Fig 1.
The architecture of YOLO11.
Fig 2.
The architecture of AOW-YOLO.
Fig 3.
Illustration of the Loss Function.
Intersection over Union (IoU) represents the ratio of the intersection between the predicted bounding box and the ground truth bounding box. Parameters involved in formula 1: denotes the Euclidean distance between the centroid of the ground truth box and the predicted box; h and w represent the height and width of the predicted box; hgt and wgt denote the height and width of the ground truth box; ch and cw denote the height and width of the minimum bounding box formed by the Prediction Box and Real Box.
Table 1.
Definitions of symbols used in the loss functions.
Fig 4.
Diagram of SGP.
Fig 5.
If its input feature map shape is , with a scaling factor of scale. It generates a new feature map with shape
(where scale is the scaling factor).
Fig 6.
Diagram of Pointwise Convolution.
Table 2.
The detailed architecture of LCFNet.
Table 3.
Experimental Hardware and Software Configuration.
Table 4.
Test Condition.
Table 5.
Comparison of different loss functions.
Fig 7.
Comparison of Convergence Rates Across Loss Functions.
Table 6.
Ablation study of AOW-YOLO.
Table 7.
Comparison of different models.
Fig 8.
Model Inference Results.
Fig 9.
Detection examples of AOW-YOLO.
[The individual in this manuscript has given written informed consent (as outlined in PLOS consent form) to publish this image].