=Paper=
{{Paper
|id=Vol-3058/paper63
|storemode=property
|title=A Survey On Smartphone-Based Road Condition Detection Systems
|pdfUrl=https://ceur-ws.org/Vol-3058/Paper-094.pdf
|volume=Vol-3058
|authors=Rishu Chhabra,Saravjeet Singh
}}
==A Survey On Smartphone-Based Road Condition Detection Systems==
https://ceur-ws.org/Vol-3058/Paper-094.pdf
A survey on smart phone-based road condition detection systems
Rishu Chhabra1 and Saravjeet Singh2
1,2
Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India.
Abstract
With the advancement in technology, Intelligent Transportation Systems (ITS) aims to maximize
the safety and convenience of the transportation system. It focuses on the integration of
technology into the traditional transportation structure for future smart cities. With the
proliferation of the road network in all nations across the world, road surface condition data has
become a critical component in reducing road accidents. Road condition monitoring is an
important part of transportation management and affects the safety of the commute. Different
methods based on manual, automatic, and semi-automatic monitoring of road conditions have
been proposed in the literature. In this paper, we present a survey of smartphone-based road
condition monitoring techniques. The data is acquired using smartphones and the algorithms
discussed detect the road anomalies like manholes, speed bumps, potholes, and cracks, etc. A
comparative analysis has been carried out based on the benefits, drawbacks, and methods used by
various techniques. Furthermore, new research directions for smartphone-based detection of road
surface anomalies have been presented.
Keywords *
ITS, pothole, road condition, smartphone, speed bump
1. Introduction
The monitoring of road surface conditions has grown increasingly crucial in recent years. Road surfaces
that are well-maintained improve road user safety and comfort. As a result, it is critical to regularly
monitor road conditions in order to improve the transportation system's driving safety.The density of road
surface anomalies is one of the key indicators used to identify road surface conditions [1]. Statistical data
obtained from collected road surface information, visual field inspections, or vehicles equipped with
special devices that measure and monitor road surface conditions are commonly used by
municipalities. However, these technologies are time-consuming, expensive, and frequently lack the data
coverage needed to provide a comprehensive picture of road conditions in large cities. Therefore, there is
a needfor a low-cost, and efficient automatic or semi-automatic road surface detection technology.With
the support of the Internet of Things (IoT), Intelligent Transportation Systems (ITS) employs different
communication technologies to the traditional transportation system and improves the safety of road users
[2], [3]. All decisions are made based on the raw data acquired by sensors or special equipment, so the
data collecting step is critical.Different technologies employing laserscanners, video cameras, vibration-
based approaches, and smartphone-based approaches are being used for data collection pertaining to road
surface conditions. Smartphone-based detection has emerged as a significant supplemental technology for
identifying road surface abnormalities [4].
International Conference on Emerging Technologies: AI, IoT, and CPS for Science & Technology Applications, September 06–07, 2021,
NITTTR Chandigarh, India
EMAIL: rishu.miglani@chitkara.edu.in (A. 1); rishuchh@gmail.com (A. 2);
ORCID: Not Available (A. 1); Not Available (A. 2);
©2021 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR Workshop Proceedings (CEUR-WS.org)
Figure 1shows the statistics of the five countries with the world's largest road networks in terms
of road network, population, and smartphone users [5]–[7]. It is evident that a good percentage of
the population owns a smartphone. Therefore, smartphone-based road condition detection
techniques could benefit the majority of road users without any additional investment.
14
12
10
Road Network Length (million kms)
8
Population (hundred millions)
6
Smartphone users (hundred millions)
4
2
0
Russia Brazil India China U.S
Figure 1: Road network and smartphone user’s analysis
Figure2 shows the process of smartphone-based road condition detection process. Data collected by
smartphone inbuilt sensors is filtered and processed for anomaly detection and then an alert is generated
on the smartphone. In this paper, we focus on smartphone-based road condition detection techniques that
detect several road anomalies like speed breakers, potholes, manholes, and road cracks etc. based on the
data acquired using a mobile smartphone. Section 2 discusses the various state-of-the-art smartphone-
based road condition detection techniques followed by a comparative analysis. Section-3 concludes the
work with future research directions.
Figure 2: Smartphone-based road condition detection process
2. Smartphone-based Road condition detection techniques
Based on the technique used for data processing for road anomaly detection, the smartphone-based road
condition detection techniques presented in this paper have been classified into twocategories: threshold
based and machine learning based techniques.
2.1 Threshold based techniques
The sensor data acquired using a smartphone is analyzed to identify the patterns or values that represent
the unfavorable road conditions. Different approaches have been proposed in the literature that apply
thresholds to the accelerometer Z-axis data that represents vertical acceleration. Thresholding on the value
of the absolute difference of accelerometer Z-axis data to detect road anomalies has been proposed in [8]–
[10].The technique presented in [11] employed thresholding along with signal and image processing
techniques and yields an accuracy of 93% for road anomaly detection. To overcome the limitations of
static thresholding, adaptive thresholding has been employed in [12]to detect potholeswith an accuracy
measurebetween 94-99%.Another technique to apply threshold on roughness index to identify road ruts
has been proposed in [13]. The accuracy of the proposed method is 94%.
2.2 Machine learning based techniques
The researchers have employed various supervised and unsupervised machine learning techniques to
process the data acquired using smartphones and identify the unfavorable road conditions. The supervised
learning technique to detect road anomalies has been employed in[14]–[16]. To improve the accuracy
measure, the techniques proposed by the authors have been enhanced by neural networks or signal
processing techniques. The signal processing approach of Dynamic Time Warping (DTW) has been used
in [17]and the system detects road bumps and potholes with 88% accuracy. In [18], authors employed
deep learning techniques for object detection using the images captured by a smartphone. The proposed
technique detects potholes approximately 100m ahead enhancing the safety of road users to great extent.
A pothole detection technique based onConvolutional Neural Network (CNN) has been proposed in [19].
The proposed system yields 97% accuracy and uses Google API to map the detected pothole on Google
Maps.
Table-1 provides the comparative analysis of the different smartphone-based state-of-the-art road
condition detection techniques based on their advantages and disadvantages.
Table 1:
Comparison of smartphone-based road condition detection techniques
Ref & Technique employed Road Advantages Disadvantages
Year Condition
detected
[20] Comparison of Pothole Advanced real-time No auto-calibration of the
(2011) STDEV(Z), ZThresh, Z- pothole detection accelerometer
DIFF, with limited hardware
and G-ZERO and software
resources
[21] Analysis of amplitude Road bump/ Simple The performance is
(2012) of accelerometer Speed-breaker implementation and dependent on type of the
readings optimum battery vehicle
usage
[22] Thresholding on Road bump Road condition The smartphonemust be
(2012) accelerometer Z-axis and pothole classification into fixed at a particular position
data large range of on floorboard for accurate
categories results.
[11] Z-DIFF and Multi- Speed bump Flexible and fast The algorithm is sensitive to
(2013) modal sensor analysis and potholes implementation with the shape of the road
visual output anomaly
[9] Temporal derivative Road bump Auto- The smartphone must be
(2014) of Z-DIFF and potholes calibration/orientation fixed to the dashboard
of the accelerometer
data
[12] Adaptive thresholding Potholes Reduced pothole Algorithm requires more
(2015) location computational power
determination errors
using GPS data
[10] Threshold-based Speed bump Early warning is No auto-calibration of the
(2015) approach on data and road pits generated with an accelerometer and reduced
from accelerometer accuracy measure of performance in case of highly
80% rough road segment
[14] Support Vector Speed bump The technique is The results have been
(2011) Machine (SVM) and potholes independent of the formulated using limited
speed of the vehicle data from few drivers
[23] K-means clustering Classify road as The study generates The machine learning model
(2012) algorithm smooth or good training data needs to be improved for
bumpy reducing the false positives
[24] Machine learning Road surface High accuracy for two Not efficient when the
(2013) technique: Multi- conditions: classes of road system encounters a greater
Layer Perceptron manholes and anomalies/events number of road anomalies in
(MLP). cracks a small area
[15] SVM for classification Classify road Identify the road The system did not efficiently
(2014) anomalies anomalies for wider for inclined road segments
road segments as well
with 90% accuracy
[25] SVM Speed bump Reduced false Less detection accuracy
(2015) positives as
accelerometer results
have been
validatedusing
gyroscope readings
[26] Image processing Pothole Highly accurate in The system is dependent on
(2015) algorithm detection and ideal environmental the surrounding
classification conditions environmental conditions at
of road the time of image capture
anomalies
[17] Dynamic Time Road bump Less complex, fast and The performance is reduced
(2017) Warping (DTW) and pothole detection accuracy is on roads with more road
not affected by anomalies in a small area
varying vehicle speed
[27] Gaussian Model Speed bump The algorithm is The system identifies the
(2017) and potholes computationally severity of the road anomaly
efficient when vehicle speed is 15-20
kmph
[28] Decision tree Pothole and Mapping of road The classifier can be
(2017) classification smooth road anomalies to the map. improved for other road
algorithm detection More accurate road anomalies and road type
anomaly detection
using data from
accelerometer and
gyroscope.
[29] Supervised machine Speed bump, The inclusion of data The accelerometer data is
(2017) learning technique potholes, and mining algorithms the input to the feature
manholes alleviates problems extraction algorithm. It
related to vehicle should be combined with
speed gyroscope data for validation
[30] Mahalanobis- Taguchi Manhole The system considers Overlap between the
(2018) System (MTS) cover, pothole, different characteristics of pothole
and speed characteristics of road and covered manhole leads
bump conditions and to increase in pothole
predicts road quality detection error rate
accurately
[16] SVM, Neural Cracks and Multi-class Real-time detection by
(2019) Networks: potholes classification placing smartphone at
Supervised machine technique that different locations was not
learning techniques considers relationship done.
between the acquired
data from different
dimensions
[31] Deep learning Road ravels, Road anomaly severity More computational power
(2020) technique cracks, is also calculated is required at the time of
potholes, and model creation
manholes
[32] KNN and Improved Speed bumps The algorithm adapts The algorithm can be
(2020) Gaussian Model and potholes according to the improved for other road
vehicle speed thus anomalies and severity of the
improving the detected anomaly
accuracy of the
system
[33] Decision Tree: Speed Improved The system accuracy reduces
(2020) machine learning breakers and performance as data for rough road surface
technique potholes considered from auto- conditions
oriented
accelerometer is
combined with
gyroscopedata.
Different types of
vehicles were
considered for
performance
evaluation.
[18] Deep learning object Potholes The range of detection Constrained by illumination
(2021) detection technique: is 100 m and alert conditions
YOLOv4 generated ahead of
time.
3. Conclusions and future research directions
The smartphone-based road condition detection techniques provide a cost-effective solution using a
pervasive device i.e., a smartphone. However, there are certain challenges associated with the
implementation of smartphone-based systems like the placement of smartphone in the vehicle and
differentiation between different types of road conditions. Different threshold based and machine learning
based techniques have been proposed in the literature for road condition detection. However, to take the
advantage of computationally efficient threshold-based technique and highly accurate machine-learning
based approach; a hybrid technique needs to be developed to identify road conditions keeping in view the
implementation cost. The communication between vehicles to transmit road condition information before
hand for safety and convenience could be another area of interest. The generation of dynamic maps with
updated road-condition information can be also used by authorities to streamline maintenance works.
4. References
[1] M. Strutu, G. Stamatescu, and D. Popescu, “A mobile sensor network based road surface
monitoring system,” in 2013 17th International Conference on System Theory, Control and
Computing (ICSTCC), 2013, pp. 630–634.
[2] A. S. El-Wakeel, J. Li, A. Noureldin, H. S. Hassanein, and N. Zorba, “Towards a practical
crowdsensing system for road surface conditions monitoring,” IEEE Internet Things J., vol. 5, no.
6, pp. 4672–4685, 2018.
[3] Z. Han, J. Liang, and J. Li, “Design of Intelligent Road Recognition and Warning System for
Vehicles Based on Binocular Vision,” IEEE Access, vol. 6, pp. 62880–62889, 2018.
[4] S. Sattar, S. Li, and M. Chapman, “Road surface monitoring using smartphone sensors: A review,”
Sensors, vol. 18, no. 11, p. 3845, 2018.
[5] “The world’s biggest road networks.” 2014.
[6] “Countries with the largest population 2019 | Statista.” 2019.
[7] “Smartphone users by country 2021 | Statista.” 2021.
[8] A. Sinharay, S. Bilal, A. Pal, and A. Sinha, “Low computational approach for road condition
monitoring using smartphones,” in Proceedings of the Computer Society of India (CSI) Annual
Convention, Theme: Intelligent Infrastructure, Visakhapatnam, India, 2013, pp. 13–15.
[9] A. Vittorio, V. Rosolino, I. Teresa, C. M. Vittoria, P. G. Vincenzo, and D. M. Francesco,
“Automated sensing system for monitoring of road surface quality by mobile devices,” Procedia-
Social Behav. Sci., vol. 111, no. 5, pp. 242–251, 2014.
[10] G. Sebestyen, D. Muresan, and A. Hangan, “Road quality evaluation with mobile devices,” in
Proceedings of the 2015 16th International Carpathian Control Conference (ICCC), 2015, pp.
458–464.
[11] F. Orhan and P. E. Eren, “Road hazard detection and sharing with multimodal sensor analysis on
smartphones,” in 2013 Seventh International Conference on Next Generation Mobile Apps,
Services and Technologies, 2013, pp. 56–61.
[12] H.-W. Wang, C.-H. Chen, D.-Y. Cheng, C.-H. Lin, and C.-C. Lo, “A real-time pothole detection
approach for intelligent transportation system,” Math. Probl. Eng., vol. 2015, 2015.
[13] T. Nomura and Y. Shiraishi, “A method for estimating road surface conditions with a
smartphone,” Int. J. Informatics Soc., vol. 7, no. 1, pp. 29–36, 2015.
[14] M. Perttunen et al., “Distributed road surface condition monitoring using mobile phones,” in
International conference on ubiquitous intelligence and computing, 2011, pp. 64–78.
[15] F. Seraj, B. J. van der Zwaag, A. Dilo, T. Luarasi, and P. Havinga, “RoADS: A road pavement
monitoring system for anomaly detection using smart phones,” in Big data analytics in the social
and ubiquitous context, Springer, 2015, pp. 128–146.
[16] A. Basavaraju, J. Du, F. Zhou, and J. Ji, “A Machine Learning Approach to Road Surface
Anomaly Assessment using Smartphone Sensors,” IEEE Sens. J., vol. 20, no. 5, pp. 2635–2647,
2019.
[17] G. Singh, D. Bansal, S. Sofat, and N. Aggarwal, “Smart patrolling: An efficient road surface
monitoring using smartphone sensors and crowdsourcing,” Pervasive Mob. Comput., vol. 40, pp.
71–88, 2017.
[18] A. Al Shaghouri, R. Alkhatib, and S. Berjaoui, “Real-Time Pothole Detection Using Deep
Learning.” 2021.
[19] S. Patra, A. I. Middya, and S. Roy, “PotSpot: Participatory sensing based monitoring system for
pothole detection using deep learning,” Multimed. Tools Appl., pp. 1–25, 2021.
[20] A. Mednis, G. Strazdins, R. Zviedris, G. Kanonirs, and L. Selavo, “Real time pothole detection
using android smartphones with accelerometers,” in Proceedings of the International Conference
on Distributed Computing in Sensor Systems and Workshops (DCOSS), 2011, pp. 1–6.
[21] M. Jain, A. P. Singh, S. Bali, and S. Kaul, “Speed-breaker early warning system,” in Proceedings
of the 6th {USENIX/ACM} Workshop on Networked Systems for Developing Regions, NSDR’12,
Boston, MA, USA, June, 2012.
[22] M. Fazeen, B. Gozick, R. Dantu, M. Bhukhiya, and M. C. González, “Safe driving using mobile
phones,” IEEE Trans. Intell. Transp. Syst., vol. 13, no. 3, pp. 1462–1468, 2012.
[23] R. Bhoraskar, N. Vankadhara, B. Raman, and P. Kulkarni, “Wolverine: Traffic and road condition
estimation using smartphone sensors,” in Proceedings of the Fourth International Conference on
Communication Systems and Networks (COMSNETS), 2012, pp. 1–6.
[24] L. C. González-Gurrola, F. Mart\’\inez-Reyes, and M. R. Carlos-Loya, “The citizen road watcher--
identifying roadway surface disruptions based on accelerometer patterns,” in Ubiquitous
computing and ambient intelligence. Context-awareness and context-driven interaction, Springer,
2013, pp. 374–377.
[25] A. Mohamed et al., “RoadMonitor: An intelligent road surface condition monitoring system,” in
Intelligent Systems’ 2014, Springer, 2015, pp. 377–387.
[26] D. Rajamohan, B. Gannu, and K. S. Rajan, “MAARGHA: a prototype system for road condition
and surface type estimation by fusing multi-sensor data,” ISPRS Int. J. Geo-Information, vol. 4,
no. 3, pp. 1225–1245, 2015.
[27] P. M. Harikrishnan and V. P. Gopi, “Vehicle vibration signal processing for road surface
monitoring,” IEEE Sens. J., vol. 17, no. 16, pp. 5192–5197, 2017.
[28] A. Allouch, A. Koubâa, T. Abbes, and A. Ammar, “Roadsense: Smartphone application to
estimate road conditions using accelerometer and gyroscope,” IEEE Sens. J., vol. 17, no. 13, pp.
4231–4238, 2017.
[29] N. Silva, J. Soares, V. Shah, M. Y. Santos, and H. Rodrigues, “Anomaly detection in roads with a
data mining approach,” Procedia Comput. Sci., vol. 121, pp. 415–422, 2017.
[30] H. Wang, N. Huo, J. Li, K. Wang, and Z. Wang, “A road quality detection method based on the
mahalanobis-taguchi system,” IEEE Access, vol. 6, pp. 29078–29087, 2018.
[31] R. Roberts, G. Giancontieri, L. Inzerillo, and G. Di Mino, “Towards Low-Cost Pavement
Condition Health Monitoring and Analysis Using Deep Learning,” Appl. Sci., vol. 10, no. 1, p.
319, 2020.
[32] R. Du, G. Qiu, K. Gao, L. Hu, and L. Liu, “Abnormal Road Surface Recognition Based on
Smartphone Acceleration Sensor,” Sensors, vol. 20, no. 2, p. 451, 2020.
[33] M. Y. Alam et al., “Crowdsourcing from the True crowd: Device, vehicle, road-surface and
driving independent road profiling from smartphone sensors,” Pervasive Mob. Comput., vol. 61, p.
101103, 2020.