公开(公告)号：US09213915B2

公开(公告)日：2015-12-15

申请号：US13837866

申请日：2013-03-15

Applicant: RAYTHEON COMPANY

Inventor： Anthony Sommese ,  Bradley A. Flanders ,  Ian S. Robinson

IPC: G06K9/46 ,  G06K9/52 ,  G06K9/00 ,  G06K9/62 ,  G06K9/48

CPC classification number: G06K9/522 ,  G06K9/0063 ,  G06K9/48 ,  G06K9/623

Abstract: The disclosure provides a filtering engine for selecting a subset of hyperspectral imaging wavebands having information useful for detecting a target in a scene. Selecting these wavebands, called “sparse bands,” is an iterative process. One or more search techniques of varying computational complexity are used in the process. The techniques rely on various selection criteria, including a signal to clutter ratio that measures the “goodness” of band selection. A convenient example of the filtering engine uses several of the techniques together in a layered approach. In this novel approach, simpler computational techniques are applied, initially, to reduce a number of bands. More computationally intensive techniques then search the reduced band space. Accordingly, the filtering engine efficiently selects a set of sparse bands tailored for each target and each scene, and maintains some of the detection capability provided with a full set of wavebands.

Abstract translation: 本公开提供了一种用于选择具有用于检测场景中的目标的信息的高光谱成像波段的子集的滤波引擎。 称为“稀疏带”的这些波段是一个迭代过程。 在该过程中使用一种或多种具有不同计算复杂度的搜索技术。 这些技术依赖于各种选择标准，包括测量频带选择的“良好性”的信噪比。 过滤引擎的一个方便的示例使用分层方法在一起的几种技术。 在这种新颖的方法中，最初应用更简单的计算技术来减少多个频带。 然后更多的计算密集型技术搜索缩小的带隙。 因此，滤波引擎有效地选择为每个目标和每个场景定制的一组稀疏频带，并且保持提供有一整套波段的一些检测能力。

公开(公告)号：US09213913B1

公开(公告)日：2015-12-15

申请号：US14561873

申请日：2014-12-05

Applicant: Raytheon Company

Inventor： Ian S. Robinson ,  Bradley Flanders ,  Anthony Sommese

IPC: G06K9/00 ,  G06K9/46 ,  G06K7/14 ,  G06K9/40 ,  G06T5/20 ,  G06K9/62 ,  G06F17/16

CPC classification number: G06K9/46 ,  G06F17/16 ,  G06K7/146 ,  G06K9/00557 ,  G06K9/0063 ,  G06K9/40 ,  G06K9/4609 ,  G06K9/6232 ,  G06K2009/00644 ,  G06K2009/4657 ,  G06T5/20 ,  G06T2207/10028

Abstract: A rapid target detection approach with corresponding method and system to detect targets in scene pixels, efficiently, is presented. The approach includes tailoring an approximation of a target score for each scene pixel, individually, based on an “intermediate target score.” The intermediate target score includes a portion of the terms used to compute the target score. The portion is selected by computing a signal-to-clutter ratio (SCR) for a spectral reference associated with a target and ranking the terms by their contribution to the SCR. Scene pixels with low intermediate target scores are removed from further processing. The remaining scene pixels are further processed, including computing target scores to detect targets in these scene pixel. Advantageously, examples of the approach process a few terms of all scene pixels, eliminate most scene pixels, and calculate more terms on high target scoring scene pixels as needed.

Abstract translation: 提出了一种快速目标检测方法，具有相应的方法和系统，有效地检测场景像素中的目标。 该方法包括基于“中间目标得分”单独地定制每个场景像素的目标分数的近似值。中间目标分数包括用于计算目标分数的术语的一部分。 通过计算与目标相关联的频谱参考的信号与杂波比（SCR）来选择该部分，并通过它们对SCR的贡献来对这些项进行排序。 具有低中等目标分数的场景像素从进一步处理中移除。 剩余的场景像素被进一步处理，包括计算目标分数以检测这些场景像素中的目标。 有利地，所述方法的示例处理所有场景像素的几个术语，消除大多数场景像素，并且根据需要在高目标评分场景像素上计算更多项。

公开(公告)号：US09189704B2

公开(公告)日：2015-11-17

申请号：US13870685

申请日：2013-04-25

Applicant: RAYTHEON COMPANY

Inventor： Ian S. Robinson ,  Bradley A. Flanders ,  Anthony Sommese

IPC: G06K9/62 ,  G01N21/31 ,  G01J3/28 ,  G06K9/00 ,  G01N21/17 ,  G06K9/46

CPC classification number: G06K9/6202 ,  G01J3/28 ,  G01N21/31 ,  G01N2021/1793 ,  G06K9/00536 ,  G06K2009/00644 ,  G06K2009/4657 ,  G06T2207/10036

Abstract: Provided are examples of a detecting engine for determining in which pixels in a hyperspectral scene are materials of interest or targets present. A collection of spectral references, typically five to a few hundred, is used in look a through a million or more pixels per scene to identify detections. An example of the detecting engine identifies detections by calculating a kernel vector for each spectral reference in the collection. This calculation is quicker than the conventional Matched Filter kernel calculation which computes a kernel for each scene pixel. Another example of the detecting engine selects pixels with high detection filter scores and calculates coherence scores for these pixels. This calculation is more efficient than the conventional Adaptive Cosine/Coherence Estimator calculation that calculates a score for each scene pixel, most of which do not provide a detection.

Abstract translation: 提供了一种用于确定高光谱场景中的像素是存在感兴趣或目标的材料的检测引擎的示例。 频谱参考的集合，通常为5到几百个，用于每个场景看一百万个或更多个像素以识别检测。 检测引擎的示例通过计算集合中的每个频谱参考的核向量来识别检测。 该计算比传统的匹配滤波器内核计算更快，它计算每个场景像素的内核。 检测引擎的另一例子选择具有高检测滤波器分数的像素并且计算这些像素的相干分数。 该计算比传统的自适应余弦/相干估计器计算更有效，其计算每个场景像素的得分，其中大部分不提供检测。

公开(公告)号：US09147126B2

公开(公告)日：2015-09-29

申请号：US13957415

申请日：2013-08-01

Applicant: RAYTHEON COMPANY

Inventor： Ian S. Robinson ,  Bradley Flanders ,  Anthony Sommese

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/6202 ,  G06K9/0063 ,  G06K2009/00644

Abstract: Provided are examples of a detecting engine for identifying detections in compressed scene pixels. For a given compressed scene pixel having a set of M basis vector coefficients, set of N basis vectors, and code linking the M basis vector coefficients to the N basis vectors, the detecting engine reduces a spectral reference (S) to an N-dimensional spectral reference (SN) based on the set of N basis vectors. The detecting engine computes an N-dimensional spectral reference detection filter (SN*) from SN and the inverse of an N-dimensional scene covariance (CN). The detecting engine forms an M-dimensional spectral reference detection filter (SM*) from SN* based on the compression code and computes a detection filter score based on SM*. The detecting engine compares the score to a threshold and determines, based on the comparison, whether the material of interest is present in the given compressed scene pixel and is a detection.

Abstract translation: 提供了用于识别压缩场景像素中的检测的检测引擎的示例。 对于具有M个基矢量系数集合，N个基矢量的集合以及将M个基矢量系数链接到N个基矢量的代码的给定压缩场景像素，检测引擎将频谱参考（S）减小到N维 基于N个基矢量的集合的频谱参考（SN）。 检测引擎计算SN的N维频谱参考检测滤波器（SN *）和N维场景协方差（CN）的倒数。 检测引擎基于压缩码从SN *形成M维频谱参考检测滤波器（SM *），并根据SM *计算检测滤波器分数。 检测引擎将得分与阈值进行比较，并且基于比较确定感兴趣的材料是否存在于给定的压缩场景像素中并且是检测。

公开(公告)号：US20140233857A1

公开(公告)日：2014-08-21

申请号：US14010467

申请日：2013-08-26

Applicant: RAYTHEON COMPANY

Inventor： Ian S. Robinson

IPC: G06K9/00

CPC classification number: G06K9/0063 ,  G06K9/0057 ,  G06K9/6232 ,  G06K2009/00644

Abstract: Provided is a method of hyperspectral image dimension reduction. The method includes receiving a hyperspectral image having a plurality of pixels. A set of basis vectors is established at least in part with respect to the spectral vectors of the initial hyperspectral image. For each pixel of the hyperspectral image, the spectral vector is read and decomposed, i.e. unmixed, with the basis vector set to provide at least a reduced dimension vector for each pixel. Collectively the reduced dimension vectors for each pixel represent the dimensionally reduced image. A system operable to perform the method is also provided.

Abstract translation: 提供了一种高光谱图像尺寸降低的方法。 该方法包括接收具有多个像素的高光谱图像。 至少部分地基于初始高光谱图像的光谱向量建立一组基矢量。 对于高光谱图像的每个像素，频谱矢量被读取和分解，即未混合，其中设置的基矢量为每个像素提供至少一个缩小的维度向量。 集合地，每个像素的缩小维度向量表示尺寸缩小的图像。 还提供了可操作以执行该方法的系统。

公开(公告)号：US20130335565A1

公开(公告)日：2013-12-19

申请号：US13903500

申请日：2013-05-28

Applicant: RAYTHEON COMPANY

Inventor： Ian S. Robinson ,  Mark T. Busch ,  Lacy G. Cook

IPC: H04N5/232

CPC classification number: H04N5/23267 ,  G06T3/00 ,  H04N5/144 ,  H04N5/23248 ,  H04N5/23287

Abstract: An imaging platform minimizes image distortion when there is relative motion of the imaging platform with respect to the scene being imaged where the imaging platform may be particularly susceptible to distortion when it is configured with a wide field of view or high angular rate of movement, or when performing long-stares at a given scene (e.g., for nighttime and low-light imaging.) Distortion correction may be performed by predicting distortion due to the relative motion of the imaging platform, determining optical transformations to prevent the distortion, dynamically adjusting the optics of the imaging platform during exposure, and performing digital image correction.

Abstract translation: 当成像平台相对于正在成像的场景存在相对运动时，成像平台在被配置为具有宽视野或高角速度运动时可能特别容易受到失真的影响，成像平台使图像失真最小化，或 当在给定的场景（例如，夜间和低光成像时）进行长时间观察时，可以通过预测由于成像平台的相对运动引起的失真来进行失真校正，确定光学变换以防止失真，动态地调整 曝光期间成像平台的光学元件，以及进行数字图像校正。