Sparse R-CNN OBB: Ship Target Detection in SAR Images Based on Oriented Sparse Proposals

TL;DR

Sparse R-CNN OBB introduces a novel, efficient framework using sparse learnable proposals for oriented ship detection in SAR images, outperforming existing models in various scenarios.

Contribution

It is the first to apply sparse learnable proposals for oriented object detection in SAR images, simplifying architecture and training.

Findings

Achieves superior detection performance on RSDD-SAR dataset.

Uses only 300 proposals instead of extensive anchors.

Outperforms state-of-the-art models in inshore and offshore scenarios.

Abstract

We present Sparse R-CNN OBB, a novel framework for the detection of oriented objects in SAR images leveraging sparse learnable proposals. The Sparse R-CNN OBB has streamlined architecture and ease of training as it utilizes a sparse set of 300 proposals instead of training a proposals generator on hundreds of thousands of anchors. To the best of our knowledge, Sparse R-CNN OBB is the first to adopt the concept of sparse learnable proposals for the detection of oriented objects, as well as for the detection of ships in Synthetic Aperture Radar (SAR) images. The detection head of the baseline model, Sparse R-CNN, is re-designed to enable the model to capture object orientation. We train the model on RSDD-SAR dataset and provide a performance comparison to state-of-the-art models. Experimental results show that Sparse R-CNN OBB achieves outstanding performance, surpassing most models on both inshore and offshore scenarios. The code is available at: www.github.com/ka-mirul/Sparse-R-CNN-OBB.