Do vehicles sense pavement surface anomalies?

Abstract

Nowadays, pavement monitoring agencies typically assess pavement quality approximately only once per year. The main reason for this low frequency of inspections is the fact that current methods are expensive and laborious. The paper presents a data-driven framework and related field studies on the use of pattern recognition techniques and smartphone sensor technologies for the detection, classification and georeferencing of roadway pavement surface anomalies. The proposed system provides continuous and reliable information about the five most common roadway pavement surface anomalies which are valuable for pavement management systems and public safety.

Spatial Roadway Condition-Assessment Mapping Utilizing Smartphones and Machine Learning Algorithms

“…Vehicle system data can be transmitted through the OBD reader to the smartphone device and then transferred for either processing or storing, via a digital cellular connection or other means (11)(12)(13). Further, visual verification of the existence of a pavement surface anomaly, the smartphone also has its video camera active for recording the routes traveled (12). Mathematically, the proposed method is based on rigid-body dynamics (Figure 2) and the underlying premise that any three-dimensional rotation can be described as a sequence of yaw, pitch, and roll rotations (11).…”

“…The paper focuses on the detection of pavement patches and potholes, in three different sections of roadways (of 5 km total distance, ∼10 data points per geographical location, 290 data points of no defect condition, 152 data points of longitudinal patches, and 329 data points of transverse patches and 428 data points of potholes), which are examined in tandem, albeit being part of a larger effort on the detection of vibration-inducing pavement anomalies, as documented in Kyriakou and Christodoulou ( 11 ) and Kyriakou et al ( 1 , 10 , 12 , 13 ). According to the Federal Highway Administration (FHWA), patches are original surface repaired with new asphalt material and potholes are holes or loss of pavement material caused by traffic loading, fatigue, and inadequate strength ( 14 ).…”

“…According to the Federal Highway Administration (FHWA), patches are original surface repaired with new asphalt material and potholes are holes or loss of pavement material caused by traffic loading, fatigue, and inadequate strength ( 14 ). Data on these types of pavement surface anomalies are collected in-situ by use of a car equipped with a smartphone (mounted on the car’s windshield) and with an OBD reader attached to it ( 12 ). The smartphone was also fitted with the DashCommand™ application for recording (and exporting) data from smartphone accelerometer and gyroscope sensor readings.…”

“…The smartphone was also fitted with the DashCommand™ application for recording (and exporting) data from smartphone accelerometer and gyroscope sensor readings. Vehicle system data can be transmitted through the OBD reader to the smartphone device and then transferred for either processing or storing, via a digital cellular connection or other means ( 11–13 ). Further, visual verification of the existence of a pavement surface anomaly, the smartphone also has its video camera active for recording the routes traveled ( 12 ).…”

“…The smartphone’s roll and pitch values can be associated with the host car’s roll and pitch values. The roll metric refers to a car’s acceleration variation between its left and right front wheels, while the pitch metric refers to a car’s acceleration variation between its front and rear wheels ( 11 , 12 ). Concurrently, the roll and pitch values define how the host car is off balance (sideways and front/back) ( 11 , 12 ).…”