A Multi-Channel Aggregation Framework for Object Detection in Large-Scale SAR Image

Synthetic aperture radar (SAR) has gradually demonstrated its advantages in a variety of application fields. However, due to the complexity of the background, the simplicity of the texture, and the multi-scale of the target, object detection in large-scale SAR images is still a major challenge. This paper focuses on a multi-channel aggregation framework, and jointly considers the preprocessing and postprocessing for algorithm optimization to improve the overall performance of object detection in large-scale SAR images. In this paper, multiple sets of slices of large-scale images are first sliced using slicers of various sizes. Feeding different groups of image slices into the detection network for feature extraction can achieve a greater degree of scaling of target features, thereby improving the ability of multi-scale target discovery. Then, a postprocessing module is proposed to transform and fuse the results from multiple channels, and two sub-algorithms result fusion and result refinement are proposed to eliminate false alarms. Result fusion merges the detection boxes from each channel and proposes a weighted NMS strategy to update the confidence of the optimal box. Result refinement proposes an adaptive belief update strategy to filter the remaining boxes for eliminating those detection boxes with low beliefs. Qualitative and quantitative experiments were conducted to prove the effectiveness of the proposed method, which can reduce the false alarm rate while increasing the recall rate.