A coarse-to-fine vehicle detection in large SAR scenes based on GL-CFAR and PRID R-CNN

With the development of deep learning and traditional algorithms in synthetic aperture radar (SAR) image target detection, vehicle target detection under large scenes in SAR images remains a challenging research topic. This is due to various factors: the difficulty of accuracy and speed of target detection; the complexity of background interference in the large scene; partition of small block object detection; and the slow window traversal process of vehicle detection method in large scene under deep learning. To address these limitations, the key is to establish a background-target adaptation model to determine the target position and improve the performance of algorithm detection. A vehicle detection algorithm based on GL-CFAR and PRID RCNN is proposed in this study by combining traditional algorithms with deep learning algorithms. GL-CFAR is used to provide fast position coarse detection of vehicle targets in large SAR scenes, and the proposed PRID RCNN network can effectively adapt to vehicle detection in SAR large scenes, which greatly improves the detection of vehicle under different backgrounds. By adding the Pyramid Real Image Denoising Network (PRID) module to the Faster RCNN network and using the K-means method to reduce the number of detection anchor boxes, reduce background interference, and achieve feature enhancement. Experiment results show that the algorithm proposed in this study has high accuracy and processing speed.