Pedestrian Detection with Wearable Cameras for the Blind: A Two-way Perspective

Blind people have limited access to information about their surroundings, which is important for ensuring one's safety, managing social interactions, and identifying approaching pedestrians. With advances in computer vision, wearable cameras can provide equitable access to such information. However, the always-on nature of these assistive technologies poses privacy concerns for parties that may get recorded. We explore this tension from both perspectives, those of sighted passersby and blind users, taking into account camera visibility, in-person versus remote experience, and extracted visual information. We conduct two studies: an online survey with MTurkers (N=206) and an in-person experience study between pairs of blind (N=10) and sighted (N=40) participants, where blind participants wear a working prototype for pedestrian detection and pass by sighted participants. Our results suggest that both of the perspectives of users and bystanders and the several factors mentioned above need to be carefully considered to mitigate potential social tensions.

[1]  Philipp A. Rauschnabel,et al.  Augmented reality smart glasses: an investigation of technology acceptance drivers , 2016 .

[2]  Khai N. Truong,et al.  Face Recognition Assistant for People with Visual Impairments , 2019, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[3]  Sen-Ching S. Cheung,et al.  LittleHelper: An augmented reality glass application to assist individuals with autism in job interview , 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

[4]  M. Saquib Sarfraz,et al.  A Multimodal Assistive System for Helping Visually Impaired in Social Interactions , 2017, Informatik-Spektrum.

[5]  Peter A. Witt,et al.  The impact of direct and indirect experiences on the development of environmental knowledge, attitudes, and behavior , 2010 .

[6]  Patrick Olivier,et al.  Exploring the acceptability of google glass as an everyday assistive device for people with parkinson's , 2014, CHI.

[7]  Albrecht Schmidt,et al.  Lifelogging: You're Wearing a Camera? , 2014, IEEE Pervasive Comput..

[8]  Tadayoshi Kohno,et al.  In situ with bystanders of augmented reality glasses: perspectives on recording and privacy-mediating technologies , 2014, CHI.

[9]  Jon Froehlich,et al.  Design of an Augmented Reality Magnification Aid for Low Vision Users , 2018, ASSETS.

[10]  Ellen Yi-Luen Do,et al.  Don't mind me touching my wrist: a case study of interacting with on-body technology in public , 2013, ISWC '13.

[11]  Yuhang Zhao,et al.  A Face Recognition Application for People with Visual Impairments: Understanding Use Beyond the Lab , 2018, CHI.

[12]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Valentin Schwind.  On the Need for Standardized Methods to Study the Social Acceptability of Emerging Technologies , 2018 .

[14]  Joo-Hwee Lim,et al.  Exploring users' attitudes towards social interaction assistance on Google Glass , 2015, AH.

[15]  Eelke Folmer,et al.  Headlock: a wearable navigation aid that helps blind cane users traverse large open spaces , 2014, ASSETS.

[16]  Apu Kapadia,et al.  Up to a Limit? , 2018, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[17]  Leah Findlater,et al.  Personalized, Wearable Control of a Head-mounted Display for Users with Upper Body Motor Impairments , 2015, CHI.

[18]  Gunasekaran Manogaran,et al.  Intelligent face recognition and navigation system using neural learning for smart security in Internet of Things , 2017, Cluster Computing.

[19]  Morgan Klaus Scheuerman,et al.  "Is Someone There? Do They Have a Gun": How Visual Information about Others Can Improve Personal Safety Management for Blind Individuals , 2017, ASSETS.

[20]  Pourang Irani,et al.  Are you comfortable doing that?: acceptance studies of around-device gestures in and for public settings , 2014, MobileHCI '14.

[21]  Halley Profita,et al.  The AT Effect: How Disability Affects the Perceived Social Acceptability of Head-Mounted Display Use , 2016, CHI.

[22]  Caroline Parker,et al.  An examination of the effects of a wearable display on informal face-to-face communication , 2006, CHI.

[23]  Stephen A. Brewster,et al.  Gestures all around us: user differences in social acceptability perceptions of gesture based interfaces , 2009, Mobile HCI.

[24]  Anja Thieme,et al.  Automated Person Detection in Dynamic Scenes to Assist People with Vision Impairments: An Initial Investigation , 2018, ASSETS.

[25]  Larry D. Rosen,et al.  The Media and Technology Usage and Attitudes Scale: An empirical investigation , 2013, Comput. Hum. Behav..

[26]  Stephen A. Brewster,et al.  Usable gestures for mobile interfaces: evaluating social acceptability , 2010, CHI.

[27]  Minho Lee,et al.  Smart Cane: Face Recognition System for Blind , 2015, HAI.

[28]  Lei Shi,et al.  Designing and Evaluating a Customizable Head-mounted Vision Enhancement System for People with Low Vision , 2019, ACM Trans. Access. Comput..

[29]  Hsin-Liu (Cindy) Kao,et al.  Understanding social perceptions towards interacting with on-skin interfaces in public , 2019, UbiComp.

[30]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[31]  Shurug Al-Khalifa,et al.  Ebsar: Indoor guidance for the visually impaired , 2016, Comput. Electr. Eng..

[32]  Aleksandrs Slivkins,et al.  Incentivizing high quality crowdwork , 2015, SECO.

[33]  Leah Findlater,et al.  Fairness issues in AI systems that augment sensory abilities , 2019, ACM SIGACCESS Access. Comput..

[34]  Sriram Subramanian,et al.  Would you do that?: understanding social acceptance of gestural interfaces , 2010, Mobile HCI.

[35]  Jeffrey P. Bigham,et al.  Supporting blind photography , 2011, ASSETS.

[36]  J. Crowley,et al.  Estimating Face orientation from Robust Detection of Salient Facial Structures , 2004 .

[37]  Stephen B. Gilbert,et al.  The WEAR Scale: Developing a Measure of the Social Acceptability of a Wearable Device , 2016, CHI Extended Abstracts.

[38]  Annuska Zolyomi,et al.  Technology-Mediated Sight: A Case Study of Early Adopters of a Low Vision Assistive Technology , 2017, ASSETS.