[Objective]This paper proposes a lightweight remote sensing ship target detection algorithm LR-YOLO based on improved YOLOv5s to meet the lightweight and fast inference requirements of ship target de-tection tasks involving remote sensing images.[Methods]First,the backbone network adopts the ShuffleN-et v2 block stacking method,effectively reducing the number of network model parameters and improving the computational speed;second,a region selection module filter is designed to select regions of interest and ex-tract effective features more fully;finally,a circular smooth label is introduced to calculate angle loss and per-form rotation detection on remote sensing ship targets,while deformable convolution is used to adapt to geo-metric deformation and improve detection performance.[Results]The experimental results on the HRSC2016 ship dataset show that the detection accuracy of the algorithm reaches 92.90%,an improvement of 1.3%,with the number of network model parameters only 39.33%that of the baseline model.[Conclusion]The proposed algorithm achieves a balance between lightweight and detection accuracy,providing references for remote sensing ship target detection.
维普
万方数据