If You See It, Swipe towards It: Crowdsourced Event Localization

This project aims to leverage crowdsourcing to locate events that are difficult to be monitored by surveillance cameras due to coverage and cost issues. The event in consideration is smoking.

UbiComp 2013

No Need to War-Drive: Unsupervised Indoor Localization

UnLoc is an unsupervised indoor localization scheme that bypasses the need for war-driving. Our key observation is that certain locations in an indoor environment present an identifiable signature.

ACM MobiSys 2012

Satellites in Our Pockets: An Object Positioning System using Smartphones

This paper attempts to solve the following problem: can a distant object be localized by looking at it through a smartphone. We design a system called Object Positioning System (OPS) that achieves reasonable localization accuracy.

ACM MobiSys 2012

Spot Localization using PHY Layer Information

This paper explores the viability of precise indoor localization using physical layer information in WiFi systems. We find evidence that channel responses from multiple OFDM subcarriers can be a promising location signature.

ACM MobiSys 2012

SpinLoc: Spin Once to Know Your Location

Towards a indoor localization solution that is easier to adopt, we propose SpinLoc that is free from war-driving. Instead, SpinLoc levies a little bit of the localization burden on the humans, expecting them to rotate around once to estimate their locations.

ACM HotMobile 2012

"Did You See Bob?": Human Localization using Mobile Phones

Finding a person in a public place, such as in a library or shopping mall, can be difficult. This paper identifies the possibility of using mobile phone sensors and opportunistic user-intersections to develop an electronic escort service.

ACM MobiCom 2010

Towards Mobile Phone Localization without War-Driving

This paper identifies the possibility of using electronic compasses and accelerometers in mobile phones and a local electronic map, as a simple and scalable method of localization without war-driving.

IEEE Infocom 2010

SurroundSense: Mobile Phone Localization Via Ambience Fingerprinting

There have been few attempts in recognizing logical locations. We postulate that by combining phone's camera, microphone and motion sensors, it may be feasible to construct an identifiable fingerprint for logical localization.

ACM MobiCom 2009

EnLoc: Energy-Efficient Localization for Mobile Phones

GPS incurs an unacceptable energy cost. Alternate localization technologies, based onWiFi or GSM, improve battery life at the expense of localization accuracy. This paper quantifies this important tradeoff that underlies a range of emerging services.

IEEE Infocom (mini) 2009


Demo UnLoc at Intel Labs at Santa Clara
Romit invited to talk on "Smartphone Positioning Systems" at Qualcomm Labs and Samsung Research
Two major US companies interested in licensing UnLoc
SurroundSense selected for ACM's TechPack on Mobility


Romit Roy Choudhury
Associate Professor
Dept. of ECE and CS

Current Students
He Wang
PhD Student
Dept. of ECE

Hyojeong Shin
Postdoctoral Associate
Dept. of ECE

Nirupam Roy
PhD Student
Dept. of ECE

Previous Students
Souvik Sen (currently at HP Labs)
Wentao Ouyang (currently postdoc at UCLA)
Alex Mariakakis (currently PhD at UW)
Ionut Constandache (currently at Oracle)
Martin Azizyan (currently PhD at CMU)

The National Science Foundation (NSF)

National Institutes of Health (NIH)

Cisco Research


Nokia Research

Microsoft Research

Scalable Network Technologies