A method for associating a traffic light detection for an at least partially autonomous motor vehicle, as well as an assistance system

The invention relates to a method for associating a traffic light 10 detection for an at least partially autonomous motor vehicle 12 by an assistance system 14 of the motor vehicle 12. The traffic light 10 is detected by a capturing device and analyzed by an electronic computing device, and wherein depending on the analysis, the traffic light 10 is associated with a mission lane 28 of the motor vehicle 12, characterized in that for the analyzing step, a convolutional neural network is used by the electronic computing device, wherein the convolutional neural network classifies the traffic light 10, and depending on the classification the association is performed. The convolutional neural network may be provided with a pooling layer, a dropout layer, a fully-connected layer, a batch normalization layer and a softmax layer.