Adaptable Accelerometer Signal Processing Pipelines for Smartphone based Evenness Estimation

Abstract Evenness is an essential indicator of road quality. Accelerometer sensors in smartphones offer an accessible and cost-efficient solution for monitoring road evenness. However, the accelerometer signal from smartphones is influenced by various internal and external factors beyond the road’s actual evenness. External factors, in particular, can introduce systematic bias due to differences in vehicle suspension or smartphone mounting methods. In this study, we investigate specific external factors affecting windshield-mounted smartphones and propose a method to automatically adapt accelerometer processing pipelines, improving robustness against such external influences.