Abstract: A method for an artificial neural network including: providing the artificial neural network, wherein the artificial neural network is trained to reduce the confidence of the artificial neural network in classifying inputs outside a desirable input distribution is provided by training the artificial neural network using a first set of inputs and associated labels, the labels correctly classifying the corresponding inputs, wherein the inputs within the first set are within the desirable input distribution of the artificial neural network; training the artificial neural network using a second set of inputs and associated labels, wherein the inputs within the second set are outside of the desirable input distribution of the artificial neural network, and wherein the labels within the second set comprise randomly assigned classifications; and feeding one or more inputs through the artificial neural network to determine classifications, classifying the inputs, and confidence values associated with the classificati

Abstract: An apparatus for recognizing a license plate of a vehicle, the apparatus having an interface for reading-in an image of a surrounding of an optical sensor, the image originating from the optical sensor picturing at least the vehicle having a detectable license plate. The apparatus further comprises a unit for analyzing the image using a convolutional neural network, the convolutional neural network having at least two separated symbol identification branches, each of the separated symbol identification branches being configured for identifying one of several symbols of the license plate and/or the convolutional neural network having a country identification branch being separated from the symbol identification branches, the country identification branch being configured for identifying the country having issued the license plate.

Abstract: An apparatus for recognizing a license plate of a vehicle, the apparatus having an interface for reading-in an image of a surrounding of an optical sensor, the image originating from the optical sensor picturing at least the vehicle having a detectable license plate. The apparatus further comprises a unit for analyzing the image using a convolutional neural network, the convolutional neural network having at least two separated symbol identification branches, each of the separated symbol identification branches being configured for identifying one of several symbols of the license plate and/or the convolutional neural network having a country identification branch being separated from the symbol identification branches, the country identification branch being configured for identifying the country having issued the license plate.

Abstract: In a process for reducing the data rate of motion vector information, the components of the motion vectors are quantised, the quantised values are compressed and transmitted and the quantisation errors are additionally transmitted, whenever sufficient channel capacity is available. When not transmitted, the quantisation errors may be recreated at the encoder receiving the transmission. Where appropriate vectors may be translated to equivalent velocity values and passed through a linear transform, further reducing the required bit capacity.