Robert Boschgmbh

Konrad Groh

Roland Norden

Matthias Woehrle

Erik Tonner

Jens-Holger Barth

Andreas Hopf

Frank Kowol

Mona Meister

Arnold Smeulders

Ivan Sosnovik

Christoph Gladisch

Oliver Willers

Christian Heinzemann

Jens Oehlerking

Michael Rittel

Artem Moskalev

A computer-implemented method for evaluating an image classifier, in which a classifier output of the image classifier is provided for the actuation of an at least semi-autonomous robot. The evaluation method includes: ascertaining a first dataset including image data and annotations being assigned to the image data, the annotations including information about the scene imaged in the respective image and/or about image regions to be classified and/or about movement information of the robot; ascertaining regions of the scenes that are reachable by the robot based on the annotations; ascertaining relevance values for image regions to be classified by the image classifier; classifying the image data of the first image dataset with the aid of the image classifier; evaluating the image classifier based on image regions correctly classified by the image classifier and incorrectly classified image regions, as well as the calculated relevance values of the corresponding image regions.

Method and device for evaluating an image classifier

A computer-implemented method for training a data-based time determining model for determining an opening or closing time of an injection valve based on a sensor signal. The method includes: providing an unlabeled analysis point time series by sampling the sensor signal of a sensor of the injection valve; training the data-based time determining model to assign a time specification which represents a specific opening or closing duration to an analysis point time series, the training process being carried out using a first shifting function to time-shift the analysis point time series and a second shifting function in order to time-shift the time specification. A consistency loss function is used for the training process.

Method and device for training a data-based time determining model for determining an opening or closing time of an injection valve using a machine learning method

A method for plausibilizing the output of an artificial neural network (ANN) used as classifier. The method includes the following steps: a plurality of images, for which the ANN has determined an assignment to one or more classes of a predetermined classification, as well as the assignment determined in each case by the ANN are provided; for each combination of one image and one assignment, a location-resolved relevance evaluation of the image is determined utilizing a relevance evaluation function, this relevance evaluation indicating which parts of the image have contributed, to what extent, to the assignment; a further classifier is trained to determine from one image and one relevance evaluation ascertained for the image, a reconstruction of the assignment to which this relevance evaluation relates; based on the agreement between the reconstructions and the actual assignments, a figure of merit is determined for the relevance evaluation function.

Plausibilizing the output of neural classifier networks

A method determines a distance metric for determining a distance to a data point having heterogeneous classes of variables. The method includes providing training records each assigning a label to a data point, the training records partitioned into training data points of a training amount and validation data points of a validation amount, and training a data-based system model with the training amount, such that the data-based system model associates data points with a model output, respectively. The method further includes for each validation data point of the validation amount, determining a quality level of the data-based system model and a distance value to a nearest training data point for each of the heterogeneous classes of variables. The distance value to the nearest training data point is determined separately with respect to a respective class of variables.

Method and apparatus for determining a distance metric for determining a distance dimension of heterogeneous data points

A system and computer-implemented method for training a machine learnable model to estimate a relative scale of objects in an image. A feature extractor and a scale estimator comprising a machine learnable model part are provided. The feature extractor may be pretrained, while the scale estimator may be trained by the system and method to transform feature maps generated by the feature extractor into relative scale estimates of objects. For that purpose, the scale estimator may be trained on training data in a specific yet non-supervised manner which may not require scale labels. During inference, the scale estimator may be applied to several image patches of an image. The resulting patch-level scale estimates may be combined into a scene geometry map which may be indicative of a geometry of a scene depicted in the image.

Training a machine learnable model to estimate relative object scale

A method for operating an injection valve by determining an opening or closing time of the injection valve based on a sensor signal. The method includes: providing an evaluation point time series by sampling a sensor signal of a sensor of the injection valve; using a non-linear data-based first sub-model to obtain a first output vector based on the evaluation point time series, wherein each element of the first output vector is associated with a specific time; using a linear, data-based second sub-model to obtain a second output vector based on the evaluation point time series, wherein each element of the second output vector is associated with a specific time; limiting the time determined by the first output vector depending on the second output vector in order to obtain the opening or closing time.

Method and device for operating a fuel injection valve with the aid of machine learning methods

A method for training a data-based evaluation model to determine an opening or closing time of an injection valve based on a sensor signal. The method includes: measuring an operation of the injection valve in order to determine at least one sensor signal and an associated opening or closing time; sampling the sensor signal at a sampling rate in order to obtain a sensor signal time series with sensor signal values; determining a plurality of training data sets by assigning a plurality of evaluation point time series generated from a sensor signal time series to the opening or closing time associated with the sensor signal, wherein the evaluation point time series has a lower temporal resolution than the sensor signal time series; training the data-based evaluation model depending on the determined training data sets.

Method and device for operating a fuel injection valve

A method for parameterizing a machine learning system, in particular a neural network, that is configured to ascertain in each case an associated class of a plurality of classes from input data. The machine learning system is trained once with correctly labeled training data, and once with not correctly labeled training data. Hyperparameters of the machine learning system are selected in such a way that the particular trained machine learning system may reproduce actual classifications of the correctly labeled training data better than actual classifications of the not correctly labeled training data.

Parameterization of a machine learning system for a control system

A method for recognizing at least one object in at least one input image. In the method, a template image of the object is processed by a first convolutional neural network (CNN) to form at least one template feature map; the input image is processed by a second CNN to form at least one input feature map; the at least one template feature map is compared to the at least one input feature map; it is evaluated from the result of the comparison whether and possibly at which position the object is contained in the input image, the convolutional neural networks each containing multiple convolutional layers, and at least one of the convolutional layers being at least partially formed from at least two filters, which are convertible into one another by a scaling operation.

Recognition of objects in images with equivariance or invariance in relation to the object size

A method for operating an injection valve by ascertaining an opening time and/or closing time of the injection valve on the basis of a sensor signal. The method includes: providing an analysis point time series by sampling a sensor signal of a sensor of the injection valve; using a nonlinear, data-based first submodel in order to obtain a first model output on the basis of the analysis point time series; using a linear, data-based second submodel in order to obtain a second model output on the basis of the analysis point time series; ascertaining the opening time and/or closing time as a function of the first and second model outputs.

Method and apparatus for operating a fuel injection valve with the aid of machine learning methods

A method for a plausibility check of the output of an artificial neural network (ANN) utilized as a classifier. The method includes: a plurality of images for which the ANN has ascertained an association with one or multiple classes of a predefined classification, and the association that is ascertained in each case by the ANN, are provided; for each image at least one feature parameter is determined which characterizes the type, the degree of specificity, and/or the position of at least one feature contained in the image; for each combination of an image and an association, a spatially resolved relevance assessment of the image is ascertained by applying a relevance assessment function; a setpoint relevance assessment is ascertained for each combination, using the feature parameter; a quality criterion for the relevance assessment function is ascertained based on the agreement between the relevance assessments and the setpoint relevance assessments.

Plausibility check of the output of neural classifier networks based on additional information about features

A method for ascertaining a depth information image for an input image. The input image is processed using a convolutional neural network, which includes multiple layers that sequentially process the input image, and each converts an input feature map into an output feature map. At least one of the layers is a depth map layer, the depth information image being ascertained as a function of a depth map layer. In the depth map layer, an input feature map of the depth map layer is convoluted with multiple scaling filters to obtain respective scaling maps, the multiple scaling maps are compared pixel by pixel to generate a respective output feature map in which each pixel corresponds to a corresponding pixel from a selected one of the scaling maps.

Method and device for ascertaining a depth information image from an input image

A computer-implemented method for reliably identifying objects in a sequence of input images received with the aid of an imaging sensor, positions of light sources in the respective input image being ascertained from the input images in each case with the aid of a first machine learning system, in particular, an artificial neural network, and objects from the sequence of input images being identified from the resulting sequence of positions of light sources, in particular, with the aid of a second machine learning system, in particular, with the aid of an artificial neural network.

Method and device for reliably identifying objects in video images

A computer-implemented method for ascertaining a closure point in time of an injector of an internal combustion engine using a classifier. The method includes: ascertaining a time series of input signals, each corresponding to a point in time within the time series, and each characterizing a deformation of the injector; ascertaining a plurality of first values using the classifier based on the time series, in each case a first value corresponding to a point in time of the time series, and the first value characterizing a probability that the closure point in time of the injector matches the point in time; ascertaining a plurality of second values, each being a sum of neighboring first values, of a first value and the first value, the second value corresponding to the point in time to which the first value corresponds; ascertaining the closure point in time based on the largest second value.

Growing community of inventors

Stuttgart, Germany

Konrad Groh