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

US5963653A Hierarchical information fusion object recognition system and method 失效
标题翻译：分层信息融合对象识别系统及方法
公开(公告)号：US5963653A
公开(公告)日：1999-10-05
申请号：US878863
申请日：1997-06-19
申请人： Charles McNary , Kurt Reiser , David M. Doria , David W. Webster , Yang Chen
发明人： Charles McNary , Kurt Reiser , David M. Doria , David W. Webster , Yang Chen
IPC分类号： G01S7/41 , G01S13/86 , G06K9/62 , G06K9/68 , G06K9/00 , G01S13/00 , G01S13/58
CPC分类号： G06K9/6293 , G01S13/867 , G01S7/417 , G06K9/3241
摘要： A hierarchical object recognition method for aggregation, interpretation and classification of information from multiple sensor sources on the detection feature attribute level. The system extracts information derived from each sensor source to obtain detections and their feature attributes. At least two processing streams, one for each sensor source, are provided for converting the detections and their feature attributes into hypotheses on identity and class of detected objects. The detections are shared and combined between the two processing streams using hierarchical information fusion algorithms to determine which ones of the hypotheses on identity and class of detected objects have sufficient probabilities for classifying the information.
摘要翻译：一种分层对象识别方法，用于在检测特征属性级别上对来自多个传感器源的信息进行聚合，解释和分类。系统提取从每个传感器源获得的信息以获得检测及其特征属性。为每个传感器源提供至少两个处理流，用于将检测及其特征属性转换成对检测对象的身份和类别的假设。使用分层信息融合算法在两个处理流之间共享和组合检测，以确定哪些对假定的身份和检测对象的类具有足够的概率来分类信息。

2. 发明申请

US20140006334A1 SYSTEM AND METHOD FOR SCALED MULTINOMIAL-DIRICHLET BAYESIAN EVIDENCE FUSION 有权
标题翻译：系统和方法用于标准化的DIRICHLET BAYESIAN证据融合
公开(公告)号：US20140006334A1
公开(公告)日：2014-01-02
申请号：US13535954
申请日：2012-06-28
申请人： David M. Doria
发明人： David M. Doria
IPC分类号： G06N5/02
CPC分类号： G06N99/005 , G06N5/04 , G06N7/005
摘要： A fusion method, implemented by one or more processors, for classifying a target having class types. The method includes: obtaining evidence from one or more classifiers, the evidence represented by scores from the one or more classifiers; representing the obtained evidence in a Bayesian context, where the Bayesian beliefs are obtained from the scores; obtaining new evidence, the new evidence represented by new scores from the classifiers; representing the obtained new evidence in an enhanced Bayesian context, where the enhanced Bayesian beliefs are obtained from the new scores; combining the scores and the new scores over multiple times; combining the evidence and the new evidence over multiple times; and using the combined scores and the combined evidence for each of the plurality of class types to classify the target.
摘要翻译：一种由一个或多个处理器实现的用于对具有类类型的目标进行分类的融合方法。该方法包括：从一个或多个分类器获得证据，由一个或多个分类器的分数表示的证据; 代表在贝叶斯语境中获得的证据，贝叶斯信念是从得分中获得的; 获得新证据，来自分类人员的新成绩的新证据; 代表在增强的贝叶斯语境中获得的新证据，其中从新分数获得增强的贝叶斯信念; 多次结合得分和新分数; 结合证据和新证据多次; 并且使用组合得分和多个类型中的每一个的组合证据来对目标进行分类。

3. 发明授权

US08155807B2 Fusion for automated target recognition 有权
标题翻译：融合用于自动化目标识别
公开(公告)号：US08155807B2
公开(公告)日：2012-04-10
申请号：US12398116
申请日：2009-03-04
申请人： David M. Doria , Robert T. Frankot
发明人： David M. Doria , Robert T. Frankot
IPC分类号： G06F19/00
CPC分类号： G06K9/6289 , G06K9/3241
摘要： A method of predicting a target type in a set of target types from at least one image is provided. At least one image is obtained. A first and second set of confidence values and associated azimuth angles are determined for each target type in the set of target types from the at least one image. The first and second set of confidence values are fused for each of the azimuth angles to produce a fused curve for each target type in the set of target types. When multiple images are obtained, first and second set of possible detections are compiled corresponding to regions of interest in the multiple images. The possible detections are associated by regions of interest. The fused curves are produced for every region of interest. In the embodiments, the target type is predicted from the set of target types based on criteria concerning the fused curve.
摘要翻译：提供了一种从至少一个图像中预测一组目标类型中的目标类型的方法。至少获得一个图像。针对来自至少一个图像的目标类型集合中的每个目标类型确定第一和第二组置信度值和相关方位角。第一和第二组置信度值针对每个方位角进行融合，以产生目标类型集合中每种目标类型的融合曲线。当获得多个图像时，第一组和第二组可能的检测被对应于多个图像中的感兴趣区域被编译。可能的检测与感兴趣的区域相关联。为每个感兴趣区域产生融合曲线。在实施例中，基于与融合曲线有关的标准，从目标类型集合预测目标类型。

4. 发明授权

US5459636A Position and orientation estimation neural network system and method 失效
标题翻译：位置和方向估计神经网络系统及方法
公开(公告)号：US5459636A
公开(公告)日：1995-10-17
申请号：US186181
申请日：1994-01-14
申请人： Allen Gee , David M. Doria
发明人： Allen Gee , David M. Doria
IPC分类号： G06F15/18 , G06K9/64 , G06N3/00 , G06T1/00 , G06T7/00 , G06K9/00
CPC分类号： G06T7/0046 , G06K9/6203
摘要： Disclosed are a system and method for determining the pose (translation, rotation, and scale), or position and orientation, of a model object that best matches a target object located in image data. Through an iterative process small adjustments are made to the original position and orientation of the model object until it converges to a state that best matches the target object contained in the image data. Edge data representative of edges of the target object and edge data representative of the model object are processed for each data point in the model object relative to each point in the target object to produce a set of minimum distance vectors between the model object and the target object. A neural network estimates translation, rotation, and scaling adjustments that are to be made to the model object. Pose of the model object is adjusted relative to the target object based upon the estimated translation, rotation, and scaling adjustments provided by the neural network. Iterative calculation of the minimum distance vectors, estimation of the translation, rotation, and scaling adjustments, and adjustment of the position and orientation of the model object is adapted to reposition the model object until it substantially overlays the target object. Final position of the model object provides an estimate of the position and orientation of the target object in the digitized image.
摘要翻译：公开了一种用于确定与位于图像数据中的目标对象最佳匹配的模型对象的姿态（平移，旋转和缩放）或位置和取向的系统和方法。通过迭代过程，对模型对象的原始位置和方向进行小的调整，直到它收敛到与图像数据中包含的目标对象最佳匹配的状态。针对目标对象的边缘和表示模型对象的边缘数据的边缘数据针对目标对象中的每个点针对模型对象中的每个数据点进行处理，以产生模型对象与目标之间的一组最小距离向量目的。神经网络估计要对模型对象进行的平移，旋转和缩放调整。基于由神经网络提供的估计的平移，旋转和缩放调整，相对于目标对象来调整模型对象的姿态。最小距离矢量的迭代计算，平移的估计，旋转和缩放调整以及模型对象的位置和方向的调整适于重新定位模型对象，直到它大致覆盖目标对象。模型对象的最终位置提供了数字化图像中目标对象的位置和方向的估计。

5. 发明授权

US08681037B2 Performance model for synthetic aperture radar automatic target recognition and method thereof 有权
标题翻译：合成孔径雷达自动目标识别性能模型及其方法
公开(公告)号：US08681037B2
公开(公告)日：2014-03-25
申请号：US13096913
申请日：2011-04-28
申请人： David M. Doria
发明人： David M. Doria
IPC分类号： G01S13/00
CPC分类号： G01S13/90 , G01S7/412 , G06K9/6277
摘要： A target correlation matrix is generated for multiple two-class combinations of target types each having a target correlation and a synthetic aperture radar observation space. A target probability density of a target radar cross-section signature and a background probability density of a background radar cross-section signature are utilized. The observation space of each of the two-class combinations is partitioned into a target partition and at least one background partition in accordance with the target correlation. A conditional log likelihood is calculated using at least one random number for each of the partitions in accordance with the target probability density and the background probability density, and summed according to the two-class combinations. A maximum log likelihood is calculated from the summed conditional log likelihoods given that one target type of the multiple two-class combinations is assumed to be true. An automatic target recognition performance prediction based on the maximum log likelihood is generated.
摘要翻译：对于具有目标相关性和合成孔径雷达观测空间的目标类型的多个两类组合，生成目标相关矩阵。利用目标雷达横截面签名的目标概率密度和背景雷达截面签名的背景概率密度。根据目标相关性，将两类组合中的每一个的观察空间划分为目标分区和至少一个背景分区。使用根据目标概率密度和背景概率密度的每个分区的至少一个随机数来计算条件对数似然，并且根据两类组合求和。假定一个目标类型的多个两类组合被假设为真，则从求和的条件对数似然性计算最大对数似然。生成基于最大对数似然度的自动目标识别性能预测。

6. 发明授权

US08438128B2 Empirical modeling of confusion matrices 有权
标题翻译：混沌矩阵的经验建模
公开(公告)号：US08438128B2
公开(公告)日：2013-05-07
申请号：US12604539
申请日：2009-10-23
申请人： David M. Doria
发明人： David M. Doria
IPC分类号： G06F9/44 , G06N7/02 , G06N7/06
CPC分类号： G06K9/6217 , G06K9/6277
摘要： A method and system of estimating the performance of a classifier system based on a reported confusion matrix includes, in one embodiment, parameters fit to observed confusion matrices, such that the expected performance of decision detection versus the probability of not-in-library reports can be estimated based on the forced decision confusion matrix. The approach also lends itself to a general methodology for modeling classes of confusers in a statistical manner, which can be extended to modeling clutter severity.
摘要翻译：基于报告的混淆矩阵来估计分类器系统的性能的方法和系统在一个实施例中包括适合观察到的混淆矩阵的参数，使得决策检测的预期性能与不在库报告中的概率相关根据强制决策混淆矩阵估算。该方法还适用于以统计学方式建模困惑者类的一般方法，可以将其扩展到建模杂波严重性。

7. 发明授权

US08781992B2 System and method for scaled multinomial-dirichlet bayesian evidence fusion 有权
标题翻译：用于缩放多项式dirichlet贝叶斯证据融合的系统和方法
公开(公告)号：US08781992B2
公开(公告)日：2014-07-15
申请号：US13535954
申请日：2012-06-28
申请人： David M. Doria
发明人： David M. Doria
IPC分类号： G06N99/00 , G06N5/04
CPC分类号： G06N99/005 , G06N5/04 , G06N7/005
摘要： A fusion method, implemented by one or more processors, for classifying a target having class types. The method includes: obtaining evidence from one or more classifiers, the evidence represented by scores from the one or more classifiers; representing the obtained evidence in a Bayesian context, where the Bayesian beliefs are obtained from the scores; obtaining new evidence, the new evidence represented by new scores from the classifiers; representing the obtained new evidence in an enhanced Bayesian context, where the enhanced Bayesian beliefs are obtained from the new scores; combining the scores and the new scores over multiple times; combining the evidence and the new evidence over multiple times; and using the combined scores and the combined evidence for each of the plurality of class types to classify the target.
摘要翻译：一种由一个或多个处理器实现的用于对具有类类型的目标进行分类的融合方法。该方法包括：从一个或多个分类器获得证据，由一个或多个分类器的分数表示的证据; 代表在贝叶斯语境中获得的证据，贝叶斯信念是从得分中获得的; 获得新证据，来自分类人员的新成绩的新证据; 代表在增强的贝叶斯语境中获得的新证据，其中从新分数获得增强的贝叶斯信念; 多次结合得分和新分数; 结合证据和新证据多次; 并且使用组合得分和多个类型中的每一个的组合证据来对目标进行分类。

8. 发明申请

US20100226534A1 FUSION FOR AUTOMATED TARGET RECOGNITION 有权
标题翻译：自动化目标识别的融合
公开(公告)号：US20100226534A1
公开(公告)日：2010-09-09
申请号：US12398116
申请日：2009-03-04
申请人： David M. Doria
发明人： David M. Doria
IPC分类号： G06K9/00
CPC分类号： G06K9/6289 , G06K9/3241
摘要： A method of predicting a target type in a set of target types from at least one image is provided. At least one image is obtained. A first and second set of confidence values and associated azimuth angles are determined for each target type in the set of target types from the at least one image. The first and second set of confidence values are fused for each of the azimuth angles to produce a fused curve for each target type in the set of target types. When multiple images are obtained, first and second set of possible detections are compiled corresponding to regions of interest in the multiple images. The possible detections are associated by regions of interest. The fused curves are produced for every region of interest. In the embodiments, the target type is predicted from the set of target types based on criteria concerning the fused curve.
摘要翻译：提供了一种从至少一个图像中预测一组目标类型中的目标类型的方法。至少获得一个图像。针对来自至少一个图像的目标类型集合中的每个目标类型确定第一和第二组置信度值和相关方位角。第一和第二组置信度值针对每个方位角进行融合，以产生目标类型集合中每种目标类型的融合曲线。当获得多个图像时，第一组和第二组可能的检测被对应于多个图像中的感兴趣区域被编译。可能的检测与感兴趣的区域相关联。为每个感兴趣区域产生融合曲线。在实施例中，基于与融合曲线有关的标准，从目标类型集合预测目标类型。

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