On the influence of artificially distorted images in firearm detection performance using deep learning

Detecting people carrying firearms in outdoor or indoor scenes usually identifies (or avoids) potentially dangerous situations. Nevertheless, the automatic detection of these weapons can be greatly affected by the scene conditions. Commonly, in real scenes these firearms can be seen from different p...

Full description

Saved in:
Bibliographic Details
Main Authors: Patricia Corral-Sanz, Alvaro Barreiro-Garrido, A. Belen Moreno, Angel Sanchez
Format: Article
Language:English
Published: PeerJ Inc. 2024-10-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2381.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181258178461696
author Patricia Corral-Sanz
Alvaro Barreiro-Garrido
A. Belen Moreno
Angel Sanchez
author_facet Patricia Corral-Sanz
Alvaro Barreiro-Garrido
A. Belen Moreno
Angel Sanchez
author_sort Patricia Corral-Sanz
collection DOAJ
description Detecting people carrying firearms in outdoor or indoor scenes usually identifies (or avoids) potentially dangerous situations. Nevertheless, the automatic detection of these weapons can be greatly affected by the scene conditions. Commonly, in real scenes these firearms can be seen from different perspectives. They also may have different real and apparent sizes. Moreover, the images containing these targets are usually cluttered, and firearms can appear as partially occluded. It is also common that the images can be affected by several types of distortions such as impulse noise, image darkening or blurring. All these perceived variabilities could significantly degrade the accuracy of firearm detection. Current deep detection networks offer good classification accuracy, with high efficiency and under constrained computational resources. However, the influence of practical conditions in which the objects are to be detected has not sufficiently been analyzed. Our article describes an experimental study on how a set of selected image distortions quantitatively degrade the detection performance on test images when the detection networks have only been trained with images that do not present the alterations. The analyzed test image distortions include impulse noise, blurring (or defocus), image darkening, image shrinking and occlusions. In order to quantify the impact of each individual distortion on the firearm detection problem, we have used a standard YOLOv5 network. Our experimental results have shown that the increased addition of impulse salt-and-pepper noise is by far the distortion that affects the most the performance of the detection network.
format Article
id doaj-art-9e3e1e28e4b6471db37af7b29bde6327
institution OA Journals
issn 2376-5992
language English
publishDate 2024-10-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-9e3e1e28e4b6471db37af7b29bde63272025-08-20T02:17:57ZengPeerJ Inc.PeerJ Computer Science2376-59922024-10-0110e238110.7717/peerj-cs.2381On the influence of artificially distorted images in firearm detection performance using deep learningPatricia Corral-Sanz0Alvaro Barreiro-Garrido1A. Belen Moreno2Angel Sanchez3Department of Computer Science and Statistics, Universidad Rey Juan Carlos, Mostoles, Madrid, SpainDepartment of Computer Science and Statistics, Universidad Rey Juan Carlos, Mostoles, Madrid, SpainDepartment of Computer Science and Statistics, Universidad Rey Juan Carlos, Mostoles, Madrid, SpainDepartment of Computer Science and Statistics, Universidad Rey Juan Carlos, Mostoles, Madrid, SpainDetecting people carrying firearms in outdoor or indoor scenes usually identifies (or avoids) potentially dangerous situations. Nevertheless, the automatic detection of these weapons can be greatly affected by the scene conditions. Commonly, in real scenes these firearms can be seen from different perspectives. They also may have different real and apparent sizes. Moreover, the images containing these targets are usually cluttered, and firearms can appear as partially occluded. It is also common that the images can be affected by several types of distortions such as impulse noise, image darkening or blurring. All these perceived variabilities could significantly degrade the accuracy of firearm detection. Current deep detection networks offer good classification accuracy, with high efficiency and under constrained computational resources. However, the influence of practical conditions in which the objects are to be detected has not sufficiently been analyzed. Our article describes an experimental study on how a set of selected image distortions quantitatively degrade the detection performance on test images when the detection networks have only been trained with images that do not present the alterations. The analyzed test image distortions include impulse noise, blurring (or defocus), image darkening, image shrinking and occlusions. In order to quantify the impact of each individual distortion on the firearm detection problem, we have used a standard YOLOv5 network. Our experimental results have shown that the increased addition of impulse salt-and-pepper noise is by far the distortion that affects the most the performance of the detection network.https://peerj.com/articles/cs-2381.pdfArtificial image distortionsFirearm detectionDeep learningYOLOObject detection metrics
spellingShingle Patricia Corral-Sanz
Alvaro Barreiro-Garrido
A. Belen Moreno
Angel Sanchez
On the influence of artificially distorted images in firearm detection performance using deep learning
PeerJ Computer Science
Artificial image distortions
Firearm detection
Deep learning
YOLO
Object detection metrics
title On the influence of artificially distorted images in firearm detection performance using deep learning
title_full On the influence of artificially distorted images in firearm detection performance using deep learning
title_fullStr On the influence of artificially distorted images in firearm detection performance using deep learning
title_full_unstemmed On the influence of artificially distorted images in firearm detection performance using deep learning
title_short On the influence of artificially distorted images in firearm detection performance using deep learning
title_sort on the influence of artificially distorted images in firearm detection performance using deep learning
topic Artificial image distortions
Firearm detection
Deep learning
YOLO
Object detection metrics
url https://peerj.com/articles/cs-2381.pdf
work_keys_str_mv AT patriciacorralsanz ontheinfluenceofartificiallydistortedimagesinfirearmdetectionperformanceusingdeeplearning
AT alvarobarreirogarrido ontheinfluenceofartificiallydistortedimagesinfirearmdetectionperformanceusingdeeplearning
AT abelenmoreno ontheinfluenceofartificiallydistortedimagesinfirearmdetectionperformanceusingdeeplearning
AT angelsanchez ontheinfluenceofartificiallydistortedimagesinfirearmdetectionperformanceusingdeeplearning