Small-Target Detection Algorithm Based on STDA-YOLOv8

Due to the inherent limitations of detection networks and the imbalance in training data, small-target detection has always been a challenging issue in the field of target detection. To address the issues of false positives and missed detections in small-target detection scenarios, a new algorithm b...

Full description

Saved in:
Bibliographic Details
Main Authors: Cun Li, Shuhai Jiang, Xunan Cao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2861
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312761859801088
author Cun Li
Shuhai Jiang
Xunan Cao
author_facet Cun Li
Shuhai Jiang
Xunan Cao
author_sort Cun Li
collection DOAJ
description Due to the inherent limitations of detection networks and the imbalance in training data, small-target detection has always been a challenging issue in the field of target detection. To address the issues of false positives and missed detections in small-target detection scenarios, a new algorithm based on STDA-YOLOv8 is proposed for small-target detection. A novel network architecture for small-target detection is designed, incorporating a Contextual Augmentation Module (CAM) and a Feature Refinement Module (FRM) to enhance the detection performance for small targets. The CAM introduces multi-scale dilated convolutions, where convolutional kernels with different dilation rates capture contextual information from various receptive fields, enabling more accurate extraction of small-target features. The FRM performs adaptive feature fusion in both channel and spatial dimensions, significantly improving the detection precision for small targets. Addressing the issue of a significant disparity in the number of annotations between small and larger objects in existing classic public datasets, a new data augmentation method called Copy–Reduce–Paste is introduced. Ablation and comparative experiments conducted on the proposed STDA-YOLOv8 model demonstrate that on the VisDrone dataset, its accuracy improved by 5.3% compared to YOLOv8, reaching 93.5%; on the PASCAL VOC dataset, its accuracy increased by 5.7% compared to YOLOv8, achieving 94.2%, outperforming current mainstream target detection models and small-target detection algorithms like QueryDet, effectively enhancing small-target detection capabilities.
format Article
id doaj-art-ddb5ff3a86a644c59bbf83b6c1111bef
institution Kabale University
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-ddb5ff3a86a644c59bbf83b6c1111bef2025-08-20T03:52:57ZengMDPI AGSensors1424-82202025-04-01259286110.3390/s25092861Small-Target Detection Algorithm Based on STDA-YOLOv8Cun Li0Shuhai Jiang1Xunan Cao2School of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaSchool of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaSchool of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaDue to the inherent limitations of detection networks and the imbalance in training data, small-target detection has always been a challenging issue in the field of target detection. To address the issues of false positives and missed detections in small-target detection scenarios, a new algorithm based on STDA-YOLOv8 is proposed for small-target detection. A novel network architecture for small-target detection is designed, incorporating a Contextual Augmentation Module (CAM) and a Feature Refinement Module (FRM) to enhance the detection performance for small targets. The CAM introduces multi-scale dilated convolutions, where convolutional kernels with different dilation rates capture contextual information from various receptive fields, enabling more accurate extraction of small-target features. The FRM performs adaptive feature fusion in both channel and spatial dimensions, significantly improving the detection precision for small targets. Addressing the issue of a significant disparity in the number of annotations between small and larger objects in existing classic public datasets, a new data augmentation method called Copy–Reduce–Paste is introduced. Ablation and comparative experiments conducted on the proposed STDA-YOLOv8 model demonstrate that on the VisDrone dataset, its accuracy improved by 5.3% compared to YOLOv8, reaching 93.5%; on the PASCAL VOC dataset, its accuracy increased by 5.7% compared to YOLOv8, achieving 94.2%, outperforming current mainstream target detection models and small-target detection algorithms like QueryDet, effectively enhancing small-target detection capabilities.https://www.mdpi.com/1424-8220/25/9/2861small-target detectioncontextual augmentationfeature refinementYOLOv8
spellingShingle Cun Li
Shuhai Jiang
Xunan Cao
Small-Target Detection Algorithm Based on STDA-YOLOv8
Sensors
small-target detection
contextual augmentation
feature refinement
YOLOv8
title Small-Target Detection Algorithm Based on STDA-YOLOv8
title_full Small-Target Detection Algorithm Based on STDA-YOLOv8
title_fullStr Small-Target Detection Algorithm Based on STDA-YOLOv8
title_full_unstemmed Small-Target Detection Algorithm Based on STDA-YOLOv8
title_short Small-Target Detection Algorithm Based on STDA-YOLOv8
title_sort small target detection algorithm based on stda yolov8
topic small-target detection
contextual augmentation
feature refinement
YOLOv8
url https://www.mdpi.com/1424-8220/25/9/2861
work_keys_str_mv AT cunli smalltargetdetectionalgorithmbasedonstdayolov8
AT shuhaijiang smalltargetdetectionalgorithmbasedonstdayolov8
AT xunancao smalltargetdetectionalgorithmbasedonstdayolov8