Urban Safety

Introduction

Death and injury caused by accidents in urban areas have seen a sharp increase in recent years, especially from vehicle accidents. Our work in this sphere seeks to explore and develop novel technologies that can help reduce the number of accidents in urban areas and improve the overall safety of the general population.

PAWS Pedestrian Safety

Vehicles are one of the biggest cause of death and injury for pedestrians in urban cities. Many of these accidents occur because the pedestrian is distracted, whilst using their smartphones, headphones, and other smart devices. We develop a wearable system, built upon a commercial-off-the-shelf headset, that leverages low-cost microphones and novel machine learning + signal processing algorithms to detect and localize dangerous vehicles approaching the pedestrian. Our system is able to detect, localize, and warn users well in advance of a vehicle passing by. More information about this project can be found on the PAWS project page.

CSAFE Construction Worker Safety

Vehicle accidents are also a major cause of injury for construction workers. However, utilizing low-power acoustics in construction worker scenarios is difficult because construction sites are very noisy. The sounds of construction work can easily overpower the sound of an approaching vehicle. To address this challenge, we develop novel sound source separation architectures and algorithms, capable of running on embedded and mobile devices, to filter out construction noises. We integrate our architectures and algorithms into a construction helmet wearable and show that our system is able to reliably filter out construction noises and improve vehicle detection in noisy construction site scenarios. More information about this project can be found on the CSAFE project page.

Future Work

Our approaches to improving urban safety have been largely based in acoustics. Looking forward, plan to further develop our adaptive sound source separation algorithms and architectures to account for more scenarios and applications. Our vision is to create a general acoustic platform that can be implemented in a wide range of low-power cyber-physical systems that could benefit from intelligent acoustic AI.

Publications

2021 | ACM/IEEE IPSN ’21
CSAFE: An Intelligent Audio Wearable Platform for Improving Construction Worker Safety in Urban Environments (to appear)
Stephen Xia, Jingping Nie, Xiaofan Jiang

2020 | ACM AIChallengeIoT ’20
PAMS: Improving Privacy in Audio-Based Mobile Systems
Stephen Xia and Xiaofan Jiang

2019 | IEEE Internet of Things Journal
Improving Pedestrian Safety in Cities using Intelligent Wearable Systems
Stephen Xia, Daniel de Godoy, Bashima Islam, Md Tamzeed Islam, Shahriar Nirjon, Peter R. Kinget, Xiaofan Jiang

2018 | IEEE VNC ’18 / Taipei, Taiwan
PAWS+: A Smartphone Platform for Pedestrian Safety
Stephen Xia, Daniel de Godoy, Bashima Islam, Stephen Xia, Md Tamzeed Islam, Shahriar Nirjon, Peter Kinget, and Xiaofan Jiang
[Runner-Up Best App Award]
[Best Presentation Award]

2018 | ACM/IEEE IoTDI ’18 / Orlando, FL, USA
PAWS: A Wearable Acoustic System for Pedestrian Safety
Daniel de Godoy, Bashima Islam, Stephen Xia, Md Tamzeed Islam, Rishikanth Chandrasekaran, Yen-Chun Chen, Shahriar Nirjon, Peter Kinget, and Xiaofan Jiang

2018 | ACM/IEEE IoTDI ’18 / Orlando, FL, USA
An Ultra-Low-Power Custom Integrated Circuit based Sound-Source Localization System
Daniel de Godoy, Stephen Xia, Wendy Fernandez, Xiaofan Jiang, and Peter Kinget
[Best Demo Award]

2018 | IEEE CICC ’18 / San Diego, CA, USA
A 78.2nW 3-Channel Time-Delay-to-Digital Converter using Polarity Coincidence for Audio-based Object Localization
Daniel de Godoy, Xiaofan Jiang, and Peter Kinget

2016 | ACM SenSys ’16 / Palo Alto, CA, USA
SEUS: A Wearable Multi-Channel Acoustic Headset Platform to Improve Pedestrian Safety: Demo Abstract
Rishikanth Chandrasekaran, Daniel de Godoy, Stephen Xia, Md Tamzeed Islam, Bashima Islam, Shahriar Nirjon, Peter Kinget, and Xiaofan Jiang
[Best Demo – Runner Up Award]