Pavement Condition Index Estimation Using Smartphone Based Accelerometers for City of Houston

Pavement condition monitoring is important for scheduling maintenance activities. Approaches to gathering pavement condition data can vary from visual inspection techniques to using advanced pavement profilers. Common shortcomings of these include high costs and high skill requirements. Another method is to use accelerometer data collected from smartphones to estimate the pavement condition. In this research, an Android application is developed to use acceleration vibration to estimate road condition. Fourteen pavement sections were selected on which to conduct test runs. Pavement condition index (PCI) data from city of Houston road network database is used to train the estimation model in the Android application. Multiple linear regression models were proposed using statistics extracted from acceleration data as explanatory variables. Furthermore, to test the repeatability of observations, two random pavement sections were selected to perform three test runs. It is observed that, except for standard deviation and variance among vertical acceleration data, other statistics showed high repeatability. Results from this research show that acceleration vibration has a good linear relationship with PCI (R-2 value 0.85 to 0.9). The results of this study can be useful for low-cost continuous monitoring of road network conditions.