The pothole patrol: using a mobile sensor network for road surface monitoring

By Jakob Eriksson, Lewis Girod, Bret Hull, R. Newton, Samuel Madden, Hari Balakrishnan. ACM SIGMOBILE International Conference on Mobile Systems, Applications, and Services, 2008

1,274 citations recorded by the source corpus.

This paper investigates an application of mobile sensing: detecting and reporting the surface conditions of roads. We describe a system and associated algorithms to monitor this important civil infrastructure using a collection of sensor-equipped vehicles. This system, which we call the Pothole Patrol (P2), uses the inherent mobility of the participating vehicles, opportunistically gathering data from vibration and GPS sensors, and processing the data to assess road surface conditions. We have deployed P2 on 7 taxis running in the Boston area. Using a simple machine-learning approach, we show that we are able to identify potholes and other severe road surface anomalies from accelerometer data. Via careful selection of training data and signal features, we have been able to build a detector that misidentifies good road segments as having potholes less than 0.2% of the time. We evaluate our system on data from thousands of kilometers of taxi drives, and show that it can successfully detect a number of real potholes in and around the Boston area. After clustering to further reduce spurious detections, manual inspection of reported potholes shows that over 90% contain road anomalies in need of repair.

Subfields: Artificial Intelligence, Civil and Structural Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/31a537c48c2bf2d98f2020df5b72c413d0fea1da

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Civil and Structural Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Micro-Blog: sharing and querying content through mobile phones and social participation (2008, background): “Accelerometer readings from phones of automobile riders [12,13], or open WiFi SSIDs near a street cafe are two examples.”
PRISM: platform for remote sensing using smartphones (2010, methodology): “The final application is inspired by Pothole Patrol [18] and Nericell [31] and involves opportunistic sensing, wherein phones equipped with GPS and accelerometer sensors are used to detect and locate road bumps automatically without any user involvement.”
Asphalt Pavement Pothole Detection and Segmentation Based on Wavelet Energy Field (2017, methodology): “[7] proposed a similar method that combines accelerometers and GPS to locate the position of the pothole.”
Safe Driving Using Mobile Phones (2012, methodology): “Pothole Patrol [15] is another system that monitors road conditions using GPS and an external accelerometer.”
Real time pothole detection using Android smartphones with accelerometers (2011, methodology): “Pothole Patrol system [8] developed at Massachusetts Institute of Technology is using a specific hardware/software platform – Linux powered Soekris 4801 embedded computers with external accelerometers (sampling rate 380Hz) and an external GPS.”
Energy-efficient rate-adaptive GPS-based positioning for smartphones (2010, background): “Hence a common approach is to periodically duty-cycle GPS.”
A Survey on Localization for Mobile Wireless Sensor Networks (2009, background): “In [78], a system is developed to detect potholes on city streets.”
ParkNet: drive-by sensing of road-side parking statistics (2010, methodology): “Other work in mobile sensing includes [9] which uses the mobility of participating vehicles to detect potholes in roads using accelerometers, and aggregate this data over time to obtain the locations of the roads that are most in need of repair.”
Crowdsourcing with Smartphones (2012, background): “The latter class includes applications for crowdsourced traffic monitoring (e.g., Waze 3 ) and road traffic delay estimation (VTrack [2]); constructing finegrained noise maps by letting users upload data captured by their smartphone microphone (Ear-Phone [3], NoiseTube [4]); identifying holes in str”
City Scanner: Building and Scheduling a Mobile Sensing Platform for Smart City Services (2018, background): “Generally, drive-by sensing employs cars (e.g., [12]) or vans (e.g., [17]); although other vehicles, such as bikes [5], buses [7], and taxi cabs [6], [11], have been utilized.”
Pseudonym Changing at Social Spots: An Effective Strategy for Location Privacy in VANETs (2012, background): “System (GPS) devices can monitor road surface conditions, detect potholes on the road [3], and then send the detected pot-”
Mobile Crowd Sensing and Computing (2015, methodology): “A similar application is PotHole [Eriksson et al. 2008], which can identify holes in streets using the crowdsourced vibration and position data collected from smartphones.”
SignalGuru: leveraging mobile phones for collaborative traffic signal schedule advisory (2011, background): “Several systems have been proposed that leverage GPS, accelerometer and proximity sensors in order to estimate traffic conditions [15, 23, 27], detect road abnormalities [11], collect information for available parking spots [22] and compute fuel efficient routes [12].”