RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion

The paper proposes a model based on receptive field enhancement and cross-scale fusion (RFCS-YOLO). It addresses challenges like complex backgrounds and problems of missing and mis-detecting traffic targets in bad weather. First, an efficient feature extraction module (EFEM) is created. It reconfigu...

Full description

Saved in:
Bibliographic Details
Main Authors: Gang Liu, Yingzheng Huang, Shuguang Yan, Enxiang Hou
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/912
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199718258278400
author Gang Liu
Yingzheng Huang
Shuguang Yan
Enxiang Hou
author_facet Gang Liu
Yingzheng Huang
Shuguang Yan
Enxiang Hou
author_sort Gang Liu
collection DOAJ
description The paper proposes a model based on receptive field enhancement and cross-scale fusion (RFCS-YOLO). It addresses challenges like complex backgrounds and problems of missing and mis-detecting traffic targets in bad weather. First, an efficient feature extraction module (EFEM) is created. It reconfigures the backbone network. This helps to make the receptive field better and improves its ability to extract features of targets at different scales. Next, a cross-scale fusion module (CSF) is introduced. It uses the receptive field coordinate attention mechanism (RFCA) to fuse information from different scales well. It also filters out noise and background information that might interfere. Also, a new Focaler-Minimum Point Distance Intersection over Union (F-MPDIoU) loss function is proposed. It makes the model converge faster and deals with issues of leakage and false detection. Experiments were conducted on the expanded Vehicle Detection in Adverse Weather Nature dataset (DWAN). The results show significant improvements compared to the conventional You Only Look Once v7 (YOLOv7) model. The mean Average Precision (mAP@0.5), precision, and recall are enhanced by 4.2%, 8.3%, and 1.4%, respectively. The mean Average Precision is 86.5%. The frame rate is 68 frames per second (FPS), which meets the requirements for real-time detection. A generalization experiment was conducted using the autonomous driving dataset SODA10M. The mAP@0.5 achieved 56.7%, which is a 3.6% improvement over the original model. This result demonstrates the good generalization ability of the proposed method.
format Article
id doaj-art-4549b6f09b4c43dfa70770fbfebf3b0e
institution OA Journals
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4549b6f09b4c43dfa70770fbfebf3b0e2025-08-20T02:12:33ZengMDPI AGSensors1424-82202025-02-0125391210.3390/s25030912RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale FusionGang Liu0Yingzheng Huang1Shuguang Yan2Enxiang Hou3Jiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence, Wuxi University, Wuxi 214105, ChinaSchool of Electronics and Information Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Electronics and Information Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Electronics and Information Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaThe paper proposes a model based on receptive field enhancement and cross-scale fusion (RFCS-YOLO). It addresses challenges like complex backgrounds and problems of missing and mis-detecting traffic targets in bad weather. First, an efficient feature extraction module (EFEM) is created. It reconfigures the backbone network. This helps to make the receptive field better and improves its ability to extract features of targets at different scales. Next, a cross-scale fusion module (CSF) is introduced. It uses the receptive field coordinate attention mechanism (RFCA) to fuse information from different scales well. It also filters out noise and background information that might interfere. Also, a new Focaler-Minimum Point Distance Intersection over Union (F-MPDIoU) loss function is proposed. It makes the model converge faster and deals with issues of leakage and false detection. Experiments were conducted on the expanded Vehicle Detection in Adverse Weather Nature dataset (DWAN). The results show significant improvements compared to the conventional You Only Look Once v7 (YOLOv7) model. The mean Average Precision (mAP@0.5), precision, and recall are enhanced by 4.2%, 8.3%, and 1.4%, respectively. The mean Average Precision is 86.5%. The frame rate is 68 frames per second (FPS), which meets the requirements for real-time detection. A generalization experiment was conducted using the autonomous driving dataset SODA10M. The mAP@0.5 achieved 56.7%, which is a 3.6% improvement over the original model. This result demonstrates the good generalization ability of the proposed method.https://www.mdpi.com/1424-8220/25/3/912receptive field enhancementcross-scale fusionattention mechanismYOLOv7loss function
spellingShingle Gang Liu
Yingzheng Huang
Shuguang Yan
Enxiang Hou
RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion
Sensors
receptive field enhancement
cross-scale fusion
attention mechanism
YOLOv7
loss function
title RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion
title_full RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion
title_fullStr RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion
title_full_unstemmed RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion
title_short RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion
title_sort rfcs yolo target detection algorithm in adverse weather conditions via receptive field enhancement and cross scale fusion
topic receptive field enhancement
cross-scale fusion
attention mechanism
YOLOv7
loss function
url https://www.mdpi.com/1424-8220/25/3/912
work_keys_str_mv AT gangliu rfcsyolotargetdetectionalgorithminadverseweatherconditionsviareceptivefieldenhancementandcrossscalefusion
AT yingzhenghuang rfcsyolotargetdetectionalgorithminadverseweatherconditionsviareceptivefieldenhancementandcrossscalefusion
AT shuguangyan rfcsyolotargetdetectionalgorithminadverseweatherconditionsviareceptivefieldenhancementandcrossscalefusion
AT enxianghou rfcsyolotargetdetectionalgorithminadverseweatherconditionsviareceptivefieldenhancementandcrossscalefusion