公开(公告)号：US06721450B2

公开(公告)日：2004-04-13

申请号：US10357974

申请日：2003-02-04

Applicant: Allen Robert Tannenbaum ,  Anthony Joseph Yezzi, Jr.

Inventor： Allen Robert Tannenbaum ,  Anthony Joseph Yezzi, Jr.

IPC: G06K934

CPC classification number: G06T7/64 ,  G06T7/12 ,  G06T2207/10088 ,  G06T2207/30016 ,  G06T2207/30048

Abstract: A technique for analyzing images for a feature of interest includes generating gradients for a characteristic of an image, such as pixel intensity value, initiating a candidate boundary, and evolving the candidate boundary to the feature boundary. The gradients may be calculated at the outset and referred to through iterative steps in expansion of the candidate boundary to improve the computational efficiency of the processing. The candidate boundary is evolved, either inwardly or outwardly, by reference to mean curvature-weighted normals, resulting in very rapid convergence on the feature. The evolution naturally stops at the feature. The gradients may be diffused or smoothed to improve tolerance to artifacts and noise, while preserving original image definition and resolution. In a cardiac application, the endocardial and myocardial boundaries are analyzed and used to generate composite images, calculate ejection fractions and so forth. The technique is also applicable to other static and dynamic structures and tissues.

Abstract translation: 用于分析感兴趣特征的图像的技术包括为图像的特征生成梯度，诸如像素强度值，发起候选边界，以及将候选边界演变成特征边界。 可以在开始时计算梯度，并通过迭代步骤来扩展候选边界，以提高处理的计算效率。 候选边界通过参考平均曲率加权法线向内或向外演化，导致特征上的非常快速的收敛。 演变自然就停止在这个功能上。 梯度可以扩散或平滑，以改善对伪像和噪声的容忍度，同时保留原始图像定义和分辨率。 在心脏应用中，分析心内膜和心肌边界以产生复合图像，计算射血分数等。 该技术也适用于其他静态和动态结构和组织。

公开(公告)号：US1708339A

公开(公告)日：1929-04-09

申请号：US22885727

申请日：1927-10-26

Applicant: ROBERT TANNENBAUM

Inventor： ROBERT TANNENBAUM

IPC: B60C11/02

CPC classification number: B60C11/02 ,  Y10T152/10045 ,  Y10T152/10297

公开(公告)号：US1367214A

公开(公告)日：1921-02-01

申请号：US34084819

申请日：1919-11-26

Applicant: ROBERT TANNENBAUM

Inventor： ROBERT TANNENBAUM

IPC: E04G9/04 ,  E04G17/02

CPC classification number: E04G9/04 ,  E04G17/02 ,  Y10S425/119

公开(公告)号：US06601895B1

公开(公告)日：2003-08-05

申请号：US10134930

申请日：2002-04-29

Applicant: L. Robert Tannenbaum ,  Joshua Tannenbaum ,  Andres Barales

Inventor： L. Robert Tannenbaum ,  Joshua Tannenbaum ,  Andres Barales

IPC: B60P334

CPC classification number: B60P1/6481 ,  B60P3/40

Abstract: The invention provides a pullout for carrying goods behind a semitrailer, which extends at approximately the same elevation as the cargo floor of the semitrailer. When the improved pullout is in a closed position, it is concealed by a decorative panel that presents an attractive, finished appearance. The rear turn signal lights and brake lights of the semitrailer are mounted in openings in the panel. The panel serves to partially enclose and protect the semitrailer's lights and associated wiring. The panel also provides a protected storage space for a support chain. A crash guard extends rearward from a housing for the new pullout so as to protect the electrical wiring and structural members of the semitrailer in the event of a collision.

Abstract translation: 本发明提供一种用于在半挂车后方携带货物的拉出装置，其在与半挂车的货物地板大致相同的高度上延伸。 当改进的拉出处于关闭位置时，它被装饰面板隐藏，呈现出吸引人的外观。 半挂车的后转信号灯和刹车灯安装在面板上的开口中。 面板用于部分包围和保护半挂车的灯和相关接线。 该面板还为支持链提供了受保护的存储空间。 防撞保护装置从用于新拉出的外壳向后延伸，以便在碰撞的情况下保护半挂车的电气配线和结构构件。

公开(公告)号：US07813581B1

公开(公告)日：2010-10-12

申请号：US11123445

申请日：2005-05-06

Applicant: Ben G. Fitzpatrick ,  Allen Robert Tannenbaum

Inventor： Ben G. Fitzpatrick ,  Allen Robert Tannenbaum

IPC: G06K9/40 ,  G06K9/00 ,  G06K9/68 ,  H04N5/225

CPC classification number: H04N5/357 ,  G06T5/002

Abstract: Improved methodology for image processing and object tracking that, inter alia, reduces noise. In one embodiment, the methodology is applied to moving targets, and comprises processing sequences of images that have been corrupted by one or more noise sources (e.g., sensor noise, medium noise, and/or target reflection noise). A likelihood or similar logical construct (e.g., Bayes' rule) is applied to the individual images (or aggregations thereof) of an image sequence in order to generate a posterior image for each observed image. The posterior images are fed-forward to the determination of the posterior image for one or more subsequent images (after smoothing), thereby making these subsequent determinations more accurate. The net result is a more accurate and noise-reduced representation (and location) of the target in each image.

Abstract translation: 改进图像处理和对象跟踪的方法，特别是减少噪声。 在一个实施例中，该方法被应用于移动目标，并且包括处理由一个或多个噪声源（例如，传感器噪声，中等噪声和/或目标反射噪声）损坏的图像序列。 可能或类似的逻辑构造（例如，贝叶斯规则）被应用于图像序列的各个图像（或其聚合），以便为每个观察到的图像生成后验图像。 后验图像被前馈到一个或多个后续图像的后验图像的确定（平滑之后），从而使得这些随后的确定更准确。 最终的结果是每个图像中目标的更准确和更低噪声的表示（和位置）。

公开(公告)号：US06535623B1

公开(公告)日：2003-03-18

申请号：US09293481

申请日：1999-04-15

Applicant: Allen Robert Tannenbaum ,  Anthony Joseph Yezzi, Jr.

Inventor： Allen Robert Tannenbaum ,  Anthony Joseph Yezzi, Jr.

IPC: G06K900

CPC classification number: G06T7/64 ,  G06T7/12 ,  G06T2207/10088 ,  G06T2207/30016 ,  G06T2207/30048

Abstract: A technique for analyzing images for a feature of interest includes generating gradients for a characteristic of an image, such as pixel intensity value, initiating a candidate boundary, and evolving the candidate boundary to the feature boundary. The gradients may be calculated at the outset and referred to through iterative steps in expansion of the candidate boundary to improve the computational efficiency of the processing. The candidate boundary is evolved, either inwardly or outwardly, by reference to mean curvature-weighted normals, resulting in very rapid convergence on the feature. The evolution naturally stops at the feature. The gradients may be diffused or smoothed to improve tolerance to artifacts and noise, while preserving original image definition and resolution. In a cardiac application, the endocardial and myocardial boundaries are analyzed and used to generate composite images, calculate ejection fractions and so forth. The technique is also applicable to other static and dynamic structures and tissues.

Abstract translation: 用于分析感兴趣特征的图像的技术包括为图像的特征生成梯度，诸如像素强度值，发起候选边界，以及将候选边界演变成特征边界。 可以在开始时计算梯度，并通过迭代步骤来扩展候选边界，以提高处理的计算效率。 候选边界通过参考平均曲率加权法线向内或向外演化，导致特征上的非常快速的收敛。 演变自然就停止在这个功能上。 梯度可以扩散或平滑，以改善对伪像和噪声的容忍度，同时保留原始图像定义和分辨率。 在心脏应用中，分析心内膜和心肌边界以产生复合图像，计算射血分数等。 该技术也适用于其他静态和动态结构和组织。

公开(公告)号：US06204853B1

公开(公告)日：2001-03-20

申请号：US09058100

申请日：1998-04-09

Applicant: Harvey Ellis Cline ,  Allen Robert Tannenbaum

Inventor： Harvey Ellis Cline ,  Allen Robert Tannenbaum

IPC: G06K940

CPC classification number: G06K9/40 ,  G06T5/002 ,  G06T5/10 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/20182 ,  H04N1/4092

Abstract: The noise reduction system of the present invention takes into account that noise is random with little between images adjacent physically, and in sampling time. It also takes into account the fact that some sequences of images are cyclical and “wrap around” in time with the beginning closely resembling the end of the cycle. A filter was developed which would smooth noise in a direction along an edge, but will not blur across an edge. It operates by determining vectors tangential to a surface point p, at a current voxel, and projecting 4D data onto the tangential vectors. A curvature matrix B&agr;&bgr; is determined. The eigenvalues of curvature matrix B&agr;&bgr; are determined to result in three curvatures for 4 dimensions. If the sign of all of the eigenvalues is the same, the current voxel is filtered, else, it is unchanged. This filtering is repeated for a number of voxels as the current voxel within a desired region for a single iteration. Preferably, this is repeated for several iterations to result in filtered data with reduced noise and little change in detail. The filtered data may then be segmented to separate structures. The segmented structures may then be used in analysis, such as in medical diagnosis.

Abstract translation: 本发明的降噪系统考虑到物理上相邻的图像和采样时间之间的噪声几乎是随机的。 它还考虑到一些事实，即图像的一些序列是周期性的，并且在时间上“缠绕”，其开始与周期结束非常类似。 已经开发了一种滤光器，其可以沿着边缘的方向平滑噪声，但是不会在边缘上模糊。 它通过确定在当前体素上与表面点p相切的矢量并将4D数据投影到切向矢量上来操作。 确定曲率矩阵Balphabeta。 曲率矩阵Balphabeta的特征值被确定为导致4个维度的三个曲率。 如果所有特征值的符号相同，则对当前体素进行过滤，否则不变。 对于多次体素重复该过滤，作为单个迭代期望的区域内的当前体素。 优选地，这被重复进行几次迭代以产生具有降低的噪声并且具有细微变化的滤波数据。 然后可以将经滤波的数据分段以分离结构。 然后可以在分析中使用分段结构，例如在医学诊断中。