Guiqing He

Drones are increasingly being used in maritime engineering for ship maintenance, emergency rescue, and safety monitoring tasks. In these tasks, action recognition is important for human–drone interaction and for detecting abnormal situations such as falls or distress signals. However, the maritime environment is highly challenging, with illumination variations, water spray, and dynamic backgrounds often leading to ambiguity between similar actions. To address this issue, we propose MSG-GCN, a multi-semantic guided graph convolutional network for human action recognition. Specifically, MSG-GCN integrates structured prior semantic information and further introduces a textual–semantic alignment mechanism to improve the consistency and expressiveness of multimodal features. Benefiting from its lightweight hierarchical design, our model offers excellent deployment flexibility, making it well suited for resource-constrained UAV applications. Experimental results on large-scale benchmark datasets, including NTU60, NTU120 and UAV-human, demonstrate that MSG-GCN surpasses state-of-the-art methods in both classification accuracy and computational efficiency.

In recent years, remote sensing object detection has witnessed significant advancements through deep explorations of convolutional neural networks (CNNs) and vision transformer (ViT) architectures. However, detecting rotated objects with high aspect ratios remains challenging. Current detection frameworks inadequately address the anisotropic feature distribution caused by such objects: feature information is highly concentrated in one spatial dimension while being sparse in another; and there are significant feature differences in the parameters representing the bounding box. To address this issue, we propose a Spatial Focusing and Progressive Decoupling Detector (SFPD-Det), which consists of three components: the Spatially Crosswise Convolution Module (SCCM), Hierarchical Decoupling Network (HDN), and Dynamic Progressive Activation Masks (DPMs). The SCCM captures diverse spatial features with long-range dependencies by combining square convolutions with multi-branch orthogonal large strip convolutions, enhancing the model adaptability to objects with varying aspect ratios. The HDN is composed of stacked ViT blocks and uses separate network branches to predict the position, angle, and size of bounding boxes in a cascaded manner. Furthermore, by combining the predicted parameters, we propose DPMs that embed the mask information of potential object boundary regions into the HDN, which progressively guide the self-attention to enhance cirtical features within the region of interest, thereby achieving precise bounding box regression. Extensive experiments on four benchmark remote sensing datasets (DOTA, DIOR-R, HRSC2016, and UCAS-AOD) demonstrate that our SFPD-Det achieves superior performance when compared with state-of-the-art detectors.

In recent years, detection methods for generic object detection have achieved significant progress. However, due to the large number of small objects in aerial images, mainstream detectors struggle to achieve a satisfactory detection performance. The challenges of small object detection in aerial images are primarily twofold: (1) Insufficient feature representation: The limited visual information for small objects makes it difficult for models to learn discriminative feature representations. (2) Background confusion: Abundant background information introduces more noise and interference, causing the features of small objects to easily be confused with the background. To address these issues, we propose a Multi-Level Contextual and Semantic Information Aggregation Network (MCSA-Net). MCSA-Net includes three key components: a Spatial-Aware Feature Selection Module (SAFM), a Multi-Level Joint Feature Pyramid Network (MJFPN), and an Attention-Enhanced Head (AEHead). The SAFM employs a sequence of dilated convolutions to extract multi-scale local context features and combines a spatial selection mechanism to adaptively merge these features, thereby obtaining the critical local context required for the objects, which enriches the feature representation of small objects. The MJFPN introduces multi-level connections and weighted fusion to fully leverage the spatial detail features of small objects in feature fusion and enhances the fused features further through a feature aggregation network. Finally, the AEHead is constructed by incorporating a sparse attention mechanism into the detection head. The sparse attention mechanism efficiently models long-range dependencies by computing the attention between the most relevant regions in the image while suppressing background interference, thereby enhancing the model’s ability to perceive targets and effectively improving the detection performance. Extensive experiments on four datasets, VisDrone, UAVDT, MS COCO, and DOTA, demonstrate that the proposed MCSA-Net achieves an excellent detection performance, particularly in small object detection, surpassing several state-of-the-art methods.

The widespread application of convolutional neural networks (CNNs) has led to significant advancements in object detection. However, challenges remain in achieving efficient and precise extraction of critical features when applying typical CNN-based methods to remote sensing detection tasks: (1) The convolutional kernels sliding horizontally in the backbone are misaligned with the features of arbitrarily oriented objects. Additionally, the detector shares the features extracted from the backbone, but the classification task requires orientation-invariant features while the regression task requires orientation-sensitive features. The inconsistency in feature requirements makes it difficult for the detector to extract the critical features required for each task. (2) The use of deeper convolutional structures can improve the detection accuracy, but it also results in substantial convolutional computations and feature redundancy, leading to inefficient feature extraction. To address this issue, we propose a Task-Sensitive Efficient Feature Extraction Network (TFE-Net). Specifically, we propose a special mixed fast convolution module for constructing an efficient network architecture that employs cheap transform operations to replace some of the convolution operations, generating more features with fewer parameters and computation resources. Next, we introduce the task-sensitive detection module, which first aligns the convolutional features with the targets using adaptive dynamic convolution based on the orientation of the targets. The task-sensitive feature decoupling mechanism is further designed to extract orientation-sensitive features and orientation-invariant features from the aligned features and feed them into the regression and classification branches, respectively, which provide the critical features needed for different tasks, thus improving the detection performance comprehensively. In addition, in order to make the training process more stable, we propose a balanced loss function to balance the gradients generated by different samples. Extensive experiments demonstrate that our proposed TFE-Net can achieve superior performance and obtain an effective balance between detection speed and accuracy on DOTA, UCAS-AOD, and HRSC2016.

Millimeter-wave integrated access and backhaul network (mmWave IABN) is a cost-effective paradigm to accommodate the ever-increasing demands of IoT devices, but its sensitivity to the obstructions is an obstacle in the practical commercial applications. Reconfigurable intelligent surface (RIS) is an innovation enabler to proactively manipulate the ambient environment in a programmable manner for the overall performance enhancement. In this paper, the resource allocation of the RIS-assisted mmWave IABN is conceived and designed to maximize the end-to-end throughput. Firstly, the end-to-end throughput maximization oriented resource allocation problem including transmission power controlling, phase-shift manipulation, and bandwidth allocation is formulated as a non-linear and non-convex programming problem, which is intractable to search an optimal solution in polynomial time. Secondly, the formulated original problem is equivalently decomposed into two subproblems to obtain a sub-optimal solution, i.e., the joint optimization subproblem of transmission power controlling at the users and phase-shift manipulation at the RIS, and the bandwidth allocation subproblem between the access part and the backhaul part. Thirdly, a decomposition iteration based resource allocation mechanism (DIRAM) is proposed, and the DIRAM is composed of two phases, which is the alternative iteration based optimization scheme of power controlling and phase-shift manipulation (AIOS-PCPM) to obtain the optimal solution of the first subproblem, and the piecewise statistical based bandwidth allocation (PSBA) scheme to obtain the optimal solution of the second subproblem. Finally, the properties of the proposed DIRAM are evaluated through abundant of simulation comparisons with other baselines, where the superiorities of the proposed DIRAM are verified in terms of spectral efficiency and end-to-end throughput.

A nonlinear optimization neural network for the implementation of optimum multiuser detector (MUD) is proposed. By theoretical analyses and computer simulations, it is shown that the proposed neural network detector has the dynamic performance of real time application and the ability of anti-interference of multiple access, and has the less error bit rate than the traditional methods.

Considering China Beidou has unique two-way communication capability for short messages that are not available in other navigation systems such as GPS, a 600bps vocoder adapted to the short message channel of Beidou is developed. The sinusoidal excitation linear prediction algorithm is adopted by the vocoder to achieve voice communication with clear communication quality. Furthermore, a coordinate compression algorithm for processing positioning information is designed to provide more transmission space for speech encoded data. Based on the above-mentioned results, a communication system that only the Beidou navigation system is used to complete two-way secure voice and positioning simultaneous interpretation is realized. The system firstly uses a voice conversion program to convert the voice coded data obtained by the vocoder codec module into the Beidou short message data format; and then the voice code analysis program and the latitude and longitude analysis program is used to parse the voice code and location information; Finally, the experimental results of voice communication and positioning transmission are verified on the Beidou short message transceiver, and the subjective MOS test score indicates that the way is paved for the practical use of Beidou short message voice communication. 针对中国北斗比GPS等其他导航系统独有的短报文双向通信功能，研发了适配北斗短报文信道的600 bit/s声码器。声码器采用正弦激励线性预测（sinusoidal excitation linear prediction，SELP）算法，实现了通信质量清晰的语音通信，并进一步设计了一种处理定位信息的坐标压缩算法，为语音编码数据提供了更大的传输空间。基于以上研究，实现了仅用北斗导航系统完成双向保密语音和定位同传的通信系统。该系统首先利用语音转换程序将声码器编解码模块获取的语音编码数据转换为北斗短报文数据格式；然后利用语音编码解析程序与经纬度解析程序从北斗短报文数据中解析出语音编码与位置信息；最后，在北斗短报文收发器上验证了语音通信与定位传输实验效果，主观MOS测试评分表明该研究为北斗短报文语音通信实用化铺平了道路。