Vehicle detection method based on multi-layer selective feature for UAV aerial images

Abstract (UAVs) play a critical role in traffic flow monitoring and rapid accident response. However, this task remains challenging due to variable high-altitude viewpoints, complex environmental interference, and limitations in algorithmic efficiency. To address these issues, a lightweight vehicle...

Full description

Saved in:
Bibliographic Details
Main Authors: Yinbao Ma, Yuyu Meng, Jiuyuan Huo
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00150-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341911437934592
author Yinbao Ma
Yuyu Meng
Jiuyuan Huo
author_facet Yinbao Ma
Yuyu Meng
Jiuyuan Huo
author_sort Yinbao Ma
collection DOAJ
description Abstract (UAVs) play a critical role in traffic flow monitoring and rapid accident response. However, this task remains challenging due to variable high-altitude viewpoints, complex environmental interference, and limitations in algorithmic efficiency. To address these issues, a lightweight vehicle detection model is developed based on UAV aerial imagery. In the backbone, a Receptive-Field Attention Convolution (RFAConv) module is introduced to retain detailed features during the downsampling process. To handle complex environments such as illumination changes and dense occlusion, a Cross-Stage Partial Fusion Bi-Level Routing Attention Network (CSP-BLRAN) module is employed to enhance contextual feature representation and suppress false and missed detections. In the neck, a multi-layer selective feature fusion pyramid (MS-FPN) is constructed to perform attention-based filtering on high-level semantic features and low-level spatial details, followed by feature enhancement via multiplication and global semantic refinement through residual connections. For the detection head, a Generalized Wasserstein Distance Loss (GWDLoss) function is proposed to quantify positional and scale discrepancies, improving the adaptability of bounding box regression to geometric variations. Extensive experiments on the VisDrone and Vehicle datasets demonstrate that the proposed method reduces the number of parameters by 22.9% and achieves mAP@50–95 improvements of 4.5% and 7.3%, respectively, over YOLO11n. The approach also surpasses mainstream models such as YOLO11s with significantly fewer parameters, confirming its effectiveness and practical value in resource-constrained low-altitude UAV-based detection tasks.
format Article
id doaj-art-9151c1bdabcc494ba84416b3a30ed5d9
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-9151c1bdabcc494ba84416b3a30ed5d92025-08-20T03:43:31ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-07-0137612810.1007/s44443-025-00150-yVehicle detection method based on multi-layer selective feature for UAV aerial imagesYinbao Ma0Yuyu Meng1Jiuyuan Huo2School of Electronic and Information Engineering, Lanzhou Jiaotong UniversitySchool of Electronic and Information Engineering, Lanzhou Jiaotong UniversitySchool of Electronic and Information Engineering, Lanzhou Jiaotong UniversityAbstract (UAVs) play a critical role in traffic flow monitoring and rapid accident response. However, this task remains challenging due to variable high-altitude viewpoints, complex environmental interference, and limitations in algorithmic efficiency. To address these issues, a lightweight vehicle detection model is developed based on UAV aerial imagery. In the backbone, a Receptive-Field Attention Convolution (RFAConv) module is introduced to retain detailed features during the downsampling process. To handle complex environments such as illumination changes and dense occlusion, a Cross-Stage Partial Fusion Bi-Level Routing Attention Network (CSP-BLRAN) module is employed to enhance contextual feature representation and suppress false and missed detections. In the neck, a multi-layer selective feature fusion pyramid (MS-FPN) is constructed to perform attention-based filtering on high-level semantic features and low-level spatial details, followed by feature enhancement via multiplication and global semantic refinement through residual connections. For the detection head, a Generalized Wasserstein Distance Loss (GWDLoss) function is proposed to quantify positional and scale discrepancies, improving the adaptability of bounding box regression to geometric variations. Extensive experiments on the VisDrone and Vehicle datasets demonstrate that the proposed method reduces the number of parameters by 22.9% and achieves mAP@50–95 improvements of 4.5% and 7.3%, respectively, over YOLO11n. The approach also surpasses mainstream models such as YOLO11s with significantly fewer parameters, confirming its effectiveness and practical value in resource-constrained low-altitude UAV-based detection tasks.https://doi.org/10.1007/s44443-025-00150-yMulti-scaleUAV aerial image vehicle detectionDownsamplingFeature fusionLoss function
spellingShingle Yinbao Ma
Yuyu Meng
Jiuyuan Huo
Vehicle detection method based on multi-layer selective feature for UAV aerial images
Journal of King Saud University: Computer and Information Sciences
Multi-scale
UAV aerial image vehicle detection
Downsampling
Feature fusion
Loss function
title Vehicle detection method based on multi-layer selective feature for UAV aerial images
title_full Vehicle detection method based on multi-layer selective feature for UAV aerial images
title_fullStr Vehicle detection method based on multi-layer selective feature for UAV aerial images
title_full_unstemmed Vehicle detection method based on multi-layer selective feature for UAV aerial images
title_short Vehicle detection method based on multi-layer selective feature for UAV aerial images
title_sort vehicle detection method based on multi layer selective feature for uav aerial images
topic Multi-scale
UAV aerial image vehicle detection
Downsampling
Feature fusion
Loss function
url https://doi.org/10.1007/s44443-025-00150-y
work_keys_str_mv AT yinbaoma vehicledetectionmethodbasedonmultilayerselectivefeatureforuavaerialimages
AT yuyumeng vehicledetectionmethodbasedonmultilayerselectivefeatureforuavaerialimages
AT jiuyuanhuo vehicledetectionmethodbasedonmultilayerselectivefeatureforuavaerialimages