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

US20070122001A1 Real-time Bayesian 3D pose tracking 有权
标题翻译：实时贝叶斯3D姿态跟踪
公开(公告)号：US20070122001A1
公开(公告)日：2007-05-31
申请号：US11290135
申请日：2005-11-30
申请人： Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
发明人： Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
IPC分类号： G06K9/00
CPC分类号： G06K9/00208 , G06K9/00241
摘要： Systems and methods are described for real-time Bayesian 3D pose tracking. In one implementation, exemplary systems and methods formulate key-frame based differential pose tracking in a probabilistic graphical model. An exemplary system receives live captured video as input and tracks a video object's 3D pose in real-time based on the graphical model. An exemplary Bayesian inter-frame motion inference technique simultaneously performs online point matching and pose estimation. This provides robust pose tracking because the relative pose estimate for a current frame is simultaneously estimated from two independent sources, from a key-frame pool and from the video frame preceding the current frame. Then, an exemplary online Bayesian frame fusion technique infers the current pose from the two independent sources, providing stable and drift-free tracking, even during agile motion, occlusion, scale change, and drastic illumination change of the tracked object.
摘要翻译：描述了实时贝叶斯3D姿态跟踪的系统和方法。在一个实现中，示例性系统和方法在概率图形模型中制定基于关键帧的差分姿态跟踪。示例性系统基于图形模型实时地接收实时捕获的视频作为输入并实时跟踪视频对象的3D姿态。示例性的贝叶斯帧间运动推理技术同时执行在线点匹配和姿态估计。这提供了鲁棒的姿势跟踪，因为当前帧的相对姿态估计是从两个独立的来源，从关键帧池和当前帧之前的视频帧同时估计的。然后，示例性的在线贝叶斯帧融合技术从两个独立的来源推测出当前姿态，即使在敏捷运动，闭塞，比例变化和被跟踪对象的剧烈照明改变的情况下，也提供稳定和无漂移的跟踪。

2. 发明申请

US20070216675A1 Digital Video Effects 有权
标题翻译：数码影像效果
公开(公告)号：US20070216675A1
公开(公告)日：2007-09-20
申请号：US11467859
申请日：2006-08-28
申请人： Jian Sun , Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
发明人： Jian Sun , Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
IPC分类号： H04N13/04 , G06T15/00
CPC分类号： G06T11/00
摘要： Digital video effects are described. In one aspect, a foreground object in a video stream is identified. The video stream comprises multiple image frames. The foreground object is modified by rendering a 3-dimensional (3-D) visual feature over the foreground object for presentation to a user in a modified video stream. Pose of the foreground object is tracked in 3-D space across respective ones of the image frames to identify when the foreground object changes position in respective ones of the image frames. Based on this pose tracking, aspect ratio of the 3-D visual feature is adaptively modified and rendered over the foreground object in corresponding image frames for presentation to the user in the modified video stream.
摘要翻译：描述数字视频效果。在一个方面，识别视频流中的前景对象。视频流包括多个图像帧。通过在前景对象上呈现三维（3-D）视觉特征来修改前景对象，以呈现给经修改的视频流中的用户。前景物体的姿态在相应的图像帧中的3-D空间中被跟踪，以识别前景对象何时改变相应图像帧中的位置。基于这种姿态跟踪，3-D视觉特征的宽高比被自适应地修改并在相应图像帧中的前景对象上呈现，以便在修改的视频流中呈现给用户。

3. 发明授权

US08026931B2 Digital video effects 有权
标题翻译：数字视频效果
公开(公告)号：US08026931B2
公开(公告)日：2011-09-27
申请号：US11467859
申请日：2006-08-28
申请人： Jian Sun , Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
发明人： Jian Sun , Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
IPC分类号： G09G5/00 , G06K9/34
CPC分类号： G06T11/00
摘要： Digital video effects are described. In one aspect, a foreground object in a video stream is identified. The video stream comprises multiple image frames. The foreground object is modified by rendering a 3-dimensional (3-D) visual feature over the foreground object for presentation to a user in a modified video stream. Pose of the foreground object is tracked in 3-D space across respective ones of the image frames to identify when the foreground object changes position in respective ones of the image frames. Based on this pose tracking, aspect ratio of the 3-D visual feature is adaptively modified and rendered over the foreground object in corresponding image frames for presentation to the user in the modified video stream.
摘要翻译：描述数字视频效果。在一个方面，识别视频流中的前景对象。视频流包括多个图像帧。通过在前景对象上呈现三维（3-D）视觉特征来修改前景对象，以呈现给经修改的视频流中的用户。前景物体的姿态在相应的图像帧中的3-D空间中被跟踪，以识别前景对象何时改变相应图像帧中的位置。基于这种姿态跟踪，3-D视觉特征的宽高比被自适应地修改并在相应图像帧中的前景对象上呈现，以便在修改的视频流中呈现给用户。

4. 发明授权

US07536030B2 Real-time Bayesian 3D pose tracking 有权
标题翻译：实时贝叶斯3D姿态跟踪
公开(公告)号：US07536030B2
公开(公告)日：2009-05-19
申请号：US11290135
申请日：2005-11-30
申请人： Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
发明人： Qiang Wang , Weiwei Zhang , Xiaoou Tang , Heung-Yeung Shum
IPC分类号： G06K9/00
CPC分类号： G06K9/00208 , G06K9/00241
摘要： Systems and methods are described for real-time Bayesian 3D pose tracking. In one implementation, exemplary systems and methods formulate key-frame based differential pose tracking in a probabilistic graphical model. An exemplary system receives live captured video as input and tracks a video object's 3D pose in real-time based on the graphical model. An exemplary Bayesian inter-frame motion inference technique simultaneously performs online point matching and pose estimation. This provides robust pose tracking because the relative pose estimate for a current frame is simultaneously estimated from two independent sources, from a key-frame pool and from the video frame preceding the current frame. Then, an exemplary online Bayesian frame fusion technique infers the current pose from the two independent sources, providing stable and drift-free tracking, even during agile motion, occlusion, scale change, and drastic illumination change of the tracked object.
摘要翻译：描述了实时贝叶斯3D姿态跟踪的系统和方法。在一个实现中，示例性系统和方法在概率图形模型中制定基于关键帧的差分姿态跟踪。示例性系统基于图形模型实时地接收实时捕获的视频作为输入并实时跟踪视频对象的3D姿态。示例性的贝叶斯帧间运动推理技术同时执行在线点匹配和姿态估计。这提供了鲁棒的姿势跟踪，因为当前帧的相对姿态估计是从两个独立的来源，从关键帧池和当前帧之前的视频帧同时估计的。然后，示例性的在线贝叶斯帧融合技术从两个独立的来源推测出当前姿态，即使在敏捷运动，闭塞，比例变化和跟踪对象的剧烈照明改变期间也能提供稳定和无漂移的跟踪。

5. 发明申请

US20070091085A1 Automatic 3D Face-Modeling From Video 有权
标题翻译：从视频自动3D面部建模
公开(公告)号：US20070091085A1
公开(公告)日：2007-04-26
申请号：US11465369
申请日：2006-08-17
申请人： Qiang Wang , Heung-Yeung Shum , Xiaoou Tang
发明人： Qiang Wang , Heung-Yeung Shum , Xiaoou Tang
IPC分类号： G06T17/00
CPC分类号： G06T17/20 , G06T7/55 , G06T2200/08
摘要： Systems and methods perform automatic 3D face modeling. In one implementation, a brief video clip of a user's head turning from front to side provides enough input for automatically achieving a model that includes 2D feature matches, 3D head pose, 3D face shape, and facial textures. The video clip of the user may be of poor quality. In a two layer iterative method, the video clip is divided into segments. Flow-based feature estimation and model-based feature refinement are applied recursively to each segment. Then the feature estimation and refinement are iteratively applied across all the segments. The entire modeling method is automatic and the two layer iterative method provides speed and efficiency, especially when sparse bundle adjustment is applied to boost efficiency.
摘要翻译：系统和方法执行自动3D脸部建模。在一个实现中，用户头部从前到后的简短视频剪辑提供足够的输入，用于自动实现包括2D特征匹配，3D头部姿势，3D脸部形状和面部纹理的模型。用户的视频剪辑可能质量差。在两层迭代方法中，视频剪辑被划分成段。基于流的特征估计和基于模型的特征细化被递归地应用于每个段。然后，特征估计和细化被迭代地应用于所有段。整个建模方法是自动的，两层迭代法提供了速度和效率，特别是当稀疏束调整应用于提高效率时。

6. 发明授权

US07755619B2 Automatic 3D face-modeling from video 有权
标题翻译：从视频自动3D面部建模
公开(公告)号：US07755619B2
公开(公告)日：2010-07-13
申请号：US11465369
申请日：2006-08-17
申请人： Qiang Wang , Heung-Yeung Shum , Xiaoou Tang
发明人： Qiang Wang , Heung-Yeung Shum , Xiaoou Tang
IPC分类号： G06T15/00
CPC分类号： G06T17/20 , G06T7/55 , G06T2200/08
摘要： Systems and methods perform automatic 3D face modeling. In one implementation, a brief video clip of a user's head turning from front to side provides enough input for automatically achieving a model that includes 2D feature matches, 3D head pose, 3D face shape, and facial textures. The video clip of the user may be of poor quality. In a two layer iterative method, the video clip is divided into segments. Flow-based feature estimation and model-based feature refinement are applied recursively to each segment. Then the feature estimation and refinement are iteratively applied across all the segments. The entire modeling method is automatic and the two layer iterative method provides speed and efficiency, especially when sparse bundle adjustment is applied to boost efficiency.
摘要翻译：系统和方法执行自动3D脸部建模。在一个实现中，用户头部从前到后的简短视频剪辑提供足够的输入，用于自动实现包括2D特征匹配，3D头部姿势，3D脸部形状和面部纹理的模型。用户的视频剪辑可能质量差。在两层迭代方法中，视频剪辑被划分成段。基于流的特征估计和基于模型的特征细化被递归地应用于每个段。然后，特征估计和细化被迭代地应用于所有段。整个建模方法是自动的，两层迭代法提供了速度和效率，特别是当稀疏束调整应用于提高效率时。

7. 外观设计

USD962692S1 Chair back 有权
公开(公告)号：USD962692S1
公开(公告)日：2022-09-06
申请号：US29790419
申请日：2021-11-25
申请人： Qiang Wang
设计人： Qiang Wang

8. 外观设计

USD935465S1 Docking unit for computer 有权
公开(公告)号：USD935465S1
公开(公告)日：2021-11-09
申请号：US29714765
申请日：2019-11-26
申请人： Qiang Wang
设计人： Qiang Wang

9. 发明申请

US20210303819A1 FAST SIGNATURE SCAN 有权
公开(公告)号：US20210303819A1
公开(公告)日：2021-09-30
申请号：US17343694
申请日：2021-06-09
申请人： Qiang Wang
发明人： Qiang Wang
IPC分类号： G06K9/00 , G06F16/28 , G06F16/903 , G06F21/56 , G06K9/62 , H04L29/06
摘要： Systems and methods for scanning signatures in a string field. In one implementation, the invention provides a method for signature scanning. The method includes receiving a particular string field, scanning the particular string field for a plurality of signatures using a larger scan step size, scanning the particular string field for the remaining signatures that are shorter than what can be scanned by the larger scan step size separately either using the same scanning method but a smaller scan step size or using a different scan method and the same or a smaller scan step size, and outputting any identified signatures in the particular string field.

10. 发明申请

US20210196211A9 METHODS AND APPARATUS FOR IMPROVING THE IMAGE RESOLUTION AND SENSITIVITY OF WHOLE-BODY POSITRON EMISSION TOMOGRAPHY (PET) IMAGING 有权
公开(公告)号：US20210196211A9
公开(公告)日：2021-07-01
申请号：US16697722
申请日：2019-11-27
申请人： Yuan-Chuan Tai , Joseph O'Sullivan , Ke Li , Qiang Wang
发明人： Yuan-Chuan Tai , Joseph O'Sullivan , Ke Li , Qiang Wang
IPC分类号： A61B6/03 , G01T1/29 , A61B6/00
摘要： A positron emission tomography (PET) technique that can enhance the image resolution and system sensitivity of a clinical PET/CT scanner for imaging a whole body or a target region of a subject is provided. The system includes a detector array and a detector panel. The detector array includes an array of gamma ray detectors defining a field of view of a scanner and configured to detect at least one coincidence event. The detector panel includes an array of gamma ray detectors having a higher intrinsic spatial resolution than the detector array and positioned in closer proximity to a patient table than the detector array. The detector panel is positioned outside the field of view defined by the detector array during at least a portion of scanning by the PET system. The detector panel is configured to detect at least one coincidence event in cooperation with the detector array. The control unit is configured to control the detector array, the detector panel, and the patient bed to operate in cooperation with each other.

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