Embracing Crowdsensing: An Enhanced Mobile Sensing Solution for Road Anomaly Detection

Abstract

Road anomaly detection is essential in road maintenance and management; however, continuously monitoring road anomalies (such as bumps and potholes) with a low-cost and high-efficiency solution remains a challenging research question. In this study, we put forward an enhanced mobile sensing solution to detect road anomalies using mobile sensed data. We first create a smartphone app to detect irregular vehicle vibrations that usually imply road anomalies. Then, the mobile sensed signals are analyzed through continuous wavelet transform to identify road anomalies and estimate their sizes. Next, we innovatively utilize a spatial clustering method to group multiple driving tests’ results into clusters based on their spatial density patterns. Finally, the optimized detection results are obtained by synthesizing each cluster’s member points. Results demonstrate that our proposed solution can accurately detect road surface anomalies (94.44%) with a high positioning accuracy (within 3.29 meters in average) and an acceptable size estimation error (with a mean error of 14 cm). This study suggests that implementing a crowdsensing solution could substantially improve the effectiveness of traditional road monitoring systems.

Crowdsensing – a new approach to road quality assessment

“…Када се прикупе подаци, следи њихова обрада. У студијама Ли и Голдберг [22] и Чен и сарадници [24] сензорски прикупљени подаци су обрађени путем дефинисаног прага детекције док су у студијама Ли и Голдберг [25] и Ел-Вакел и сарадници [23] сензорски подаци обрађени на бази приступа таласне анализе. У свим студијама аутори наводе да су добијени резултати углавном поуздани али у студији Ли и Голдберг [25] аутори објашњавају да су резултати добијени применом таласне анализе показали висок степен тачности и поузданости.…”

“…У студијама Ли и Голдберг [22] и Чен и сарадници [24] сензорски прикупљени подаци су обрађени путем дефинисаног прага детекције док су у студијама Ли и Голдберг [25] и Ел-Вакел и сарадници [23] сензорски подаци обрађени на бази приступа таласне анализе. У свим студијама аутори наводе да су добијени резултати углавном поуздани али у студији Ли и Голдберг [25] аутори објашњавају да су резултати добијени применом таласне анализе показали висок степен тачности и поузданости. У студијама Ли и Голдберг [25] и Ел-Вакел и сарадници [23] [25] сугеришу да је квалитет сензора на савременим возилима далеко већи и да они сакупљају хиљаде сигнала путем технологије магистралне мреже на подручју контролера CAN (енгл.…”

An Automated Machine-Learning Approach for Road Pothole Detection Using Smartphone Sensor Data

“…Basavaraju et al examined the differences between using features from all axes and features from the Y -axis only to investigate the possibility of using single-axis data. Li et al [ 25 ] were the first to apply the continuous Wavelet transform to feature extraction in pothole detection; they proposed a novel solution for estimating the pothole size.…”

Quality Estimation for Scarce Scenarios Within Mobile Crowdsensing Systems

“…Processing is a fundamental element of the MCS campaign, as it is the means by which data becomes useful, and by which inferences -and thus insights -about the sensed phenomena are obtained. Pre-processing [54][55][56][57] refers to the preliminary treatment of the contributed data. The purpose of the preprocessing step is to ensure that the data is 2.1 The Communication Layer consistent in later steps.…”

“…Opportunistic sensing [21,57,73], on the other hand, is an approach in which sensing is done passively. As a result, opportunistic sensing often employs context-awareness to evaluate the conditions required to execute the task [21,54].…”