The invention provides a vehicle neural network. A system includes a processor and a memory including instructions executable by the processor to: train a deep neural network based on a plurality of real-world images; determining that an accuracy of the deep neural network is below a threshold based on identifying, by the deep neural network, one or more physical features including one or more object types in the plurality of real-world images; and generating a plurality of composite images using a realistic image rendering software program and a generative adversarial network based on determining that the accuracy of the deep neural network is below a threshold from identifying the one or more physical features. The instructions may include additional instructions to retrain the deep neural network based on the plurality of real-world images and the plurality of composite images and output the retrained deep neural network.
本公开提供了“车辆神经网络”。一种系统,其包括处理器和存储器,所述存储器包括可由所述处理器执行以进行以下操作的指令:基于多个真实世界图像来训练深度神经网络;基于通过所述深度神经网络识别在所述多个真实世界图像中的包括一个或多个对象类型的一个或多个物理特征来确定所述深度神经网络的准确度低于阈值;以及基于根据识别所述一个或多个物理特征确定所述深度神经网络的所述准确度低于阈值,使用真实感图像渲染软件程序和生成式对抗网络来生成多个合成图像。所述指令可以包括另外的指令:基于所述多个真实世界图像和所述多个合成图像重新训练所述深度神经网络以及输出所述重新训练的深度神经网络。
Vehicle neural network
车辆神经网络
2022-04-08
Patent
Electronic Resource
Chinese
IPC: | G06V / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR / G06K Erkennen von Daten , RECOGNITION OF DATA |