The invention relates to a method for training an artificial neural network using training data comprising first image data of a first image of an infrastructure and second image data of a second image, wherein the first image comprises a first feature and wherein the second image comprises a second feature corresponding to the first image, and wherein the training data comprises a target relative translation and a target relative rotation between the first feature and the second feature, a first feature is extracted from the first image and a second feature is extracted from the second image, the extracted first feature is represented by first feature data having a first data amount, the extracted second feature is represented by second feature data having a second data amount, and the first feature data and the second feature data are extracted by means of an artificial neural network. Determining a relative translation and a relative rotation between the extracted first feature and the extracted second feature, where the artificial neural network is always trained, the method is carried out until a loss function related to the attitude of the feature and related to the first data volume and/or the second data volume has a minimum value or is less than or equal to a predetermined loss function threshold value. The invention relates to an artificial neural network, to a method for extracting features from images of the surroundings of a motor vehicle, to a device, to a computer program and to a machine-readable storage medium.

    本发明涉及一种用于在使用训练数据的情况下训练人工神经网络的方法,这些训练数据包括基础设施的第一图像的第一图像数据和第二图像的第二图像数据,其中第一图像包括第一特征而且其中第二图像包括与该第一图像相对应的第二特征,其中这些训练数据包括在该第一特征与该第二特征之间的目标相对平移和目标相对旋转,其中该训练包括:借助于人工神经网络,从第一图像中提取第一特征并且从第二图像中提取第二特征,其中通过具有第一数据量的第一特征数据来表示所提取的第一特征,其中通过具有第二数据量的第二特征数据来表示所提取的第二特征,借助于人工神经网络,确定在所提取的第一特征与所提取的第二特征之间的相对平移和相对旋转,其中该人工神经网络一直被训练,直至与特征的姿态有关并且与该第一数据量和/或该第二数据量有关的损失函数具有最小值或者小于或小于等于预先给定的损失函数阈值为止。本发明涉及一种人工神经网络、一种用于从机动车辆的周围环境的图像中提取特征的方法、一种设备、一种计算机程序和一种机器可读存储介质。


    Access

    Download


    Export, share and cite



    Title :

    Method for training artificial neural network


    Additional title:

    用于训练人工神经网络的方法


    Contributors:

    Publication date :

    2022-12-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion



    METHOD FOR TRAINING AN ARTIFICIAL NEURAL GENERATOR NETWORK, METHOD FOR TRAINING AN ARTIFICIAL NEURAL DISCRIMINATOR NETWORK, AND TEST UNIT

    BANNENBERG SEBASTIAN / LORENZ FABIAN / RASCHE RAINER | European Patent Office | 2021

    Free access


    Adaptive Signal Control Expert by Artificial Neural Network Training

    Chang, A. T. S. / IEEE / Vehicular Technology Society | British Library Conference Proceedings | 1995