Classification of electromagnetic interference induced image noise in an analog video link

With the ever-increasing electrification of the vehicle showing no sign of retreating, electronic systems deployed in automotive applications are subject to more stringent Electromagnetic Immunity compliance  constraints than ever before, to ensure the proximity of nearby electronic systems will not affect their operation. The EMI compliance testing of an analog camera link requires video quality to be monitored and  assessed to validate such compliance, which up to now, has been a manual task. Due to the nature of human  interpretation, this is open to inconsistency. Here, we propose a solution using deep learning models that  analyse, and grade video content derived from an EMI compliance test. These models are trained using a dataset built entirely from real test image data to ensure the accuracy of the resultant model(s) is maximised. Starting with the standard AlexNet, we propose four models to classify the EMI noise level.