Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier

Marks Dextre; Oscar Rosas; Jesus Lazo; Juan C. Gutiérrez

doi:10.1109/CLEI53233.2021.9640100

Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier

Marks Dextre, Oscar Rosas, Jesus Lazo, Juan C. Gutiérrez

Departamento Académico de Ingeniería de Sistemas e Informática

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

Resumen

Automating the detection of weapons from video surveillance images is a difficult task due to: lighting, focus, resolution, among others. Solving this problem would be very useful for citizen security purposes. In this sense, this research work trains a weapon detection system based on YOLOv5 (You Only Look Once) for different data sources, reaching an accuracy of 98.56 % in video surveillance images, performing Real-Time inferences reaching 33 fps on Nvidia’s Jetson AGX Xavier which is a good result compared to other existing research in the state of the art.

Idioma original	Inglés
Título de la publicación alojada	Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021
Editorial	Institute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)	9781665495035
DOI	https://doi.org/10.1109/CLEI53233.2021.9640100
Estado	Publicada - 2021
Evento	47th Latin American Computing Conference, CLEI 2021 - Virtual, Cartago, Costa Rica Duración: 25 oct. 2021 → 29 oct. 2021

Serie de la publicación

Nombre	Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021

Conferencia

Conferencia	47th Latin American Computing Conference, CLEI 2021
País/Territorio	Costa Rica
Ciudad	Virtual, Cartago
Período	25/10/21 → 29/10/21

Nota bibliográfica

Publisher Copyright:
©2021 IEEE

Acceder al documento

10.1109/CLEI53233.2021.9640100

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Dextre, M., Rosas, O., Lazo, J., & Gutiérrez, J. C. (2021). Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier. En Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021 (Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CLEI53233.2021.9640100

@inproceedings{721d342c1aa842b9b1127c844cb87ef5,

title = "Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier",

abstract = "Automating the detection of weapons from video surveillance images is a difficult task due to: lighting, focus, resolution, among others. Solving this problem would be very useful for citizen security purposes. In this sense, this research work trains a weapon detection system based on YOLOv5 (You Only Look Once) for different data sources, reaching an accuracy of 98.56 % in video surveillance images, performing Real-Time inferences reaching 33 fps on Nvidia{\textquoteright}s Jetson AGX Xavier which is a good result compared to other existing research in the state of the art.",

keywords = "Edge computing, Gun detection, Jetson AGX Xavier, Object detection, Real-Time, YOLOv5",

author = "Marks Dextre and Oscar Rosas and Jesus Lazo and Guti{\'e}rrez, {Juan C.}",

note = "Publisher Copyright: {\textcopyright}2021 IEEE; 47th Latin American Computing Conference, CLEI 2021 ; Conference date: 25-10-2021 Through 29-10-2021",

year = "2021",

doi = "10.1109/CLEI53233.2021.9640100",

language = "Ingl{\'e}s",

series = "Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021",

address = "Estados Unidos",

}

Dextre, M, Rosas, O, Lazo, J & Gutiérrez, JC 2021, Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier. En Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021. Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021, Institute of Electrical and Electronics Engineers Inc., 47th Latin American Computing Conference, CLEI 2021, Virtual, Cartago, Costa Rica, 25/10/21. https://doi.org/10.1109/CLEI53233.2021.9640100

Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier. / Dextre, Marks; Rosas, Oscar; Lazo, Jesus et al.
Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier

AU - Dextre, Marks

AU - Rosas, Oscar

AU - Lazo, Jesus

AU - Gutiérrez, Juan C.

PY - 2021

Y1 - 2021

N2 - Automating the detection of weapons from video surveillance images is a difficult task due to: lighting, focus, resolution, among others. Solving this problem would be very useful for citizen security purposes. In this sense, this research work trains a weapon detection system based on YOLOv5 (You Only Look Once) for different data sources, reaching an accuracy of 98.56 % in video surveillance images, performing Real-Time inferences reaching 33 fps on Nvidia’s Jetson AGX Xavier which is a good result compared to other existing research in the state of the art.

AB - Automating the detection of weapons from video surveillance images is a difficult task due to: lighting, focus, resolution, among others. Solving this problem would be very useful for citizen security purposes. In this sense, this research work trains a weapon detection system based on YOLOv5 (You Only Look Once) for different data sources, reaching an accuracy of 98.56 % in video surveillance images, performing Real-Time inferences reaching 33 fps on Nvidia’s Jetson AGX Xavier which is a good result compared to other existing research in the state of the art.

KW - Edge computing

KW - Gun detection

KW - Jetson AGX Xavier

KW - Object detection

KW - Real-Time

KW - YOLOv5

UR - http://www.scopus.com/inward/record.url?scp=85123861492&partnerID=8YFLogxK

U2 - 10.1109/CLEI53233.2021.9640100

DO - 10.1109/CLEI53233.2021.9640100

M3 - Contribución a la conferencia

AN - SCOPUS:85123861492

T3 - Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021

BT - Proceedings - 2021 47th Latin American Computing Conference, CLEI 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 47th Latin American Computing Conference, CLEI 2021

Y2 - 25 October 2021 through 29 October 2021

ER -

Gun Detection in Real-Time, using YOLOv5 on Jetson AGX Xavier

Resumen

Serie de la publicación

Conferencia

Nota bibliográfica

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto