S2CGNet: A Robust Aircraft Detector Based on the Sword-Shaped Component Geometry

Abstract

Aircraft detection is a challenging task for remote sensing images. The anchor-based methods are of high complexity and the keypoint-based detectors suffer the grouping difficulty. And some line-based models relying on local features are hindered by the adhesion and dis-integrity problems. Moreover, those detection representations rarely take into account the sword-shaped component geometric semantics ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., fuselage and the wing) of the aircraft itself, leading to being less robust and unfavorable for downstream tasks, such as ones needing the detailed size and shape of aircraft. Accordingly, we model the sword-shaped component geometry and propose S2CGNet, a more robust appearance-based aircraft detector. The Sword Attenuation Mask (SAM) module is devised to encode a “sword-shaped mask” for each aircraft while exploring more robustness via the geometric surface embedding. The SAM can provide clearer borders to separate different aircraft more precisely. Besides, to address the instance disintegrity problem and further boost the quality of SAM, we propose an Instance Aware Graph (IAG) module to jointly optimize the parameters of the fuselage/wing detection heads. Experimental results show that the performance of S2CGNet can reach the state-of-the-art (SOTA) level. Specifically, it achieves 98.5% in term of AP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sub> on the combined dataset of Aircraft-KP and NWPU VHR-10, boosting 3.8% than the baseline. Besides, S2CGNet boosts the quality of detection results greatly, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., it yields a significant improvement of 21.3% on AP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">75</sub> compared to the baseline. Furthermore, the generalization comparisons on FAIR1M dataset strongly demonstrate the robustness of our model surpasses other oriented detectors by a large margin.