Use of Phone Sensors to Enhance Distracted Pedestrians’ Safety

Studies have shown that using smartphones while walking—called <italic>distracted walking</italic> —significantly increases the risk of pedestrians colliding with dangerous objects. In this paper, we explore how to mitigate this problem by exploiting the phone's built-in sensors only and developing an application called <monospace>BumpAlert</monospace>. <monospace>BumpAlert</monospace> provides a generic solution without requiring any prior knowledge of the user's surroundings by estimating distances to nearby objects using the phone's speakers and microphones. This process is enhanced further by using the images acquired from the phone's rear camera, when necessary. We have evaluated <monospace>BumpAlert</monospace> under a variety of settings ranging from aisle to outdoor environments with walls, pillars, signboards, dustbins, and people, etc., that are common in our daily surroundings. Our evaluation has shown an average accuracy of <monospace>BumpAlert</monospace> to be higher than 95 percent with a less than 2 percent false-positive rate to detect frontal objects 2–4m away, which suffices for the user to react and avoid collision. Even though <monospace>BumpAlert</monospace> is unable to detect all dangerous situations, most participants of our user study feel safer when they walk with <monospace>BumpAlert </monospace> enabled. Integrating our current design of <monospace>BumpAlert</monospace> with other safety systems can provide a practical solution for protecting distracted pedestrians.

[1]  Yoram Koren,et al.  The vector field histogram-fast obstacle avoidance for mobile robots , 1991, IEEE Trans. Robotics Autom..

[2]  Illah R. Nourbakhsh,et al.  Appearance-Based Obstacle Detection with Monocular Color Vision , 2000, AAAI/IAAI.

[3]  Larry S. Davis,et al.  Pedestrian tracking from a moving vehicle , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[4]  Osama Masoud,et al.  Computer vision algorithms for intersection monitoring , 2003, IEEE Trans. Intell. Transp. Syst..

[5]  Javier Minguez,et al.  The obstacle-restriction method for robot obstacle avoidance in difficult environments , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Ali Rafiee,et al.  Radar pulse compression techniques , 2005 .

[7]  J.A.B. Neves,et al.  Angle Invariance for Distance Measurements Using a Single Camera , 2006, 2006 IEEE International Symposium on Industrial Electronics.

[8]  R. Kram,et al.  Effects of obesity and sex on the energetic cost and preferred speed of walking. , 2006, Journal of applied physiology.

[9]  Guobin Shen,et al.  BeepBeep: a high accuracy acoustic ranging system using COTS mobile devices , 2007, SenSys '07.

[10]  Fehmi Ben Abdesslem,et al.  Less is more: energy-efficient mobile sensing with senseless , 2009, MobiHeld '09.

[11]  Gang Wang,et al.  I am the antenna: accurate outdoor AP location using smartphones , 2011, MobiCom '11.

[12]  Peter A. Dinda,et al.  Indoor localization without infrastructure using the acoustic background spectrum , 2011, MobiSys '11.

[13]  D. Ghose,et al.  Vision based obstacle detection using 3D HSV histograms , 2011, 2011 Annual IEEE India Conference.

[14]  Mo Li,et al.  IODetector: a generic service for indoor outdoor detection , 2012, SenSys '12.

[15]  Anthony Rowe,et al.  Indoor pseudo-ranging of mobile devices using ultrasonic chirps , 2012, SenSys '12.

[16]  Srihari Nelakuditi,et al.  SpinLoc: spin once to know your location , 2012, HotMobile '12.

[17]  Antonio Corradi,et al.  WalkSafe: a pedestrian safety app for mobile phone users who walk and talk while crossing roads , 2012, HotMobile '12.

[18]  Xiaolin Li,et al.  Guoguo: enabling fine-grained indoor localization via smartphone , 2013, MobiSys '13.

[19]  Derek Troyer,et al.  Pedestrian injuries due to mobile phone use in public places. , 2013, Accident; analysis and prevention.

[20]  Qiang Li,et al.  Auditeur: a mobile-cloud service platform for acoustic event detection on smartphones , 2013, MobiSys '13.

[21]  Pourang Irani,et al.  CrashAlert: enhancing peripheral alertness for eyes-busy mobile interaction while walking , 2013, CHI.

[22]  Alireza Sahami Shirazi,et al.  Upright or sideways?: analysis of smartphone postures in the wild , 2013, MobileHCI '13.

[23]  Guihai Chen,et al.  APT: Accurate outdoor pedestrian tracking with smartphones , 2013, 2013 Proceedings IEEE INFOCOM.

[24]  Xinyu Zhang,et al.  Ubiquitous keyboard for small mobile devices: harnessing multipath fading for fine-grained keystroke localization , 2014, MobiSys.

[25]  Marco Gruteser,et al.  LookUp: Enabling Pedestrian Safety Services via Shoe Sensing , 2015, MobiSys.

[26]  Kang G. Shin,et al.  EchoTag: Accurate Infrastructure-Free Indoor Location Tagging with Smartphones , 2015, MobiCom.

[27]  R. van Emmerik,et al.  Dual task interference during walking: The effects of texting on situational awareness and gait stability. , 2015, Gait & posture.

[28]  Kang G. Shin,et al.  Expansion of Human-Phone Interface By Sensing Structure-Borne Sound Propagation , 2016, MobiSys.