Ship Detection Based on Faster R-CNN in SAR Imagery by Anchor Box Optimization

Object detection in synthetic aperture radar (SAR) imagery is a fundamental and challenging problem in the field of SAR imagery analysis for many fields like military, intelligence, commercial applications, etc. Object detection based on faster-regions convolutional neural network (Faster R-CNN) has lesser running time as compared to a convolutional neural network (CNN) in the detection process. Nowadays, anchor boxes are widely used in the detection model. This paper aims to provide an anchor box optimization method to improve ship detection accuracy in SAR imagery. By using Residual Network (ResNet-50) as a backbone in Faster R-CNN and it's compatible anchor sets better mean Average Precision (mAP) achieved. We compared the mAP with the two sets of anchor parameters, we found that in the ship detection process mAP achieves more than 4.29 % significant improvement.