Efficient CNN-based low-resolution facial detection from UAVs

Julio Díez-Tomillo; Ignacio Martinez-Alpiste; Gelayol Golcarenarenji; Qi Wang; Jose M. Alcaraz-Calero

doi:10.1007/s00521-023-09401-3

Efficient CNN-based low-resolution facial detection from UAVs

Julio Díez-Tomillo, Ignacio Martinez-Alpiste, Gelayol Golcarenarenji, Qi Wang, Jose M. Alcaraz-Calero

Research output: Contribution to journal › Article › peer-review

Abstract

Face detection in UAV imagery requires high accuracy and low execution time for real-time mission-critical operations in public safety, emergency management, disaster relief and other applications. This study presents UWS-YOLO, a new convolutional neural network (CNN)-based machine learning algorithm designed to address these demanding requirements. UWS-YOLO’s key strengths lie in its exceptional speed, remarkable accuracy and ability to handle complex UAV operations. This algorithm presents a balanced and portable solution for real-time face detection in UAV applications. Evaluation and comparison with the state-of-the-art algorithms using standard and UAV-specific datasets demonstrate UWS-YOLO’s superiority. It achieves 59.29% of accuracy compared with 27.43% in a state-of-the-art solution RetinaFace and 46.59% with YOLOv7. Additionally, UWS-YOLO operates at 11 milliseconds, which is 345% faster than RetinaFace and 373% than YOLOv7.

Original language	English
Pages (from-to)	5847-5860
Number of pages	14
Journal	Neural Computing and Applications
Volume	36
Issue number	11
Early online date	13 Jan 2024
DOIs	https://doi.org/10.1007/s00521-023-09401-3
Publication status	Published - Apr 2024

Bibliographical note

Copyright © The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

Keywords

face detection
UAV
YOLO
RetinaFace

Access to Document

10.1007/s00521-023-09401-3

J Diez-Tomillo et al_Efficient CNN-based low-resolution facial detection from UAVs
Copyright © The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/
Final published version, 1.93 MBLicence: CC BY 4.0

Cite this

@article{4e0d0b063e1b45ec92bd82841d5e5564,

title = "Efficient CNN-based low-resolution facial detection from UAVs",

abstract = "Face detection in UAV imagery requires high accuracy and low execution time for real-time mission-critical operations in public safety, emergency management, disaster relief and other applications. This study presents UWS-YOLO, a new convolutional neural network (CNN)-based machine learning algorithm designed to address these demanding requirements. UWS-YOLO{\textquoteright}s key strengths lie in its exceptional speed, remarkable accuracy and ability to handle complex UAV operations. This algorithm presents a balanced and portable solution for real-time face detection in UAV applications. Evaluation and comparison with the state-of-the-art algorithms using standard and UAV-specific datasets demonstrate UWS-YOLO{\textquoteright}s superiority. It achieves 59.29% of accuracy compared with 27.43% in a state-of-the-art solution RetinaFace and 46.59% with YOLOv7. Additionally, UWS-YOLO operates at 11 milliseconds, which is 345% faster than RetinaFace and 373% than YOLOv7.",

keywords = "face detection, UAV, YOLO, RetinaFace",

author = "Julio D{\'i}ez-Tomillo and Ignacio Martinez-Alpiste and Gelayol Golcarenarenji and Qi Wang and Alcaraz-Calero, {Jose M.}",

note = "Copyright {\textcopyright} The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/",

year = "2024",

month = apr,

doi = "10.1007/s00521-023-09401-3",

language = "English",

volume = "36",

pages = "5847--5860",

journal = "Neural Computing and Applications",

issn = "0941-0643",

publisher = "Springer",

number = "11",

}

TY - JOUR

T1 - Efficient CNN-based low-resolution facial detection from UAVs

AU - Díez-Tomillo, Julio

AU - Martinez-Alpiste, Ignacio

AU - Golcarenarenji, Gelayol

AU - Wang, Qi

AU - Alcaraz-Calero, Jose M.

N1 - Copyright © The Author(s) 2024. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

PY - 2024/4

Y1 - 2024/4

N2 - Face detection in UAV imagery requires high accuracy and low execution time for real-time mission-critical operations in public safety, emergency management, disaster relief and other applications. This study presents UWS-YOLO, a new convolutional neural network (CNN)-based machine learning algorithm designed to address these demanding requirements. UWS-YOLO’s key strengths lie in its exceptional speed, remarkable accuracy and ability to handle complex UAV operations. This algorithm presents a balanced and portable solution for real-time face detection in UAV applications. Evaluation and comparison with the state-of-the-art algorithms using standard and UAV-specific datasets demonstrate UWS-YOLO’s superiority. It achieves 59.29% of accuracy compared with 27.43% in a state-of-the-art solution RetinaFace and 46.59% with YOLOv7. Additionally, UWS-YOLO operates at 11 milliseconds, which is 345% faster than RetinaFace and 373% than YOLOv7.

AB - Face detection in UAV imagery requires high accuracy and low execution time for real-time mission-critical operations in public safety, emergency management, disaster relief and other applications. This study presents UWS-YOLO, a new convolutional neural network (CNN)-based machine learning algorithm designed to address these demanding requirements. UWS-YOLO’s key strengths lie in its exceptional speed, remarkable accuracy and ability to handle complex UAV operations. This algorithm presents a balanced and portable solution for real-time face detection in UAV applications. Evaluation and comparison with the state-of-the-art algorithms using standard and UAV-specific datasets demonstrate UWS-YOLO’s superiority. It achieves 59.29% of accuracy compared with 27.43% in a state-of-the-art solution RetinaFace and 46.59% with YOLOv7. Additionally, UWS-YOLO operates at 11 milliseconds, which is 345% faster than RetinaFace and 373% than YOLOv7.

KW - face detection

KW - UAV

KW - YOLO

KW - RetinaFace

UR - https://link.springer.com/article/10.1007/s00521-023-09401-3

U2 - 10.1007/s00521-023-09401-3

DO - 10.1007/s00521-023-09401-3

M3 - Article

SN - 0941-0643

VL - 36

SP - 5847

EP - 5860

JO - Neural Computing and Applications

JF - Neural Computing and Applications

IS - 11

ER -

Efficient CNN-based low-resolution facial detection from UAVs

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this