YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images

A new algorithm called YOLO-APDM is proposed to address low quality and multi-scale target detection issues in infrared road scenes. The method reconstructs the neck section of the algorithm using the multi-scale attentional feature fusion idea. Based on this reconstruction, the P2 detection layer i...

Full description

Saved in:
Bibliographic Details
Main Authors: Song Ling, Xianggong Hong, Yongchao Liu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7197
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850227955448414208
author Song Ling
Xianggong Hong
Yongchao Liu
author_facet Song Ling
Xianggong Hong
Yongchao Liu
author_sort Song Ling
collection DOAJ
description A new algorithm called YOLO-APDM is proposed to address low quality and multi-scale target detection issues in infrared road scenes. The method reconstructs the neck section of the algorithm using the multi-scale attentional feature fusion idea. Based on this reconstruction, the P2 detection layer is established, which optimizes network structure, enhances multi-scale feature fusion performance, and expands the detection network’s capacity for multi-scale complicated targets. Replacing YOLOv8’s C2f module with C2f-DCNv3 increases the network’s ability to focus on the target region while lowering the amount of model parameters. The MSCA mechanism is added after the backbone’s SPPF module to improve the model’s detection performance by directing the network’s detection resources to the major road target detection zone. Experimental results show that on the FLIR_ADAS_v2 dataset retaining eight main categories, using YOLO-APDM compared to YOLOv8n, mAP<sub>@0.5</sub> and mAP<sub>@0.5:0.95</sub> increased by 6.6% and 5.0%, respectively. On the M3FD dataset, mAP<sub>@0.5</sub> and mAP<sub>@0.5</sub> increased by 8.1% and 5.9%, respectively. The number of model parameters and model size were reduced by 8.6% and 4.8%, respectively. The design requirements of the high-precision detection of infrared road targets were achieved while considering the requirements of model complexity control.
format Article
id doaj-art-e6bde93ec0744fa88988fa215d977884
institution OA Journals
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e6bde93ec0744fa88988fa215d9778842025-08-20T02:04:40ZengMDPI AGSensors1424-82202024-11-012422719710.3390/s24227197YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared ImagesSong Ling0Xianggong Hong1Yongchao Liu2School of Information Engineering, Nanchang University, Nanchang 330019, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330019, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330019, ChinaA new algorithm called YOLO-APDM is proposed to address low quality and multi-scale target detection issues in infrared road scenes. The method reconstructs the neck section of the algorithm using the multi-scale attentional feature fusion idea. Based on this reconstruction, the P2 detection layer is established, which optimizes network structure, enhances multi-scale feature fusion performance, and expands the detection network’s capacity for multi-scale complicated targets. Replacing YOLOv8’s C2f module with C2f-DCNv3 increases the network’s ability to focus on the target region while lowering the amount of model parameters. The MSCA mechanism is added after the backbone’s SPPF module to improve the model’s detection performance by directing the network’s detection resources to the major road target detection zone. Experimental results show that on the FLIR_ADAS_v2 dataset retaining eight main categories, using YOLO-APDM compared to YOLOv8n, mAP<sub>@0.5</sub> and mAP<sub>@0.5:0.95</sub> increased by 6.6% and 5.0%, respectively. On the M3FD dataset, mAP<sub>@0.5</sub> and mAP<sub>@0.5</sub> increased by 8.1% and 5.9%, respectively. The number of model parameters and model size were reduced by 8.6% and 4.8%, respectively. The design requirements of the high-precision detection of infrared road targets were achieved while considering the requirements of model complexity control.https://www.mdpi.com/1424-8220/24/22/7197YOLOv8infrared road detectionfeature fusiondeformable convolutionattention mechanism
spellingShingle Song Ling
Xianggong Hong
Yongchao Liu
YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images
Sensors
YOLOv8
infrared road detection
feature fusion
deformable convolution
attention mechanism
title YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images
title_full YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images
title_fullStr YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images
title_full_unstemmed YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images
title_short YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images
title_sort yolo apdm improved yolov8 for road target detection in infrared images
topic YOLOv8
infrared road detection
feature fusion
deformable convolution
attention mechanism
url https://www.mdpi.com/1424-8220/24/22/7197
work_keys_str_mv AT songling yoloapdmimprovedyolov8forroadtargetdetectionininfraredimages
AT xianggonghong yoloapdmimprovedyolov8forroadtargetdetectionininfraredimages
AT yongchaoliu yoloapdmimprovedyolov8forroadtargetdetectionininfraredimages