Garuda: A deep learning based solution for capturing selfies safely

Jitender Singh Virk; Abhinav Dhall

doi:10.1145/3308557.3308669

Garuda: A deep learning based solution for capturing selfies safely

Jitender Singh Virk, Abhinav Dhall

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Clicking selfies using mobile phones has become a trend in the past few years. It is documented that the thrill of clicking selfies at adventurous places has resulted in serious injuries and even death in some cases. To overcome this, we propose a system which can alert the user by detecting the level of danger in the background while capturing selfies. Our app is based on a deep Convolutional Neural Network (CNN). The prediction is performed as a 5 class classification problem with classes representing a different level of danger. Face detection and device orientation information are also used for robustness and lesser battery consumption.

Original language	English
Title of host publication	Companion Proceedings of the 24th International Conference on Intelligent User Interfaces
Place of Publication	New York, NY
Publisher	Association for Computing Machinery
Pages	43-44
Number of pages	2
ISBN (Electronic)	9781450366731
DOIs	https://doi.org/10.1145/3308557.3308669
Publication status	Published - 16 Mar 2019
Externally published	Yes
Event	24th International Conference on Intelligent User Interfaces - Marina del Ray, United States Duration: 16 Mar 2019 → 20 Mar 2019 Conference number: 24th

Publication series

Name	International Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference	24th International Conference on Intelligent User Interfaces
Abbreviated title	IUI '19
Country/Territory	United States
City	Marina del Ray
Period	16/03/19 → 20/03/19

Keywords

Deep learning
Safe selfie
Scene analysis
Selfie

Access to Document

10.1145/3308557.3308669Licence: In Copyright

Cite this

@inproceedings{18ddff68a9944513aa8f3de86cba0b43,

title = "Garuda: A deep learning based solution for capturing selfies safely",

abstract = "Clicking selfies using mobile phones has become a trend in the past few years. It is documented that the thrill of clicking selfies at adventurous places has resulted in serious injuries and even death in some cases. To overcome this, we propose a system which can alert the user by detecting the level of danger in the background while capturing selfies. Our app is based on a deep Convolutional Neural Network (CNN). The prediction is performed as a 5 class classification problem with classes representing a different level of danger. Face detection and device orientation information are also used for robustness and lesser battery consumption.",

keywords = "Deep learning, Safe selfie, Scene analysis, Selfie",

author = "Virk, {Jitender Singh} and Abhinav Dhall",

year = "2019",

month = mar,

day = "16",

doi = "10.1145/3308557.3308669",

language = "English",

series = "International Conference on Intelligent User Interfaces, Proceedings IUI",

publisher = "Association for Computing Machinery",

pages = "43--44",

booktitle = "Companion Proceedings of the 24th International Conference on Intelligent User Interfaces",

note = "24th International Conference on Intelligent User Interfaces, IUI '19 ; Conference date: 16-03-2019 Through 20-03-2019",

}

Virk, JS & Dhall, A 2019, Garuda: A deep learning based solution for capturing selfies safely. in Companion Proceedings of the 24th International Conference on Intelligent User Interfaces. International Conference on Intelligent User Interfaces, Proceedings IUI, Association for Computing Machinery, New York, NY, pp. 43-44, 24th International Conference on Intelligent User Interfaces, Marina del Ray, California, United States, 16/03/19. https://doi.org/10.1145/3308557.3308669

Garuda: A deep learning based solution for capturing selfies safely. / Virk, Jitender Singh; Dhall, Abhinav.
Companion Proceedings of the 24th International Conference on Intelligent User Interfaces. New York, NY: Association for Computing Machinery, 2019. p. 43-44 (International Conference on Intelligent User Interfaces, Proceedings IUI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Garuda

T2 - 24th International Conference on Intelligent User Interfaces

AU - Virk, Jitender Singh

AU - Dhall, Abhinav

N1 - Conference code: 24th

PY - 2019/3/16

Y1 - 2019/3/16

N2 - Clicking selfies using mobile phones has become a trend in the past few years. It is documented that the thrill of clicking selfies at adventurous places has resulted in serious injuries and even death in some cases. To overcome this, we propose a system which can alert the user by detecting the level of danger in the background while capturing selfies. Our app is based on a deep Convolutional Neural Network (CNN). The prediction is performed as a 5 class classification problem with classes representing a different level of danger. Face detection and device orientation information are also used for robustness and lesser battery consumption.

AB - Clicking selfies using mobile phones has become a trend in the past few years. It is documented that the thrill of clicking selfies at adventurous places has resulted in serious injuries and even death in some cases. To overcome this, we propose a system which can alert the user by detecting the level of danger in the background while capturing selfies. Our app is based on a deep Convolutional Neural Network (CNN). The prediction is performed as a 5 class classification problem with classes representing a different level of danger. Face detection and device orientation information are also used for robustness and lesser battery consumption.

KW - Deep learning

KW - Safe selfie

KW - Scene analysis

KW - Selfie

UR - http://www.scopus.com/inward/record.url?scp=85074449106&partnerID=8YFLogxK

U2 - 10.1145/3308557.3308669

DO - 10.1145/3308557.3308669

M3 - Conference contribution

AN - SCOPUS:85074449106

T3 - International Conference on Intelligent User Interfaces, Proceedings IUI

SP - 43

EP - 44

BT - Companion Proceedings of the 24th International Conference on Intelligent User Interfaces

PB - Association for Computing Machinery

CY - New York, NY

Y2 - 16 March 2019 through 20 March 2019

ER -

Garuda: A deep learning based solution for capturing selfies safely

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this