Small target detection algorithm based on the fusion attention mechanism and multi-layer convolution

• Published in: PloS one Vol. 20; no. 7; p. e0328003
• Main Authors: Li, Xiujing, Zhang, Haifei, Hang, Yiliu, Chen, Hao
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 31.07.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Analysis; Biology and Life Sciences; Classification; Computer and Information Sciences; Convolution; Deep learning; Design; Detection Algorithms; Image processing; Localization; Machine vision; Medicine and Health Sciences; Methods; Modules; Multilayers; Neural networks; Object recognition; Physical Sciences; Research and Analysis Methods; Semantics; Social Sciences; Surveillance; Target detection; Telematics; Unmanned Aerial Devices; Unmanned aerial vehicles; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0328003

In the realm of unmanned aerial vehicles, we proposed an enhanced small target detection algorithm, MGAC-YOLO, to address the challenges of missed detections and low accuracy associated with small target identification. Initially, we designed the MConv (Multi-layer Convolution) module to replace the conventional Conv module within the backbone network, thereby augmenting the dimensionality of information capture and enhancing the detection performance for small targets. Subsequently, we harnessed the advantages of both attention mechanisms—GAM (Global Attention Mechanism) and CloAttention (Contextualized Local and Global Attention)—to create a GACAttention module that extracts small target features from both global and local perspectives, thereby enriching the network’s focus on small target feature information and further enhancing its feature processing capabilities. Finally, we incorporated an additional small target detection layer to capture feature information at a shallower level, thereby reducing the likelihood of missed detections and bolstering the detection capabilities for small targets. Experimental results on the VisDrone2019 dataset demonstrate that the Precision, mAP 50 , and mAP 50-95 of the MGAC-YOLO algorithm have improved by 5.3%, 6.3%, and 4.4%, respectively, in comparison to the baseline model YOLOv8s. Furthermore, when compared to other leading algorithms, the MGAC-YOLO algorithm has exhibited notable superiority.