Small object detection in complex open-pit mine backgrounds based on improved YOLOv11

Small object detection in open-pit mines faces challenges such as wide viewing angles and long detection distances, which result in small target imaging. Existing object detection models suffer from feature attenuation caused by progressive image downsampling operations. To address this issue, an im...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHU Yongjun, CAI Guangqi, HAN Jin, MIAO Yanzi, MA Xiaoping, JIAO Wenhua
Format: Article
Language:zho
Published: Editorial Department of Industry and Mine Automation 2025-04-01
Series:Gong-kuang zidonghua
Subjects:
Online Access:http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2025020018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414806284533760
author ZHU Yongjun
CAI Guangqi
HAN Jin
MIAO Yanzi
MA Xiaoping
JIAO Wenhua
author_facet ZHU Yongjun
CAI Guangqi
HAN Jin
MIAO Yanzi
MA Xiaoping
JIAO Wenhua
author_sort ZHU Yongjun
collection DOAJ
description Small object detection in open-pit mines faces challenges such as wide viewing angles and long detection distances, which result in small target imaging. Existing object detection models suffer from feature attenuation caused by progressive image downsampling operations. To address this issue, an improved YOLOv11 model was proposed and applied to small object detection under complex backgrounds in open-pit mines. The improved YOLOv11 model introduced a Robust Feature Downsampling (RFD) module to replace the stride convolution downsampling module, effectively preserving the feature information of small objects. A Small Target Feature Enhancement Neck (STFEN) network was designed to replace the original feature pyramid structure in the neck, incorporating a cross-stage partial fusion module to integrate feature maps from different levels. The original CIoU loss function was replaced with the Powerful-IoU (PIoU) loss function to solve the anchor box expansion issue during training, enabling the model to rapidly and accurately focus on small targets. Experimental results on a small object dataset from open-pit mining areas showed that: ① the RFD module reduced model parameters while increasing mAP by 1.5%. Although the STFEN network increased the number of parameters, it improved mAP by 2.2%. The PIoU loss function improved mAP by 1.7% without changing the number of parameters or FLOPs. The combination of all three led to a total mAP improvement of 3.9%. ② The improved YOLOv11 model achieved higher accuracy while maintaining a high inference speed, with mAP improvements of 2.6%, 1.5%, 0.9%, and 2.2% over YOLOv5m, YOLOv8m, YOLOv11m, and RtDetr-L, respectively, and with fewer parameters, making it more suitable for edge deployment.
format Article
id doaj-art-ac90e7575b95491980df8e69f5cdf3d6
institution Kabale University
issn 1671-251X
language zho
publishDate 2025-04-01
publisher Editorial Department of Industry and Mine Automation
record_format Article
series Gong-kuang zidonghua
spelling doaj-art-ac90e7575b95491980df8e69f5cdf3d62025-08-20T03:33:42ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2025-04-01514939910.13272/j.issn.1671-251x.2025020018Small object detection in complex open-pit mine backgrounds based on improved YOLOv11ZHU Yongjun0CAI Guangqi1HAN Jin2MIAO YanziMA Xiaoping3JIAO WenhuaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaChina Coal Pingshuo Group Co., Ltd., Shuozhou 036006, ChinaChina Coal Pingshuo Group Co., Ltd., Shuozhou 036006, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSmall object detection in open-pit mines faces challenges such as wide viewing angles and long detection distances, which result in small target imaging. Existing object detection models suffer from feature attenuation caused by progressive image downsampling operations. To address this issue, an improved YOLOv11 model was proposed and applied to small object detection under complex backgrounds in open-pit mines. The improved YOLOv11 model introduced a Robust Feature Downsampling (RFD) module to replace the stride convolution downsampling module, effectively preserving the feature information of small objects. A Small Target Feature Enhancement Neck (STFEN) network was designed to replace the original feature pyramid structure in the neck, incorporating a cross-stage partial fusion module to integrate feature maps from different levels. The original CIoU loss function was replaced with the Powerful-IoU (PIoU) loss function to solve the anchor box expansion issue during training, enabling the model to rapidly and accurately focus on small targets. Experimental results on a small object dataset from open-pit mining areas showed that: ① the RFD module reduced model parameters while increasing mAP by 1.5%. Although the STFEN network increased the number of parameters, it improved mAP by 2.2%. The PIoU loss function improved mAP by 1.7% without changing the number of parameters or FLOPs. The combination of all three led to a total mAP improvement of 3.9%. ② The improved YOLOv11 model achieved higher accuracy while maintaining a high inference speed, with mAP improvements of 2.6%, 1.5%, 0.9%, and 2.2% over YOLOv5m, YOLOv8m, YOLOv11m, and RtDetr-L, respectively, and with fewer parameters, making it more suitable for edge deployment.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2025020018open-pit minesmall object detectionyolov11robust feature downsamplingsmall target feature enhancement neckpiou loss function
spellingShingle ZHU Yongjun
CAI Guangqi
HAN Jin
MIAO Yanzi
MA Xiaoping
JIAO Wenhua
Small object detection in complex open-pit mine backgrounds based on improved YOLOv11
Gong-kuang zidonghua
open-pit mine
small object detection
yolov11
robust feature downsampling
small target feature enhancement neck
piou loss function
title Small object detection in complex open-pit mine backgrounds based on improved YOLOv11
title_full Small object detection in complex open-pit mine backgrounds based on improved YOLOv11
title_fullStr Small object detection in complex open-pit mine backgrounds based on improved YOLOv11
title_full_unstemmed Small object detection in complex open-pit mine backgrounds based on improved YOLOv11
title_short Small object detection in complex open-pit mine backgrounds based on improved YOLOv11
title_sort small object detection in complex open pit mine backgrounds based on improved yolov11
topic open-pit mine
small object detection
yolov11
robust feature downsampling
small target feature enhancement neck
piou loss function
url http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671-251x.2025020018
work_keys_str_mv AT zhuyongjun smallobjectdetectionincomplexopenpitminebackgroundsbasedonimprovedyolov11
AT caiguangqi smallobjectdetectionincomplexopenpitminebackgroundsbasedonimprovedyolov11
AT hanjin smallobjectdetectionincomplexopenpitminebackgroundsbasedonimprovedyolov11
AT miaoyanzi smallobjectdetectionincomplexopenpitminebackgroundsbasedonimprovedyolov11
AT maxiaoping smallobjectdetectionincomplexopenpitminebackgroundsbasedonimprovedyolov11
AT jiaowenhua smallobjectdetectionincomplexopenpitminebackgroundsbasedonimprovedyolov11