公开(公告)号：US20160210521A1

公开(公告)日：2016-07-21

申请号：US14913049

申请日：2014-08-13

Applicant: FTS COMPUTERTECHNIK GMBH

Inventor： Stefan Traxler

IPC: G06K9/03 ,  G06K9/00

CPC classification number: G06K9/03 ,  G06K9/00805

Abstract: A method for error detection for at least one system (1), characterised by a) at least partially optically measuring at least one system variable S1 at least at one moment in time t1 or at least in a time interval Δt1, b) creating at least one prediction value Px for at least one system variable Sx for at least one moment in time t2 following the moment in time t1 or for at least one time interval Δt2 following the time interval Δt1 with the aid of the at least one computing model (4), c) comparing the at least one prediction value Px with at least one value of the at least one system variable Sx associated with the moment in time t2 or the time interval Δt2, and d) using the result of the comparison of step c) to determine the presence of at least one error.

Abstract translation: 一种用于至少一个系统（1）的错误检测方法，其特征在于：a）至少部分地至少在时间t1或者至少在时间间隔Dgr; t1中的某个时刻光学测量至少一个系统变量S1; b） 对于至少一个系统变量Sx至少一个预测值Px，在时间t1之后的时间t2内的至少一个时刻，或在时间间隔＆Dgr; t1之后的至少一个时间间隔＆Dgr; t2，借助于 至少一个计算模型（4），c）将所述至少一个预测值Px与至少一个系统变量Sx的至少一个值进行比较，该至少一个系统变量Sx与时间t2或时间间隔Dgr; t2中的时刻相关联，以及d） 使用步骤c）的比较的结果来确定至少一个错误的存在。

公开(公告)号：US20160205396A1

公开(公告)日：2016-07-14

申请号：US14912954

申请日：2014-08-13

Applicant: FTS COMPUTERTECHNIK GMBH

Inventor： Stefan Traxler ,  Eric Schmidt

IPC: H04N17/00 ,  G06K9/03 ,  G06K9/62 ,  G06K9/00

CPC classification number: H04N17/002 ,  G06K9/00791 ,  G06K9/03 ,  G06K9/6202 ,  G06K9/6262

Abstract: A method for error detection for at least one image processing system for capturing the surroundings of a motor vehicle, comprising the following steps: a) capturing at least one first primary image (PB1), b) producing at least one first reference image (RB1) by introducing at least one reference feature (RM) into the at least one first primary image (PB1), c) processing the at least one first reference image (RB1) with the aid of at least one algorithm to be checked, d) extracting at least one test feature (TM) associated with the at least one reference feature (RM) from the processed at least one first reference image (RB1), e) comparing the at least one test feature (TM) with the at least one reference feature (RM) and using the result of the comparison in order to determine the presence of at least one error.

Abstract translation: 一种用于至少一个用于捕获机动车辆的周围环境的图像处理系统的误差检测方法，包括以下步骤：a）捕获至少一个第一原始图像（PB1），b）产生至少一个第一参考图像（RB1 ）通过将至少一个参考特征（RM）引入所述至少一个第一主图像（PB1）中，c）借助于要检查的至少一个算法来处理所述至少一个第一参考图像（RB1），d） 从所处理的至少一个第一参考图像（RB1）提取与所述至少一个参考特征（RM）相关联的至少一个测试特征（TM）; e）将所述至少一个测试特征（TM）与所述至少一个 参考特征（RM），并使用比较结果来确定是否存在至少一个错误。

公开(公告)号：US20160205395A1

公开(公告)日：2016-07-14

申请号：US14912953

申请日：2014-08-13

Applicant: FTS COMPUTERTECHNIK GMBH

Inventor： Eric Schmidt ,  Stefan Traxler

IPC: H04N17/00 ,  G06K9/03 ,  G06K9/00

CPC classification number: H04N17/002 ,  G06K9/00791 ,  G06K9/03 ,  G06K9/6262

Abstract: A method for error detection for at least one image processing system for capturing the surroundings of a motor vehicle, wherein the following steps can be performed in any order unless specified otherwise: a) capturing at least one first primary image (PB1) on the basis of a primary image source (PBU), b) processing the at least one first primary image (PB1) with the aid of at least one algorithm to be checked, after step a), c) extracting at least one primary image feature (PBM) on the basis of the processed at least one first primary image (PB1), after step b), d) producing or capturing at least one reference image (RB1) by displacing and/or rotating the at least one first primary image (PB1) or the primary image source (PBU), after step a), e) processing the at least one reference image (RB1) with the aid of the at least one algorithm to be checked, after step d), f) extracting at least one reference image feature (RBM) from the at least one processed reference image (RB1), after step e), g) comparing the at least one primary image feature (PBM) with the at least one reference image feature (RBM) and using the result of the comparison in order to determine the presence of at least one error, after steps c) and f).

Abstract translation: 一种用于至少一个用于捕获机动车辆的周围环境的图像处理系统的错误检测方法，其中可以以任何顺序执行以下步骤，除非另有规定：a）基于基础捕获至少一个第一主图像（PB1） 主要图像源（PBU），b）在步骤a）之后借助于要检查的至少一个算法来处理所述至少一个第一主图像（PB1），c）提取至少一个主图像特征（PBM ）在步骤b）之后，基于经处理的至少一个第一原始图像（PB1），d）通过使至少一个第一主要图像（PB1）移位和/或旋转来产生或捕获至少一个参考图像（RB1） ）或主图像源（PBU），在步骤a）之后，e）在步骤d）之后借助于待检查的至少一个算法处理所述至少一个参考图像（RB1），f）至少提取 一个参考图像特征（RBM）来自至少一个经处理的参考图像（RB1） 步骤e），g）将所述至少一个主要图像特征（PBM）与所述至少一个参考图像特征（RBM）进行比较，并且使用比较的结果来确定在步骤c之后存在至少一个错误 ）和f）。