Fast Single-Shot Ship Instance Segmentation Based on Polar Template Mask in Remote Sensing Images

Abstract

Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets. The latest methods tried to take into account both the efficiency and the accuracy of instance segmentation. In order to improve both of them, in this paper, we propose a single-shot convolutional neural network structure, which is conceptually simple and straightforward, and meanwhile makes up for the problem of low accuracy of single-shot networks. Our method, termed with SSS-Net, detects targets based on the location of the object's center and the distances between the center and the points on the silhouette sampling with non-uniform angle intervals, thereby achieving a balanced sampling of lines in mask generation. In addition, we propose a non-uniform polar template IoU based on the contour template in polar coordinates. Experiments on both the Airbus Ship Detection Challenge dataset and the ISAID-ships dataset show that SSS-Net has strong competitiveness in precision and speed for ship instance segmentation.