OBBStacking: An Ensemble Method for Remote Sensing Object Detection

TL;DR

This paper introduces OBBStacking, a novel ensemble method tailored for remote sensing object detection that effectively fuses oriented bounding boxes and confidence scores, leading to improved detection performance.

Contribution

The paper presents OBBStacking, the first ensemble approach specifically designed for oriented bounding boxes and confidence score integration in remote sensing object detection.

Findings

Achieved 1st place in the Gaofen Challenge track.

Demonstrated improved performance on DOTA and FAIR1M datasets.

Analyzed features and effectiveness of OBBStacking.

Abstract

Ensemble methods are a reliable way to combine several models to achieve superior performance. However, research on the application of ensemble methods in the remote sensing object detection scenario is mostly overlooked. Two problems arise. First, one unique characteristic of remote sensing object detection is the Oriented Bounding Boxes (OBB) of the objects and the fusion of multiple OBBs requires further research attention. Second, the widely used deep learning object detectors provide a score for each detected object as an indicator of confidence, but how to use these indicators effectively in an ensemble method remains a problem. Trying to address these problems, this paper proposes OBBStacking, an ensemble method that is compatible with OBBs and combines the detection results in a learned fashion. This ensemble method helps take 1st place in the Challenge Track \textit{Fine-grained Object Recognition in High-Resolution Optical Images}, which was featured in \textit{2021 Gaofen Challenge on Automated High-Resolution Earth Observation Image Interpretation}. The experiments on DOTA dataset and FAIR1M dataset demonstrate the improved performance of OBBStacking and the features of OBBStacking are analyzed.