Learning Non-local Quadrature Contrast for Detection and Recognition of Infrared Rotary-wing UAV Targets in Complex Background

Traditional data-driven algorithms suffer from data reliance, hyper-parameter sensitivity, and faint characteristics in infrared (IR) "low, slow, and small" unmanned aerial vehicle target detection and recognition, resulting in performance degradation in complex backgrounds. Inspired by model-driven methods, this paper proposes a learnable feature modulation module that uses prior knowledge to enhance feature representation. Specifically, this method converts the local contrast measure into a non-local quadrature difference measure in deep feature space, considering feature points that break semantic continuity as the potential target locations through a self-attentive approach. On this basis, considering the scale changes of aircraft targets during radial approach to IR detectors, a multi-scale single-stage detector is designed by effective receptive field calculation. In this network structure, a bidirectional serial feature modulation method is used to fully retain the multi-scale features of the target and ensure adaptability to point, spot, and area targets while satisfying real-time requirements. The ablation studies verify the effectiveness of each component and help determine the optimal parameter configuration. Finally, comparison experiments with state-of-the-art methods are conducted on a 10k scale IR dataset. The experimental results show that the detection accuracy of this method is better than other baseline methods while ensuring real-time performance, especially in highly complex and low-contrast scenes, achieving superior higher target detection accuracy.