的运动; 以及基于所述比较来确定所述面部是否对应于所述用户的实际，实时用户或图像，所述确定由处理器执行。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式