Self-classification of neural networks

A method of classifying objects detected with n (n=2,3…) artificial neural networks in at least one image either as a reliably detected object or as an unreliably detected object,

• wherein objects contained in the image are detected using a computing unit applying n neural networks, and
• each detected object is assigned to a defined object class or an undefined object class,
• wherein an IoU value is created for each object selected and detected with each neural network,
• wherein:
• a detected object is classified as a confident object with the computing unit,
• if the object is assigned to the same defined object class with a number of neural networks greater than or equal to a first default value and which object has an IoU value greater than or equal to a threshold value, or
• the computing unit classifies a detected object as an uncertain object if the object is assigned to the same defined object class with a number of neural networks less than a first preset value, or
• the object is assigned to an undefined object class with a number of neural networks greater than or equal to a second default value, which object has an IoU value less than a threshold value, wherein the first default value and the second default value are less than or equal to the number of neural networks.