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. 发明授权

US07702489B2 Method and apparatus for fast machine learning using probability maps and fourier transforms 有权
标题翻译：使用概率图和傅立叶变换进行快速机器学习的方法和装置
公开(公告)号：US07702489B2
公开(公告)日：2010-04-20
申请号：US10286142
申请日：2002-11-01
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06F7/60 , G06F17/10
CPC分类号： G06K9/6255
摘要： The present invention provides a method of constructing recognition models. Under the method, a set of probabilities is estimated for values of a hidden variable. A Fourier transform is determined for the set of probabilities and is used to determine a Fourier transform of an estimated prototype pattern. The inverse Fourier transform is then determined for the Fourier transform of the estimated prototype pattern to form an estimated prototype pattern.
摘要翻译：本发明提供一种构建识别模型的方法。在该方法下，对一个隐含变量的值估计一组概率。对于概率集合确定傅里叶变换，并且用于确定估计原型图案的傅里叶变换。然后，对于所估计的原型图案的傅立叶变换来确定逆傅立叶变换以形成估计的原型图案。

2. 发明授权

US07113185B2 System and method for automatically learning flexible sprites in video layers 有权
标题翻译：在视频层自动学习灵活精灵的系统和方法
公开(公告)号：US07113185B2
公开(公告)日：2006-09-26
申请号：US10294211
申请日：2002-11-14
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06T17/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

3. 发明授权

US07680353B2 Stabilization of objects within a video sequence 有权
标题翻译：稳定视频序列中的对象
公开(公告)号：US07680353B2
公开(公告)日：2010-03-16
申请号：US11534646
申请日：2006-09-23
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06K9/40
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

4. 发明授权

US07940264B2 Generative models for constructing panoramas from an image sequence 有权
标题翻译：用于从图像序列构建全景图的生成模型
公开(公告)号：US07940264B2
公开(公告)日：2011-05-10
申请号：US12794765
申请日：2010-06-06
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06T17/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

5. 发明授权

US07750904B2 Modeling variable illumination in an image sequence 有权
标题翻译：在图像序列中建模可变照明
公开(公告)号：US07750904B2
公开(公告)日：2010-07-06
申请号：US11534649
申请日：2006-09-23
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06T17/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

6. 发明授权

US07750903B2 Modeling reflections within an image sequence 有权
标题翻译：建模图像序列中的反射
公开(公告)号：US07750903B2
公开(公告)日：2010-07-06
申请号：US11534647
申请日：2006-09-23
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06T17/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

7. 发明申请

US20100238266A1 GENERATIVE MODELS FOR CONSTRUCTING PANORAMAS FROM AN IMAGE SEQUENCE 有权
标题翻译：从图像序列构建全景的一般模型
公开(公告)号：US20100238266A1
公开(公告)日：2010-09-23
申请号：US12794765
申请日：2010-06-06
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： H04N7/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

8. 发明授权

US07982738B2 Interactive montages of sprites for indexing and summarizing video 有权
标题翻译：用于索引和总结视频的精灵互动蒙太奇
公开(公告)号：US07982738B2
公开(公告)日：2011-07-19
申请号：US11004760
申请日：2004-12-01
申请人： Nebojsa Jojic , Chris Pal
发明人： Nebojsa Jojic , Chris Pal
IPC分类号： G06T13/00
CPC分类号： G06F17/30811 , G06F17/30843 , G06F17/30852 , G11B27/034 , G11B27/28 , G11B27/34 , H04N21/44008 , H04N21/44029 , H04N21/45452 , H04N21/8193 , H04N21/8549 , Y10S345/95
摘要： A “Video Browser” provides interactive browsing of unique events occurring within an overall video recording. In particular, the Video Browser processes the video to generate a set of video sprites representing unique events occurring within the overall period of the video. These unique events include, for example, motion events, security events, or other predefined event types, occurring within all or part of the total period covered by the video. Once the video has been processed to identify the sprites, the sprites are then arranged over a background image extracted from the video to create an interactive static video montage. The interactive video montage illustrates all events occurring within the video in a single static frame. User selection of sprites within the montage causes either playback of a portion of the video in which the selected sprites were identified, or concurrent playback of the selected sprites within a dynamic video montage.
摘要翻译： “视频浏览器”提供了在整个视频录制中发生的独特事件的交互式浏览。特别地，视频浏览器处理视频以生成表示在视频的整个周期内发生的唯一事件的一组视频精灵。这些独特的事件包括例如运动事件，安全事件或其他预定事件类型，发生在视频所涵盖的整个周期的全部或部分内。一旦视频被处理以识别精灵，则将精灵布置在从视频提取的背景图像上，以创建交互式静态视频蒙太奇。交互式视频蒙太奇在单个静态帧中说明视频内发生的所有事件。蒙太奇内的精灵的用户选择导致播放所选择的精灵被识别的视频的一部分，或动态视频蒙太奇中所选精灵的并发回放。

9. 发明授权

US07978906B2 Capturing long-range correlations in patch models 有权
标题翻译：在补丁模型中捕获长距离相关性
公开(公告)号：US07978906B2
公开(公告)日：2011-07-12
申请号：US11763136
申请日：2007-06-14
申请人： Nebojsa Jojic , Vincent Cheung
发明人： Nebojsa Jojic , Vincent Cheung
IPC分类号： G06K9/62
CPC分类号： G06K9/469 , G06K9/6255
摘要： Systems and methodologies for modeling data in accordance with one or more embodiments disclosed herein are operable to receive input data, create data patches from the input data, obtain long-range correlations between the data patches, and model the input data as a patch model based at least in part on the data patches and the long-range correlations. Various learning algorithms are additionally provided for refining the patch model created in accordance with one or more embodiments disclosed herein. Further, systems and methodologies for synthesizing a patch model created in accordance with various aspects of the present invention with a set of test data to perform a transformation represented by the patch model on the test data are provided.
摘要翻译：根据本文公开的一个或多个实施例的用于建模数据的系统和方法可操作用于接收输入数据，从输入数据创建数据补丁，获得数据补丁之间的长距离相关性，并将输入数据建模为基于补丁模型至少部分地基于数据补丁和长距离相关性。另外提供了各种学习算法，用于细化根据本文公开的一个或多个实施例创建的贴片模型。此外，提供了用于根据本发明的各个方面创建的用于合成测试数据的一组测试数据来进行由测试数据上的补丁模型表示的变换的补丁模型的系统和方法。

10. 发明授权

US07657102B2 System and method for fast on-line learning of transformed hidden Markov models 有权
标题翻译：用于快速在线学习变换隐马尔科夫模型的系统和方法
公开(公告)号：US07657102B2
公开(公告)日：2010-02-02
申请号：US10649382
申请日：2003-08-27
申请人： Nebojsa Jojic , Nemanja Petrovic
发明人： Nebojsa Jojic , Nemanja Petrovic
IPC分类号： G06K9/62 , G10L15/06
CPC分类号： G11B27/28 , G06K9/00711 , G06K9/6297
摘要： A fast variational on-line learning technique for training a transformed hidden Markov model. A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, once the model has been initialized, an expectation-maximization (“EM”) algorithm is used to learn the one or more object class models, so that the video sequence has high marginal probability under the model. In the expectation step (the “E-Step”), the model parameters are assumed to be correct, and for an input image, probabilistic inference is used to fill in the values of the unobserved or hidden variables, e.g., the object class and appearance. In one embodiment of the invention, a Viterbi algorithm and a latent image is employed for this purpose. In the maximization step (the “M-Step”), the model parameters are adjusted using the values of the unobserved variables calculated in the previous E-step.
摘要翻译：一种快速变化的在线学习技术，用于训练变换后的隐马尔可夫模型。提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，一旦模型被初始化，使用期望最大化（“EM”）算法来学习一个或多个对象类模型，使得视频序列在该模型下具有高边际概率。在期望步骤（“E步骤”）中，假设模型参数是正确的，对于输入图像，使用概率推断来填充未观察或隐藏变量的值，例如对象类和出现。在本发明的一个实施例中，为此目的采用维特比算法和潜像。在最大化步骤（“M步骤”）中，使用在先前E步骤中计算的未观察到的变量的值来调整模型参数。

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