Abstract: A method is for the classification of temporally sequential digital audio data that describe acoustic signals that identify hazardous situations. The method includes calculating a large number of frequency spectrograms for stepwise progressive time intervals of the temporally sequential audio data, and forming a specific number of frequency segments for each octave of each individual frequency spectrogram. The frequency segments include a subset of the individual frequency spectrograms. The method further includes adding corresponding frequency segments of the octaves of each individual frequency spectrogram, calculating frequency components through the formation of mean values for the individual, added frequency segments in each individual frequency spectrogram, and generating a classification vector using a classifier and the number of frequency components of the large number of frequency spectrograms.

Abstract: A method recognizes an object in a surroundings of a vehicle. The vehicle has an ultrasonic sensor for monitoring the surroundings of the vehicle and for the transmission and reception of ultrasonic signals. In the method, sensor data generated by the ultrasonic sensor are received. Classification data that contain features to be classified, are subsequently generated from the sensor data. The classification data and/or the sensor data are hereupon entered into a classifier that has been trained with training data for assigning the classification data and/or the sensor data to object classes. Object information that indicates at least one of the object classes is output.

Abstract: A method is for the classification of temporally sequential digital audio data that describe acoustic signals that identify hazardous situations. The method includes calculating a large number of frequency spectrograms for stepwise progressive time intervals of the temporally sequential audio data, and forming a specific number of frequency segments for each octave of each individual frequency spectrogram. The frequency segments include a subset of the individual frequency spectrograms. The method further includes adding corresponding frequency segments of the octaves of each individual frequency spectrogram, calculating frequency components through the formation of mean values for the individual, added frequency segments in each individual frequency spectrogram, and generating a classification vector using a classifier and the number of frequency components of the large number of frequency spectrograms.