Multi-Dimensional Automatic Detection of Scanning Radar Images of Marine Targets Based on Radar PPInet

Traditional radar target detection algorithms are mostly based on statistical theory. They have weak generalization capabilities for complex sea clutter environments and diverse characteristics, their performance would be significantly reduced. In this paper, the range-azimuth-frame information obtained by scanning is converted into plain position indicator (PPI) images, a novel Radar-PPInet proposed used marine detection. The model includes CSPDarknet53, SPP, PANet, power non-maximum suppression (P-NMS), multi-frame fusion section. prediction frame coordinates, category, corresponding confidence directly given through feature extraction network. network structure strengthens receptive field attention distribution structure, further improves efficiency of training. P-NMS can effectively improve problem missed multi-targets. Moreover, false alarms caused strong reduced fusion, which also benefit verification using X-band navigation PPI image dataset shows that compared with traditional cell-average constant alarm rate detector (CA-CFAR) two-stage Faster R-CNN algorithm, method improved probability 15% 10% under certain conditions, more suitable various environment characteristics. computational burden discussed showing lower than in terms parameters calculations.