Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection

The application of deep learning in tree pit detection of unmanned aerial vehicle (UAV) images has problems such as dense distribution, high density, small size, false detections, missed detections, and high localization error. To address these challenges, this paper proposes a small target detectio...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiuhao Liang, Jun Xiang, Sheng Qin, Yundan Xiao, Lifen Chen, Dongxia Zou, Honglun Ma, Dong Huang, Yongxin Huang, Wei Wei
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525004125
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849716747294212096
author Xiuhao Liang
Jun Xiang
Sheng Qin
Yundan Xiao
Lifen Chen
Dongxia Zou
Honglun Ma
Dong Huang
Yongxin Huang
Wei Wei
author_facet Xiuhao Liang
Jun Xiang
Sheng Qin
Yundan Xiao
Lifen Chen
Dongxia Zou
Honglun Ma
Dong Huang
Yongxin Huang
Wei Wei
author_sort Xiuhao Liang
collection DOAJ
description The application of deep learning in tree pit detection of unmanned aerial vehicle (UAV) images has problems such as dense distribution, high density, small size, false detections, missed detections, and high localization error. To address these challenges, this paper proposes a small target detection algorithm based on SAHI-ImprovedYOLOv8 for detecting tree pits, which includes Slicing Aided Hyper Inference (SAHI), Focal loss, Spatial Pyramid Pooling Concurrent Spatial Pyramid Convolution (SPPCSPC), and Convolutional Block Attention Module (CBAM). The accuracy of identification and positioning can be improved by using the SAHI via cutting high-resolution UAV imagery into slices that match the detection model, avoiding the loss of small target detail caused by direct downsampling. The identification accuracy is improved by using the Focal loss and CBAM, SPPCSPC to mitigate the data imbalance, strengthen key semantic features, and realize fine-grained information enhancement. The experimental results show that the SAHI-Improved-YOLOv8 model outperforms YOLOv3, YOLOv5, YOLOv8, YOLOv10, YOLOv11 and SAHI-YOLOv8 with a Precision of 85.17 %, a Recall of 85.07 %, a AP50–90 of 78.63 % and a F1 score of 85.12 %. In conclusion, the SAHI-Improved-YOLOv8 has the capability of efficiently processing high-resolution images, which alleviates the problems of high density of small targets, false detections, missed detections, and high localization error. In practical applications, the SAHI-Improved-YOLOv8 model performs excellently in tree pit detection in UAV imagery, significantly reducing false detections and missed detections, and providing reliable technology support for large-scale forest management.
format Article
id doaj-art-dfddf0d40ba7471f902ecc4bf04c5448
institution DOAJ
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-dfddf0d40ba7471f902ecc4bf04c54482025-08-20T03:12:53ZengElsevierSmart Agricultural Technology2772-37552025-12-011210118110.1016/j.atech.2025.101181Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detectionXiuhao Liang0Jun Xiang1Sheng Qin2Yundan Xiao3Lifen Chen4Dongxia Zou5Honglun Ma6Dong Huang7Yongxin Huang8Wei Wei9Guangxi Laboratory of Forestry, Guangxi Oil-tea Superior Species Cultivation Research Center of Engineering Technology, Nanning Eucalypt Plantation Ecosystem Observation and Research Station of Guangxi, Guangxi Forestry Research Institute, Nanning 530002, ChinaGuangxi Laboratory of Forestry, Guangxi Oil-tea Superior Species Cultivation Research Center of Engineering Technology, Nanning Eucalypt Plantation Ecosystem Observation and Research Station of Guangxi, Guangxi Forestry Research Institute, Nanning 530002, ChinaGuangxi Key Lab of Brain-inspired Computing and Intelligent Chips, School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541000, ChinaInstitute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaSchool of Physics and Telecommunication Engineering, Yulin Normal University, Yulin 537006, ChinaGuangxi Laboratory of Forestry, Guangxi Oil-tea Superior Species Cultivation Research Center of Engineering Technology, Nanning Eucalypt Plantation Ecosystem Observation and Research Station of Guangxi, Guangxi Forestry Research Institute, Nanning 530002, ChinaGuangxi Zhuang Autonomous Region State-owned Dongmen Forest Farm, Chongzuo 532108, ChinaGuilin Forestry Science Institute, Guilin 541004, ChinaGuangxi State-owned Beijianghe Forest Farm of Rongshui, Liuzhou 545000, ChinaGuangxi Laboratory of Forestry, Guangxi Oil-tea Superior Species Cultivation Research Center of Engineering Technology, Nanning Eucalypt Plantation Ecosystem Observation and Research Station of Guangxi, Guangxi Forestry Research Institute, Nanning 530002, China; Corresponding author.The application of deep learning in tree pit detection of unmanned aerial vehicle (UAV) images has problems such as dense distribution, high density, small size, false detections, missed detections, and high localization error. To address these challenges, this paper proposes a small target detection algorithm based on SAHI-ImprovedYOLOv8 for detecting tree pits, which includes Slicing Aided Hyper Inference (SAHI), Focal loss, Spatial Pyramid Pooling Concurrent Spatial Pyramid Convolution (SPPCSPC), and Convolutional Block Attention Module (CBAM). The accuracy of identification and positioning can be improved by using the SAHI via cutting high-resolution UAV imagery into slices that match the detection model, avoiding the loss of small target detail caused by direct downsampling. The identification accuracy is improved by using the Focal loss and CBAM, SPPCSPC to mitigate the data imbalance, strengthen key semantic features, and realize fine-grained information enhancement. The experimental results show that the SAHI-Improved-YOLOv8 model outperforms YOLOv3, YOLOv5, YOLOv8, YOLOv10, YOLOv11 and SAHI-YOLOv8 with a Precision of 85.17 %, a Recall of 85.07 %, a AP50–90 of 78.63 % and a F1 score of 85.12 %. In conclusion, the SAHI-Improved-YOLOv8 has the capability of efficiently processing high-resolution images, which alleviates the problems of high density of small targets, false detections, missed detections, and high localization error. In practical applications, the SAHI-Improved-YOLOv8 model performs excellently in tree pit detection in UAV imagery, significantly reducing false detections and missed detections, and providing reliable technology support for large-scale forest management.http://www.sciencedirect.com/science/article/pii/S2772375525004125Tree pit detectionSmall targetSAHI-improved-YOLOv8UAV imageryDeep learning
spellingShingle Xiuhao Liang
Jun Xiang
Sheng Qin
Yundan Xiao
Lifen Chen
Dongxia Zou
Honglun Ma
Dong Huang
Yongxin Huang
Wei Wei
Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection
Smart Agricultural Technology
Tree pit detection
Small target
SAHI-improved-YOLOv8
UAV imagery
Deep learning
title Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection
title_full Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection
title_fullStr Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection
title_full_unstemmed Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection
title_short Small target detection algorithm based on SAHI-Improved-YOLOv8 for UAV imagery: A case study of tree pit detection
title_sort small target detection algorithm based on sahi improved yolov8 for uav imagery a case study of tree pit detection
topic Tree pit detection
Small target
SAHI-improved-YOLOv8
UAV imagery
Deep learning
url http://www.sciencedirect.com/science/article/pii/S2772375525004125
work_keys_str_mv AT xiuhaoliang smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT junxiang smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT shengqin smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT yundanxiao smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT lifenchen smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT dongxiazou smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT honglunma smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT donghuang smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT yongxinhuang smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection
AT weiwei smalltargetdetectionalgorithmbasedonsahiimprovedyolov8foruavimageryacasestudyoftreepitdetection