Nericell: Rich Monitoring of Road and Traffic Conditionsusing Mobile SmartphonesPrashanth [email protected] [email protected] [email protected] Research India, BangaloreABSTRACTWe consider the problem of monitoring road and traffic con-ditions in a city. Prior work in this area has required thedeployment of dedicated sensors on vehicles and/or on theroadside, or the tracking of mobile phones by service providers.Furthermore, prior work has largely focused on the devel-oped world, with its relatively simple traffic flow patterns.In fact, traffic flow in cities of the developing regions, whichcomprise much of the world, tends to be much more com-plex owing to varied road conditions (e.g., potholed roads),chaotic traffic (e.g., a lot of braking and honking), and aheterogeneous mix of vehicles (2-wheelers, 3-wheelers, cars,buses, etc.).To monitor road and traffic conditions in such a setting,we present Nericell, a system that performs rich sensing bypiggybacking on smartphones that users carry with themin normal course. In this paper, we focus specifically onthe sensing component, which uses the accelerometer, mi-crophone, GSM radio, and/or GPS sensors in these phonesto detect potholes, bumps, braking, and honking. Nericelladdresses several challenges including virtually reorientingthe accelerometer on a phone that is at an arbitrary orien-tation, and performing honk detection and localization in anenergy efficient manner. We also touch upon the idea of trig-gered sensing, where dissimilar sensors are used in tandemto conserve energy. We evaluate the effectiveness of the sens-ing functions in Nericell based on ex periments conducted onthe roads of Bangalore, with promising results.Categories and Subject DescriptorsC.m [Computer Systems Organization]: Miscellaneous—Mobile Sensing SystemsGeneral TermsAlgorithms, Design, Experimentation, MeasurementPermission to make digital or hard copies of all or part of this work forpersonal or classroom use is granted without fee provided that copies arenot made or distributed for profit or commercial advantage and that copiesbear this notice and the full citation on the first page. To copy otherwise, torepublish, to post on servers or to redistribute to lists, requires prior specificpermission and/or a fee.SenSys’08, November 5–7, 2008, Raleigh, North Carolina, USA.Copyright 2008 ACM 978-1-59593-990-6/08/11 ...$5.00.KeywordsSensing, Roads, Traffic, Mobile Phones1. INTRODUCTIONRoads and vehicular traffic are a key part of t he day-to-day lives of people. Therefore, monitoring their conditionshas received a significant amount of attention. Prior workin this area has primarily focused on the developed world,where good roads and orderly traffic mean that the trafficconditions on a stretch of road can largely be characterizedby the volume and speed of traffic flowing through it. Tomonitor this information, intelligent transportation systems(ITS) [9] have been developed. Many of these involve deploy-ing dedicated sensors in vehicles (e.g., GPS-based trackingunits [12]) and/or on roads (indu ctive loop vehicle detec-tors, traffic cameras, doppler radar, etc.), which can be anexpensive proposition and so is typically restricted to thebusiest stretches of road. See [3] for a good overview of traf-fic surveillance techn ologies and Section 2 for related work.In contrast, road and t raffic conditions in the develop-ing world tend to be more varied because of various socio-economic reasons. Road qu ality tends to be variable, withbumpy roads and potholes b eing commonplace even in theheart of cities. The flow of traffic can be chaotic, with lit-tle or no adherence to right of way protocols at some in-tersections and liberal use of honking (The Nericell projectwebpage [11] includes a video clip of a chaotic intersectionin Bangalore). Vehicles types are also very heterogeneous,ranging from 2-wheelers (e.g., scooters and motorbikes) and3-wheelers (e.g., autorickshaws) to 4-wheelers (e.g., cars)and larger vehicles (e.g., buses).Monitoring such varied road and traffic conditions is chal-lenging, but it holds the promise of enabling new and usefulfunctionality. For instance, information gathered via richsensing could be used to annotate a map, thereby allowinga user to search for driving directions that would minimizestress by avoiding chaotic roads and intersections.To address this challenge, we present Nericell1, a systemfor rich monitoring of road and traffic conditions that pig-gybacks on mobile smartphones. Nericell orchestrates thesmartphones to perform sensing and report data back to aserver for aggregation. Indeed, smartphones include a rangeof sensing and communication capabilities, in addition tocomputing. A phone might include any or all of a micro-phone, camera, GPS, and accelerometer, each of which could1Nericell is a play on the word ‘Nerisal’, which means ‘con-gestion’ in Tamil.be used for traffic sensing functions. In addition, the phonewould include a cellular radio (e.g., GSM), possibly withdata communication capabilities (e.g., GPRS or UMTS).A mobile phone-based approach t o traffic monitoring is agood match for developing regions because it avoids the needfor expensive and specialized traffic monitoring infrastruc-ture. It also avoids dependence on advanced vehicle featuressuch the Controller A rea Network (CAN) bus t hat are absentin the many low-cost vehicles that are commonplace in de-veloping regions (e.g., the 3-wheeled autorickshaws in India).Moreover, it takes advantage of the booming growth of mo-bile telephony in such regions. For example, as of mid-2008,India had 287 million mobile telephony subscribers, growingat an estimated 7 million each month [15, 7]. Although themajority of users have b asic mobile phones to day, a largenumber of them, in fact more than t he number of PC Inter-net users in In dia, access the internet on their ph ones [10],suggesting that t he prospects of greater penetration of morecapable phones are good. There are similar growth trendsin many other parts of the world, with the total number ofmobile subscriptions worldwide estimated at 3.3 billion [5].Note that despite being mobile phone-based, our approachto traffic monitoring is distinct from prior work based on re-mote tracking of mobile phones by cellular operators [39, 2,1]. Our sensing and inferences goes beyond just monitoringlocation and speed information, hence requiring a