Due to the issues of remote sensing object detection algorithms based on deep learning, such as a high number of network parameters, large model size, and high computational requirements, it is challenging to deploy them on small mobile devices. This paper proposes an extremely lightweight remote sensing aircraft object detection network based on the improved YOLOv5n. This network combines Shufflenet v2 and YOLOv5n, significantly reducing the network size while ensuring high detection accuracy. It substitutes the original CIoU and convolution with EIoU and deformable convolution, optimizing for the small-scale characteristics of aircraft objects and further accelerating convergence and improving regression accuracy. Additionally, a coordinate attention (CA) mechanism is introduced at the end of the backbone to focus on orientation perception and positional information. We conducted a series of experiments, comparing our method with networks like GhostNet, PP-LCNet, MobileNetV3, and MobileNetV3s, and performed detailed ablation studies. The experimental results on the Mar20 public dataset indicate that, compared to the original YOLOv5n network, our lightweight network has only about one-fifth of its parameter count, with only a slight decrease of 2.7% in mAP@0.5. At the same time, compared with other lightweight networks of the same magnitude, our network achieves an effective balance between detection accuracy and resource consumption such as memory and computing power, providing a novel solution for the implementation and hardware deployment of lightweight remote sensing object detection networks.

Small-target detection in remote sensing presents three fundamental challenges: limited pixel representation of targets, multi-angle imaging-induced appearance variance, and complex background interference. This paper introduces a dual-component neural architecture comprising Hierarchical Dynamic Refinement Attention (HiDRA) and Densely Connected Dilated Block (DCDBlock) to address these challenges systematically. The HiDRA mechanism implements a dual-phase feature enhancement process: channel competition through bottleneck compression for discriminative feature selection, followed by spatial-semantic reweighting for foreground–background decoupling. The DCDBlock architecture synergizes multi-scale dilated convolutions with cross-layer dense connections, establishing persistent feature propagation pathways that preserve critical spatial details across network depths. Extensive experiments on AI-TOD, VisDrone, MAR20, and DOTA-v1.0 datasets demonstrate our method’s consistent superiority, achieving average absolute gains of +1.16% (mAP₅₀), +0.93% (mAP₉₅), and +1.83% (F1-score) over prior state-of-the-art approaches across all benchmarks. With 8.1 GFLOPs computational complexity and 2.6 ms inference speed per image, our framework demonstrates practical efficacy for real-time remote sensing applications, achieving superior accuracy–efficiency trade-off compared to existing approaches.

To address limitations in the modulation-quality analysis of high-order Quadrature Amplitude Modulation (QAM) signals, including insufficient timing synchronization accuracy, challenges in carrier recovery, and coupling between synchronization errors and parameter estimation, a cascaded digital baseband processing framework tailored for measurement scenarios is proposed. The proposed framework is designed to integrate synchronization recovery and parameter measurement. In the timing synchronization stage, a feedforward open-loop structure based on the Oerder–Meyr (OM) algorithm is employed to estimate the optimal sampling instants rapidly. In the carrier synchronization stage, a two-stage recovery structure is constructed, comprising coarse frequency offset estimation based on polarity decision and fine synchronization using an improved frequency–phase detector (FPD), thereby achieving both robust acquisition of large frequency offsets and high-precision compensation of residual errors. On this basis, a unified modulation quality evaluation model is established, enabling the joint estimation of the Error Vector Magnitude (EVM) and the Modulation Error Ratio (MER), as well as amplitude, phase, and frequency errors, within a consistent analytical framework. System-level validation of 256 QAM and 1024 QAM signals is conducted using a MATLAB R2021b-based simulation platform. The results demonstrate that stable synchronization recovery can be achieved under timing, frequency, and phase perturbations, yielding well-defined constellation diagrams. In terms of parameter estimation, the relative errors of all evaluated metrics are maintained within 2%, which is significantly below the conventional 5% measurement criterion. Further analysis indicates that the proposed method maintains strong robustness across varying signal-to-noise ratios (SNRs) and sampling rates. The results confirm that the proposed cascaded processing framework effectively unifies synchronization recovery and modulation quality analysis, significantly improving parameter estimation accuracy while maintaining high synchronization precision. This approach provides a practical and efficient solution for high-order QAM signal testing and measurement systems.