Outlier-Robust Feature Selection and Classification for Low-Altitude UAVs and Ground Vehicles Based on Radar Micro-Doppler Signatures

Ground vehicles pose significant challenges for low-altitude surveillance radar to classify low-flying multirotor unmanned aerial vehicles (UAVs). Radar micro-Doppler signatures could provide a variety of kinematic and structural features to potentially distinguish between them. However, the integration usage of such diverse features always exerts a strong impact on the classification performance, suffering redundancy and sensitivity to outliers. To address this issue, we propose a micro-Doppler feature selection and classification framework to distinguish between low-altitude multirotor UAVs and ground vehicles. A sparse learning model with joint <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\ell _{1}$</tex-math></inline-formula>-norm regularization and outlier compensation is employed to simultaneously select discriminative features and suppress outlier samples. Additionally, a kernel density-based thresholding strategy is introduced to optimize classification under class imbalance by modeling the prediction score distribution. Finally, experimental results on real radar dataset demonstrate the proposed framework outperforms conventional feature selection ones with stronger outlier robustness, better class imbalance adaptability, and higher classification accuracy.