I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images

UAV small target detection in urban security, disaster monitoring, agricultural inspection, and other fields faces the challenge of increasing accuracy and real-time requirements. However, existing detection algorithms still have weak small target representation ability, extensive computational reso...

Full description

Saved in:
Bibliographic Details
Main Authors: Yukai Ma, Caiping Xi, Ting Ma, Han Sun, Huiyang Lu, Xiang Xu, Chen Xu
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4857
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405868467027968
author Yukai Ma
Caiping Xi
Ting Ma
Han Sun
Huiyang Lu
Xiang Xu
Chen Xu
author_facet Yukai Ma
Caiping Xi
Ting Ma
Han Sun
Huiyang Lu
Xiang Xu
Chen Xu
author_sort Yukai Ma
collection DOAJ
description UAV small target detection in urban security, disaster monitoring, agricultural inspection, and other fields faces the challenge of increasing accuracy and real-time requirements. However, existing detection algorithms still have weak small target representation ability, extensive computational resource overhead, and poor deployment adaptability. Therefore, this paper proposes a lightweight algorithm, I-YOLOv11n, based on YOLOv11n, which is systematically improved in terms of both feature enhancement and structure compression. The RFCBAMConv module that combines deformable convolution and channel–spatial attention is designed to adjust the receptive field and strengthen the edge features dynamically. The multiscale pyramid of STCMSP context and the lightweight Transformer–DyHead hybrid detection head are designed by combining the multiscale hole feature pyramid (DFPC), which realizes the cross-scale semantic modeling and adaptive focusing of the target area. A collaborative lightweight strategy is proposed. Firstly, the semantic discrimination ability of the teacher model for small targets is transferred to guide and protect the subsequent compression process by integrating the mixed knowledge distillation of response alignment, feature imitation, and structure maintenance. Secondly, the LAMP–Taylor channel pruning mechanism is used to compress the model redundancy, mainly to protect the key channels sensitive to shallow small targets. Finally, K-means++ anchor frame optimization based on IoU distance is implemented to adapt the feature structure retained after pruning and the scale distribution of small targets of UAV. While significantly reducing the model size (parameter 3.87 M, calculation 14.7 GFLOPs), the detection accuracy of small targets is effectively maintained and improved. Experiments on VisDrone, AI-TOD, and SODA-A datasets show that the mAP@0.5 and mAP@0.5:0.95 of I-YOLOv11n are 7.1% and 4.9% higher than the benchmark model YOLOv11 n, respectively, while maintaining real-time processing capabilities, verifying its comprehensive advantages in accuracy, light weight, and deployment.
format Article
id doaj-art-04b9f3cf613447328c3da545af23c631
institution Kabale University
issn 1424-8220
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-04b9f3cf613447328c3da545af23c6312025-08-20T03:36:34ZengMDPI AGSensors1424-82202025-08-012515485710.3390/s25154857I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial ImagesYukai Ma0Caiping Xi1Ting Ma2Han Sun3Huiyang Lu4Xiang Xu5Chen Xu6College of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaCollege of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaCollege of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaSchool of Integrated Circuits, Tsinghua University, Beijing 100084, ChinaCollege of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaCollege of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaCollege of Automation, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaUAV small target detection in urban security, disaster monitoring, agricultural inspection, and other fields faces the challenge of increasing accuracy and real-time requirements. However, existing detection algorithms still have weak small target representation ability, extensive computational resource overhead, and poor deployment adaptability. Therefore, this paper proposes a lightweight algorithm, I-YOLOv11n, based on YOLOv11n, which is systematically improved in terms of both feature enhancement and structure compression. The RFCBAMConv module that combines deformable convolution and channel–spatial attention is designed to adjust the receptive field and strengthen the edge features dynamically. The multiscale pyramid of STCMSP context and the lightweight Transformer–DyHead hybrid detection head are designed by combining the multiscale hole feature pyramid (DFPC), which realizes the cross-scale semantic modeling and adaptive focusing of the target area. A collaborative lightweight strategy is proposed. Firstly, the semantic discrimination ability of the teacher model for small targets is transferred to guide and protect the subsequent compression process by integrating the mixed knowledge distillation of response alignment, feature imitation, and structure maintenance. Secondly, the LAMP–Taylor channel pruning mechanism is used to compress the model redundancy, mainly to protect the key channels sensitive to shallow small targets. Finally, K-means++ anchor frame optimization based on IoU distance is implemented to adapt the feature structure retained after pruning and the scale distribution of small targets of UAV. While significantly reducing the model size (parameter 3.87 M, calculation 14.7 GFLOPs), the detection accuracy of small targets is effectively maintained and improved. Experiments on VisDrone, AI-TOD, and SODA-A datasets show that the mAP@0.5 and mAP@0.5:0.95 of I-YOLOv11n are 7.1% and 4.9% higher than the benchmark model YOLOv11 n, respectively, while maintaining real-time processing capabilities, verifying its comprehensive advantages in accuracy, light weight, and deployment.https://www.mdpi.com/1424-8220/25/15/4857small object detectionYOLOv11nRFCBAMConvDFPCSTCMSPknowledge distillation
spellingShingle Yukai Ma
Caiping Xi
Ting Ma
Han Sun
Huiyang Lu
Xiang Xu
Chen Xu
I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images
Sensors
small object detection
YOLOv11n
RFCBAMConv
DFPC
STCMSP
knowledge distillation
title I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images
title_full I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images
title_fullStr I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images
title_full_unstemmed I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images
title_short I-YOLOv11n: A Lightweight and Efficient Small Target Detection Framework for UAV Aerial Images
title_sort i yolov11n a lightweight and efficient small target detection framework for uav aerial images
topic small object detection
YOLOv11n
RFCBAMConv
DFPC
STCMSP
knowledge distillation
url https://www.mdpi.com/1424-8220/25/15/4857
work_keys_str_mv AT yukaima iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages
AT caipingxi iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages
AT tingma iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages
AT hansun iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages
AT huiyanglu iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages
AT xiangxu iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages
AT chenxu iyolov11nalightweightandefficientsmalltargetdetectionframeworkforuavaerialimages