Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Army Hand Signal Recognition System using Smartwatch Sensors

Choi, Weonji (2018) Army Hand Signal Recognition System using Smartwatch Sensors. Master's Thesis, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Download (1MB) | Preview

Abstract

The organized armies of the world all have their own hand signal systems to deliver commands and messages between combatants during operations such as search, reconnaissance, and infiltration. For instance, to command a troop to stop, a commander would lift his/her fist next to the his/her face height. When the operation is carried out by a small unit, the hand signal system plays a very important role. However, obviously, there is an aspect of limitation in this method; each signal should be relayed by individuals, which while waiting attentively for a signal can cause soldiers to lose attention on the front observation and be distracted. Another limitation is, it takes a certain period to convey signals from the first person to the last person. While the limitations above are related to a short moment, that can be fatal in the field of battle.
Gesture recognition has emerged as a very important and effective way for interaction between human and computer (HCI). An application of inertial measurement unit (IMU) sensor data from smart devices has lead gesture recognition into the next level, because it means people don’t need to rely on any external equipment, such as a camera to read movements. Especially wearable devices can be more adequate for gesture recognition than hand-held devices because of its distinguished strengths. If soldiers can deliver signals using an off-the-shelf smartwatch, without additional training, it can resolve many drawbacks of the current hand signal system.
In the battlefield, cameras to record combatants’ movement for image processing cannot be installed nor utilized, and there are countless obstacles, such as tree branches, trunks, or valleys that hinder the camera to observe movements of the combatants. Because of unique characteristics of battlefield, a gesture recognition system using a smartwatch can be the most appropriate solution for making troops mobility more efficient and secure. For the system to be used successfully in combat zone, the system requires high precision and prompt processing; although accuracy and operating speed are inversely proportional in most of cases.
This paper will present a gesture recognition tool for army hand signals with high accuracy and fast processing speed. It is expected that the army hand signal recognition system (AHSR) will assist small units to carry-out their maneuver with higher efficiency.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Choi, Weonjiwec69@pitt.eduwec690000-0002-3946-3120
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairGao, WeiWEIGAO@pitt.eduWEIGAO
Committee MemberAkcakaya, Muratakcakaya@pitt.eduakcakaya
Committee MemberMao, Zhi-hongzhm4@pitt.eduzhm4
Date: 20 September 2018
Date Type: Publication
Defense Date: 29 May 2018
Approval Date: 20 September 2018
Submission Date: 29 May 2018
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 68
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Computer Engineering
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: HCI, wearable, smartwatch, pattern recognition, gesture recognition, army hand signal
Date Deposited: 20 Sep 2018 18:41
Last Modified: 20 Sep 2018 18:41
URI: http://d-scholarship.pitt.edu/id/eprint/34516

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item