The topic of object detection (OD) in remote sensing (RS) has received a lot of attention due to the rapid growth of deep learning. However, RS images typically have the following characteristics: significant variations in object scales, tight arrangement of small objects, and indistinguishable feature boundaries between objects and backgrounds. These challenges lead to defects, such as insufficient feature extraction and information loss of the existing methods. To address the above issues, based on the YOLOv7 architecture, we present a novel OD method named GDRS-you only look once (YOLO). Our primary contributions include: first, an enhanced feature extraction network based on deformable convolution is proposed to improve the network’s ability to model geometric transformations. Second, we abandoned the traditional feature pyramid architecture and construct a multiscale feature aggregation network based on the gather-and-distribute mechanism, which makes effective use of the feature obtained from the backbone and reduces the loss of information in the transmission process. Finally, the normalized Wasserstein distance (NWD) is introduced for hybrid loss training, which alleviates the sensitivity of the IoU-based metric to the location deviation of tiny objects. We demonstrate the effectiveness of GDRS-YOLO on the publicly available datasets NWPU VHR-10 and VisDrone datasets. Compared to the original YOLOv7, the proposed method improves the mean average precision (mAP) by 1.9% and 5.5%, respectively. These results emphasize the superior performance of the proposed model, which provides an efficient multiscale feature fusion solution for RS applications.
In the process of imbalanced dataset classification, traditional oversampling technologies do not take into the account of the distribution characteristics of data sets, which easily results in low classification accuracy of positive samples. In order to improve the recognition rate of positive samples, the algorithm combining the K-means clustering with the MAHAKIL oversampling is proposed in this paper. Firstly, the K-means clustering algorithm is used to divide the positive samples into K clusters. The samples in each cluster are then divided into two initial populations according to the magnitude of the Mahalanobis distance. Finally, the crossover operator of the genetic algorithm is used to continuously synthesize new data samples to balance the data set. The experimental results show that when K-means MAHAKIL oversampling algorithm is combined with different classification algorithms, it can achieve better classification performance, which verifies the effectiveness of the algorithm.
With the rapid development of deep learning, object detection in remote sensing images has attracted extensive attention. However, remote sensing images typically exhibit the following characteristics: significant variations in object scales, dense small targets, and complex backgrounds. To address these challenges, a novel object detection method named MCRS-YOLO is innovatively proposed. Firstly, a Multi-Branch Aggregation (MBA) network is designed to enhance information flow and mitigate challenges caused by insufficient object feature representation. Secondly, we construct a Multi-scale Feature Refinement and Fusion Pyramid Network (MFRFPN) to effectively integrate spatially multi-scale features, thereby augmenting the semantic information of feature maps. Thirdly, a Large Depth-wise Separable Kernel (LDSK) module is proposed to comprehensively capture contextual information while achieving an enlarged effective receptive field. Finally, the Normalized Wasserstein Distance (NWD) is introduced into hybrid loss training to emphasize small object features and suppress background interference. The efficacy and superiority of MCRS-YOLO are rigorously validated through extensive experiments on two publicly available datasets: NWPU VHR-10 and VEDAI. Compared with the baseline YOLOv11, the proposed method demonstrates improvements of 4.0% and 6.7% in mean Average Precision (mAP), which provides an efficient and accurate solution for object detection in remote sensing images.
For the purpose of achieving high-precision position control in electro-hydraulic servo system(EHSS), a nonlinear disturbance observer-based adaptive feedforward fractional-order sliding mode control algorithm (NDOB-AFFOSMC) is proposed. First, the basic principles of hydraulic actuators and the mathematical description of the EHSS are studied, and the system's state equation is derived from the theoretical model. Given that sliding mode control (SMC) is invariant to external disturbances and parameter variations, this algorithm is employed to tackle uncertainties in the position control of EHSS. To reduce the inherent chattering of sliding mode control, a fractional calculus algorithm is integrated, and an adaptive reaching law is designed to further mitigate chattering. A feedforward link is added to lighten the load on the feedback controller, with an adaptive rate for the feedforward link to enhance tracking capability for signals of different frequencies. Additionally, a nonlinear disturbance observer(NDOB) is introduced to compensate for interference from external load disturbances, further improving tracking performance. Lyapunov stability theory is employed to validate the stability of the proposed control strategy. Ultimately, MATLAB/Simulink-based simulations validate both the effectiveness and dynamic performance of the NDOB-AFFOSMC approach. The findings indicate that in comparison to conventional Proportional-Integral-Derivative (PID) control and SMC incorporating a saturation function, this proposed scheme provides superior control precision and enhanced robustness for electro-hydraulic servo position control systems.
Imaging technologies are widely used in surveillance, medical diagnostics, and other critical applications. However, under low-light conditions, captured images often suffer from insufficient brightness, blurred details, and excessive noise, degrading quality and hindering downstream tasks. Conventional low-light image enhancement (LLIE) methods not only require annotated data but also often involve heavy models with high computational costs, making them unsuitable for real-time processing. To tackle these challenges, a lightweight and unsupervised LLIE method utilizing a dual-stage frequency-domain calibration network (DFCNet) is proposed. In the first stage, the input image undergoes the preliminary feature modulation (PFM) module to guide the illumination estimation (IE) module in generating a more accurate illumination map. The final enhanced image is obtained by dividing the input by the estimated illumination map. The second stage is used only during training. It applies a frequency-domain residual calibration (FRC) module to the first-stage output, generating a calibration term that is added to the original input to darken dark regions and brighten bright areas. This updated input is then fed back to the PFM and IE modules for parameter optimization. Extensive experiments on benchmark datasets demonstrate that DFCNet achieves superior performance across multiple image quality metrics while delivering visually clearer and more natural results.