Small Target Detection on Water Based on Improved YOLOv7 Unmanned Vessel

The problems of low detection accuracy and high leakage rate of small targets on the water’s surface when observed from the viewpoint of an uncrewed ship are proposed to be resolved by an improved YOLOv7 detection algorithm. Firstly, the parameter-free attention mechanisms SimAM and PConv are introduced into the network to enhance the model’s feature extraction for small targets and reduce the number of model parameters, and SimAM and PConv in the backbone are combined with ELAN1 to form a new efficient layer aggregation network module ELAN1-SAPC. Then, the Head part of the model adopts the newly proposed MP-CXOS structure, which can enhance the model’s focus on small targets and effectively reduce the loss of small target feature information. Finally, the loss function is optimized by incorporating the new NWD metric approach to improve the model’s ability to detect small targets and speed up network convergence. The data set is also processed using data augmentation to improve the model’s generalization. The experiments show that compared with the basic model, the mean Average Precision of the improved YOLOv7 model increases by 5.3 per cent, the F1 score increases by 0.06, and the number of parameters decreases by 20.0 per cent. Therefore, the improved model has significantly improved detection performance and is more lightweight.