Cargando…
Dual-YOLO Architecture from Infrared and Visible Images for Object Detection
With the development of infrared detection technology and the improvement of military remote sensing needs, infrared object detection networks with low false alarms and high detection accuracy have been a research focus. However, due to the lack of texture information, the false detection rate of in...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10055770/ https://www.ncbi.nlm.nih.gov/pubmed/36991645 http://dx.doi.org/10.3390/s23062934 |
_version_ | 1785015953467113472 |
---|---|
author | Bao, Chun Cao, Jie Hao, Qun Cheng, Yang Ning, Yaqian Zhao, Tianhua |
author_facet | Bao, Chun Cao, Jie Hao, Qun Cheng, Yang Ning, Yaqian Zhao, Tianhua |
author_sort | Bao, Chun |
collection | PubMed |
description | With the development of infrared detection technology and the improvement of military remote sensing needs, infrared object detection networks with low false alarms and high detection accuracy have been a research focus. However, due to the lack of texture information, the false detection rate of infrared object detection is high, resulting in reduced object detection accuracy. To solve these problems, we propose an infrared object detection network named Dual-YOLO, which integrates visible image features. To ensure the speed of model detection, we choose the You Only Look Once v7 (YOLOv7) as the basic framework and design the infrared and visible images dual feature extraction channels. In addition, we develop attention fusion and fusion shuffle modules to reduce the detection error caused by redundant fusion feature information. Moreover, we introduce the Inception and SE modules to enhance the complementary characteristics of infrared and visible images. Furthermore, we design the fusion loss function to make the network converge fast during training. The experimental results show that the proposed Dual-YOLO network reaches 71.8% mean Average Precision (mAP) in the DroneVehicle remote sensing dataset and 73.2% mAP in the KAIST pedestrian dataset. The detection accuracy reaches 84.5% in the FLIR dataset. The proposed architecture is expected to be applied in the fields of military reconnaissance, unmanned driving, and public safety. |
format | Online Article Text |
id | pubmed-10055770 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100557702023-03-30 Dual-YOLO Architecture from Infrared and Visible Images for Object Detection Bao, Chun Cao, Jie Hao, Qun Cheng, Yang Ning, Yaqian Zhao, Tianhua Sensors (Basel) Article With the development of infrared detection technology and the improvement of military remote sensing needs, infrared object detection networks with low false alarms and high detection accuracy have been a research focus. However, due to the lack of texture information, the false detection rate of infrared object detection is high, resulting in reduced object detection accuracy. To solve these problems, we propose an infrared object detection network named Dual-YOLO, which integrates visible image features. To ensure the speed of model detection, we choose the You Only Look Once v7 (YOLOv7) as the basic framework and design the infrared and visible images dual feature extraction channels. In addition, we develop attention fusion and fusion shuffle modules to reduce the detection error caused by redundant fusion feature information. Moreover, we introduce the Inception and SE modules to enhance the complementary characteristics of infrared and visible images. Furthermore, we design the fusion loss function to make the network converge fast during training. The experimental results show that the proposed Dual-YOLO network reaches 71.8% mean Average Precision (mAP) in the DroneVehicle remote sensing dataset and 73.2% mAP in the KAIST pedestrian dataset. The detection accuracy reaches 84.5% in the FLIR dataset. The proposed architecture is expected to be applied in the fields of military reconnaissance, unmanned driving, and public safety. MDPI 2023-03-08 /pmc/articles/PMC10055770/ /pubmed/36991645 http://dx.doi.org/10.3390/s23062934 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Bao, Chun Cao, Jie Hao, Qun Cheng, Yang Ning, Yaqian Zhao, Tianhua Dual-YOLO Architecture from Infrared and Visible Images for Object Detection |
title | Dual-YOLO Architecture from Infrared and Visible Images for Object Detection |
title_full | Dual-YOLO Architecture from Infrared and Visible Images for Object Detection |
title_fullStr | Dual-YOLO Architecture from Infrared and Visible Images for Object Detection |
title_full_unstemmed | Dual-YOLO Architecture from Infrared and Visible Images for Object Detection |
title_short | Dual-YOLO Architecture from Infrared and Visible Images for Object Detection |
title_sort | dual-yolo architecture from infrared and visible images for object detection |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10055770/ https://www.ncbi.nlm.nih.gov/pubmed/36991645 http://dx.doi.org/10.3390/s23062934 |
work_keys_str_mv | AT baochun dualyoloarchitecturefrominfraredandvisibleimagesforobjectdetection AT caojie dualyoloarchitecturefrominfraredandvisibleimagesforobjectdetection AT haoqun dualyoloarchitecturefrominfraredandvisibleimagesforobjectdetection AT chengyang dualyoloarchitecturefrominfraredandvisibleimagesforobjectdetection AT ningyaqian dualyoloarchitecturefrominfraredandvisibleimagesforobjectdetection AT zhaotianhua dualyoloarchitecturefrominfraredandvisibleimagesforobjectdetection |