公开(公告)号：US20230351737A1

公开(公告)日：2023-11-02

申请号：US18301312

申请日：2023-04-17

Applicant: Southwest Research Institute

Inventor： Harold A. GARZA ,  David R. CHAMBERS ,  Douglas A. BROOKS

IPC: G06V10/776 ,  G06V10/778 ,  G06V10/82 ,  G06V10/774

CPC classification number: G06V10/776 ,  G06V10/7796 ,  G06V10/82 ,  G06V10/7747 ,  G06V2201/02

Abstract: In an approach to integrating real-world properties into machine learning training, a real-world image is received. The real-world image is compared to a simulated image, where the comparison is performed using a discriminator network of a generative adversarial network (GAN). A generator network of the GAN is trained with results of the comparison of the real-world image to the simulated image. Responsive to determining that the real-world image is not optimal, the real-world image is iteratively tuned, using the generator network of the GAN, until it is determined that the real-world image is optimal, where the real-world image is optimal if the real-world image meets a predetermined threshold for accuracy of one or more image parameters of the simulated image versus the real-world image. The discriminator network of the GAN is trained with the real-world image.

公开(公告)号：US20160358088A1

公开(公告)日：2016-12-08

申请号：US14732002

申请日：2015-06-05

Applicant: Southwest Research Institute

Inventor： Stephan J. LEMMER ,  David R. CHAMBERS

IPC: G06N7/00 ,  G06N99/00 ,  G06N3/12 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06N7/00 ,  G06K9/00791 ,  G06K9/6256 ,  G06K9/6277 ,  G06N3/126 ,  G06N99/005

Abstract: A method and system is provided for estimation of sensor data confidence based on statistical analysis of different classifier and feature-set (CF) configurations. A method may include: training a classifier of a CF configuration based on a training set of nominal sensor data values; executing the classifier on the training set to generate a first set of confidence values; collecting statistics on the confidence values; calculating a confidence decision threshold based on the collected statistics; executing the classifier on an evaluation set of nominal and degraded sensor data values, to generate a second set of confidence values; deciding whether the sensor data values of the evaluation set are nominal or degraded based on a comparison of the second set of confidence values to the confidence decision threshold; and calculating a score to evaluate the trained classifier based on a verification of the decisions.

Abstract translation: 提供了一种基于不同分类器和特征集（CF）配置的统计分析来估计传感器数据置信度的方法和系统。 一种方法可以包括：基于标准传感器数据值的训练集来训练CF配置的分类器; 在训练集上执行分类器以生成第一组置信度值; 收集信心值统计; 基于收集的统计量计算置信决策阈值; 在名义和劣化传感器数据值的评估集上执行分类器，以产生第二组置信度值; 基于所述第二组置信度值与所述置信判定阈值的比较来判定所述评估集合的传感器数据值是否为标称值或劣化值; 以及基于对所述决定的验证来计算得分以评估所训练的分类器。

公开(公告)号：US20150262352A1

公开(公告)日：2015-09-17

申请号：US14208941

申请日：2014-03-13

Applicant: Southwest Research Institute

Inventor： John T. CARROLA, JR. ,  Warren Carl COUVILLION, JR. ,  Susan M. PORTER ,  David R. CHAMBERS ,  Christopher J. GUERRA

IPC: G06T7/00 ,  G01L1/24 ,  G01B11/16 ,  G06K9/00 ,  G06T7/60 ,  G06K9/46 ,  G06K9/62 ,  G01L1/06 ,  H04N5/33

CPC classification number: G06T7/0012 ,  A61B34/10 ,  G01B11/168 ,  G01L1/06 ,  G01L1/241 ,  G01L1/248 ,  G01N21/21 ,  G01N21/23 ,  G01N21/55 ,  G01N2021/557 ,  G06F3/011 ,  G06K9/00624 ,  G06K9/4642 ,  G06K9/6267 ,  G06T7/60 ,  G09B23/28 ,  H04N5/33

Abstract: A method and system for analysis of a viscoelastic response in a deformable material. The system includes a light source configured to provide linearly polarized light and a polariscope configured to receive said linearly polarized light and to generate an image associated with a viscoelastic response of said deformable material. The system also includes a machine vision system configured to operate on the image to locate the response on the deformable material and to classify the response as one of a plurality of predefined types of responses. A display may then be provide that is configured to provide feedback of the location of the viscoelastic response and classification of the response to a user of said system.

Abstract translation: 用于分析可变形材料中的粘弹性响应的方法和系统。 该系统包括被配置为提供线性偏振光的光源和被配置为接收所述线偏振光并且产生与所述可变形材料的粘弹性响应相关联的图像的偏光镜。 该系统还包括机器视觉系统，其被配置为在图像上操作以定位可变形材料上的响应并将响应分类为多种预定类型的响应之一。 然后可以提供被配置为提供粘弹性响应的位置的反馈和对所述系统的用户的响应的分类的显示。