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

US06954544B2 Visual motion analysis method for detecting arbitrary numbers of moving objects in image sequences 失效
标题翻译：用于检测图像序列中移动物体的任意数目的视觉运动分析方法
公开(公告)号：US06954544B2
公开(公告)日：2005-10-11
申请号：US10155815
申请日：2002-05-23
申请人： Allan D. Jepson , David J. Fleet , Michael J. Black
发明人： Allan D. Jepson , David J. Fleet , Michael J. Black
IPC分类号： G06T7/20 , G06K9/00
CPC分类号： G06K9/32 , G06T7/215 , G06T7/251 , G06T2207/10016 , G06T2207/30196
摘要： A visual motion analysis method that uses multiple layered global motion models to both detect and reliably track an arbitrary number of moving objects appearing in image sequences. Each global model includes a background layer and one or more foreground “polybones”, each foreground polybone including a parametric shape model, an appearance model, and a motion model describing an associated moving object. Each polybone includes an exclusive spatial support region and a probabilistic boundary region, and is assigned an explicit depth ordering. Multiple global models having different numbers of layers, depth orderings, motions, etc., corresponding to detected objects are generated, refined using, for example, an EM algorithm, and then ranked/compared. Initial guesses for the model parameters are drawn from a proposal distribution over the set of potential (likely) models. Bayesian model selection is used to compare/rank the different models, and models having relatively high posterior probability are retained for subsequent analysis.
摘要翻译：一种视觉运动分析方法，其使用多层全局运动模型来检测和可靠地跟踪出现在图像序列中的任意数量的移动物体。每个全局模型包括背景层和一个或多个前景“多边形”，每个前景多边形包括参数形状模型，外观模型和描述相关联的运动对象的运动模型。每个多骨架包括独占空间支持区域和概率边界区域，并被分配明确的深度排序。使用例如EM算法进行精细化，然后进行排序/比较，生成与被检测对象对应的具有不同层数，深度顺序，动作等的多个全局模型。模型参数的初始猜测是从一组潜在（可能）模型中的提案分布中得出的。贝叶斯模型选择用于比较/排列不同模型，并且保留具有较高后验概率的模型用于后续分析。

2. 发明授权

US07058205B2 Robust, on-line, view-based appearance models for visual motion analysis and visual tracking 失效
公开(公告)号：US07058205B2
公开(公告)日：2006-06-06
申请号：US10016659
申请日：2001-12-07
申请人： Allan D. Jepson , David J. Fleet , Thomas F. El-Maraghi
发明人： Allan D. Jepson , David J. Fleet , Thomas F. El-Maraghi
IPC分类号： G06K9/00
CPC分类号： G06K9/00228 , G06T7/251 , G06T7/277 , G06T2207/10016 , G06T2207/30201
摘要： A robust, adaptive, appearance model is disclosed that includes both a stable model component, learned over a long time course, and a transient component, learned over a relatively short time course (e.g., a 2-frame motion component and/or an outlier processing component). An on-line EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. The appearance model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions, or variations in 3D pose.

3. 发明授权

US07093202B2 Method and system for interpreting imprecise object selection paths 有权
公开(公告)号：US07093202B2
公开(公告)日：2006-08-15
申请号：US10104523
申请日：2002-03-22
申请人： Eric Saund , Edward Lank , David J. Fleet , James V. Mahoney , Daniel L. Larner , Thomas P. Moran
发明人： Eric Saund , Edward Lank , David J. Fleet , James V. Mahoney , Daniel L. Larner , Thomas P. Moran
IPC分类号： G06F3/00 , G06T11/20
CPC分类号： G06F3/0481
摘要： A graphical input and display system having a user interface for selecting and creating image object elements includes input devices permitting a user to manipulate elements of electronic images. A processor, connected to the system, receives requests for various image object selection operations and also accesses a memory structure. The system memory structure includes a user interaction module, which allows a user to select image objects, an image object selection module for interpreting imprecise image object selection paths, and data memory.

4. 发明授权

US5949055A Automatic geometric image transformations using embedded signals 失效
标题翻译：使用嵌入式信号的自动几何图像变换
公开(公告)号：US5949055A
公开(公告)日：1999-09-07
申请号：US956839
申请日：1997-10-23
申请人： David J. Fleet , David J. Heeger , Todd A. Cass , David L. Hecht
发明人： David J. Fleet , David J. Heeger , Todd A. Cass , David L. Hecht
IPC分类号： G06T1/00 , H04N1/32 , G06K7/12
CPC分类号： G06T1/0028 , G06T1/0064 , H04N1/32203 , H04N1/32208 , H04N1/32229 , H04N1/32309 , G06T2201/0051 , G06T2201/0083 , G06T2201/0202 , G06T2201/0601 , H04N2201/3233 , H04N2201/327
摘要： An acquired (e.g., scanned) image contains an imperceptible periodic signal component (e.g., a sinusoid), decoding of which can be used to automatically determine a linear geometric relationship between the acquired image and the original image in which the signal was embedded, without having the original image available during the decoding process. This known geometric relationship allows for linear geometric properties of the acquired image, such as alignment and scaling, to be automatically matched with those of the original image so that the acquired image may be automatically oriented and scaled to the size of the original image. The embedded periodic signals produce a distinct pattern of local peak power concentrations in a spatial frequency amplitude spectrum of the acquired image. Using geometric constraint information about the embedded signals when the signals were originally embedded in the image, the locations and spatial frequencies of the signals are decoded from the image, providing a linear mapping between the peak power concentrations of the acquired and original image spatial frequency amplitude spectra. This linear mapping can be used to compute the linear geometric relationship between the two images. In an illustrated embodiment, the acquired image contains a set of sinusoidal signals that act as a grid. Decoding of the sinusoids does not require the original image, only information about the predetermined geometric relationship of the embedded sinusoids.
摘要翻译：获取的（例如，扫描的）图像包含不可察觉的周期性信号分量（例如，正弦曲线），其解码可用于自动确定所获取的图像与其中嵌入信号的原始图像之间的线性几何关系，而没有在解码过程中可以获得原始图像。这种已知的几何关系允许所获取的图像的线性几何属性（例如对准和缩放）自动与原始图像的几何属性匹配，使得所获取的图像可以被自动定向并且缩放到原始图像的尺寸。嵌入的周期信号在所获取的图像的空间频率幅度谱中产生局部峰值功率浓度的不同图案。当信号最初嵌入到图像中时，使用关于嵌入信号的几何约束信息，从图像中解码信号的位置和空间频率，从而提供所获取的和原始图像空间频率幅度的峰值功率浓度之间的线性映射光谱。该线性映射可用于计算两个图像之间的线性几何关系。在所示实施例中，所获取的图像包含用作网格的一组正弦信号。正弦曲线的解码不需要原始图像，只有关于嵌入的正弦曲线的预定几何关系的信息。

5. 发明授权

US06903751B2 System and method for editing electronic images 有权
标题翻译：用于编辑电子图像的系统和方法
公开(公告)号：US06903751B2
公开(公告)日：2005-06-07
申请号：US10104805
申请日：2002-03-22
申请人： Eric Saund , Thomas P. Moran , Daniel L. Larner , James V. Mahoney , David J. Fleet , Ashok C. Popat
发明人： Eric Saund , Thomas P. Moran , Daniel L. Larner , James V. Mahoney , David J. Fleet , Ashok C. Popat
IPC分类号： B41J5/30 , G06F3/12 , G06T11/60 , G06T11/80 , G09G5/00 , H04N1/387
CPC分类号： G06T11/60
摘要： A graphical input and display system for creating and manipulating electronic images includes input devices permitting a user to manipulate elements of electronic images received from various image input sources. A processor, connected to the system, receives requests for various image editing operations and also accesses a memory structure. The system memory structure includes a user interaction module, which allows a user to enter new image material or select and modify existing image material to form primary image objects, as well as a grouping module, which maintains an unrestricted grouping structure, an output module, and data memory.
摘要翻译：用于创建和操纵电子图像的图形输入和显示系统包括允许用户操纵从各种图像输入源接收的电子图像的元素的输入装置。连接到系统的处理器接收对各种图像编辑操作的请求，并且还访问存储器结构。系统存储器结构包括用户交互模块，其允许用户输入新的图像材料或选择和修改现有图像材料以形成主要图像对象，以及分组模块，其维持非限制性分组结构，输出模块，和数据存储器。

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