Vision based feature diagnosis for automobile instrument cluster using machine learning

This papers deals with an advanced and effective approach for testing system, by utilizing the hardware-in-the-loop (HIL) with the vision based machine learning technique to make end to end automation in the feature diagnosis and validation of automotive instrument clusters. Recently, numerous HIL systems are in practice for simulating the vehicle networks in real time, by providing necessary signals based on the test cases. There are many approaches to tap the signal from the instrument cluster before it gets displayed, and based on the test case the signal that is captured will be compared with the expected value. The current approaches deal only at the software level and fails in identifying the faults in the end display unit of cluster. The proposed method uses vision based machine learning system to monitor the cluster visually thereby identifying faults in cluster at the end product level. This approach greatly eases the task of testing for more number of units by making onerous repeated test without any human intervention, as the current testing method needs human approval for each and every test case which is tedious task to do.