Fig 1.
Structure of YOLOv11 model.
Fig 2.
Schematic diagram of Dynamic Convolution.
Fig 3.
Schematic diagram of Deformable Convolutional Networks (DCN).
Fig 4.
Task-aligned head structure.
Fig 5.
Ghost Module Structure.
Fig 6.
Structure diagram of GD_C3k2.
Fig 7.
Structure of the SimAM attention mechanism.
Fig 8.
Structure diagram of the improved detection head Tahead.
Fig 9.
Overall architecture of the proposed GTS-YOLO model.
Fig 10.
Samples of the dataset.
Fig 11.
Distribution of sample categories.
Table 1.
Experimental Configuration table.
Table 2.
Ablation Experiment Results.
Table 3.
Comparison Results with Mainstream Models.
Table 4.
Statistical Significance Analysis.
Table 5.
Performance Comparison Results of Different Attention Mechanisms.
Fig 12.
Comparison of Detection Results.
Fig 13.
Heatmap Comparison and Analysis.
Fig 14.
Loss Analysis of Training and Validation Processes.
Table 6.
Public Dataset Testing Results.