ABSTRACT Small object detection, a critical technique for recognizing and localizing diminutive targets in visual data, plays a vital role in applications ranging from remote sensing and unmanned aerial vehicle (UAV) vision to autonomous driving. Current methodologies, however, face substantial challenges, including detection accuracy limitations, low‐resolution image processing difficulties, background noise interference, and target occlusion issues. To address these challenges, we propose FMF‐DETR, an innovative small object detection framework featuring frequency‐domain feature optimization through three key components: (1) High‐Low Frequency Fusion Model (HLFM), (2) Focused Diffusion Feature Pyramid Network (FDFPN), and (3) BiPathNet (BPNet). Specifically, the HLFM module enhances multiscale feature representation by emphasizing high‐frequency details while suppressing low‐frequency background noise. The FDFPN architecture improves detection performance in complex scenarios through multiscale feature fusion and saliency‐aware diffusion. BPNet introduces a dual‐path feature extraction mechanism that simultaneously enhances feature discriminability and reduces computational overhead. Through the synergistic integration of these components, the proposed framework enhances both detection accuracy and operational efficiency. Comprehensive evaluations on the VisDrone dataset demonstrate FMF‐DETR's superior performance, achieving a 2.2% accuracy improvement while reducing model parameters by 13.03M and computational complexity by 97.2G FLOPs compared to baseline methods. These results validate both the effectiveness and efficiency of our proposed framework.

In order to evaluate the performance of bidirectional isolation AC-DC matrix converter under different modulation parameters, an accurate model of power device loss is built in this paper. Since the current/voltage of the power device is high-frequency, time-varying and irregular, which is different in each sampling period and hardly able to be estimated directly, the superposition principle is introduced to calculate the current/voltage in the model. Simulation and experimental results show that under different conditions, the simulated and calculated values are essentially consistent and the error percentage between the calculated values by using the model and the real values is within 0.87% in rectification mode and inversion mode, which means that the built model is accurate. Furthermore, by using this model allows for calculation and analysis of the device loss in the converter.

In the conventional model predictive control (MPC) for indirect matrix converter - induction motor (IMC-IM) drive system, the weighting factor is fixed, which cannot ensure good input/output performances of the IMC in a wide operation range. In order to solve this problem, a weighting factor tuning method is proposed based on analytic hierarchy process (AHP). The basic weighting factor is designed firstly by introducing the AHP algorithm, and then the optimal weighting factor is achieved by combining the operating condition parameters. Simulation and experimental results show that sinusoidal grid currents of the indirect matrix converter with unity power factor have been realized. In addition, good steady-state and dynamic performances of the induction motor drive system within a very wide operation range in terms of speed and torque have been achieved.

The aim of pansharpening is to fuse panchromatic (PAN) images and the corresponding low-resolution multispectral (LRMS) images to generate high-resolution multispectral (HRMS) images. In recent years, convolutional neural network (CNN)-based methods have obtained excellent performance in this field. In order to break through the limitations of standard convolution, the dynamic convolution is also proposed for pansharpening. However, the existing dynamic convolution ignores the context along channel dimension and does not consider the mutual enhancement between spatial and spectral information. In this letter, we propose a novel cross-interaction kernel attention network (CIKANet). The proposed model consists of two branches to extract spectral and spatial information. In particular, spatial and spectral kernel attention modules that can dynamically scale the parameters of convolutional kernels are applied. To strengthen the interactions between branches and obtain complementary information, we adopt a cross kernel attention structure. A series of experiments conducted on the WV3 and QB datasets suggest that CIKANet outperforms other state-of-the-art (SOTA) models visually and quantitatively.

Pan-sharpening, a task involving information fusion, entails merging panchromatic (PAN) images with high spatial resolution and low-resolution multispectral (LRMS) images in order to obtain high-resolution multispectral (HRMS) images. Due to deep learning’s excellent regression capabilities, it has recently become the dominating technique for this assignment. Meanwhile, the development of the transformer, a novel deep learning architecture for natural language processing, has provided researchers with new insights. In this letter, we seek to extend transformer’s excellent mechanisms to pixel-level fusion challenges. We designed a parallel convolutional neural network structure for learning both the regions of interest from the LRMS images and the residuals required for regression to HRMS images. Then, in our proposed pixelwise attention constraint (PAC) module, the residuals will be changed utilizing the learned region of interest. In addition, we presented a novel multireceptive-field attention block (MRFAB) to frame our network. Experiments on two datasets also show that our work is better than the mainstream algorithms at both indicators and visualization.

In order to reduce the high cost of sampling circuits, simplify commutation procedure and improve the conversion efficiency of the indirect matrix converter (IMC), a zero current commutation model predictive control (ZCC-MPC) strategy with the input voltage observation is proposed in this paper. The input voltage observer is designed by using the model of the input LC filter, hence, three sampling and conditioning circuits for input phase voltages have been cancelled. The switching state combination with fixed duty cycle for the inverter stage is adopted in each sampling period, which ensures the zero dc-bus current during the whole commutation procedure in the rectifier stage. A simple two-step zero current commutation (ZCC) method has been adopted instead of complex four-step commutation. Simulation and experimental results show that sinusoidal input/output currents, good steady state/dynamic performance and unity input power factor have been achieved based on the proposed strategy. As well, the hardware cost has been lowered and the commutation reliability has been enhanced.