Classification of electromagnetic interference induced image noise in an analog video link
This work addresses inconsistency in EMI compliance testing for automotive analog camera links, but it is incremental as it applies existing deep learning methods to a specific domain problem.
The paper tackles the problem of manually assessing electromagnetic interference (EMI) noise in analog video links for automotive compliance testing, which is inconsistent, by proposing deep learning models that classify EMI noise levels using real test image data, achieving classification with trained models based on AlexNet.
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