Drone object detection serves as a fundamental task for more advanced applications. However, drone images typically exhibit challenges such as small object sizes, dense distributions, and high levels of overlap. Traditional object detection networks struggle to achieve the required accuracy and efficiency under these conditions. In this paper, we propose DAU-YOLO, a novel object detection method tailored for drone imagery, built upon the YOLOv11 framework. To enhance feature extraction, a Receptive-Field Attention (RFA) module is introduced in the backbone, allowing adaptive convolution kernel adjustments across different local regions, thereby addressing the challenge of dense object distributions. In the neck, we propose a Dynamic Attention and Upsampling (DAU) module, which incorporates additional low-level features rich in small-object information. Furthermore, Scale-Diffusion Attention and Task-Aware Attention are employed to refine these features, significantly improving the network’s ability to detect small objects. To maintain an extremely lightweight architecture, the bottom-most Bottom–Up layer is removed, reducing model complexity without compromising detection accuracy. In the experiments, the proposed method achieves state-of-the-art (SOTA) performance on the VisDrone2019 dataset. On the validation set, DAU-YOLO(l) attains an $mA{P}_{50}$ of 56.1%, surpassing the baseline YOLOv11(l) by 9.1% and the latest similar-structure method Drone-YOLO(l) by 4.8%, while maintaining only 28.9M parameters, almost half those of Drone-YOLO(l). In the discussion, we provide a detailed analysis of the improvements in small object detection as well as the trade-off between detection accuracy and inference speed. These results demonstrate the effectiveness of DAU-YOLO in addressing the challenges of drone object detection, offering a highly accurate and lightweight solution for real-time applications in complex aerial scenes.

Road safety is important for the rapid development of the economy and society. Thus, it is of great significance to monitor the dynamic changing processes of road diseases, such as cavities, to provide a basis for the daily maintenance of roads and prevent any possible car accidents. The ground penetrating radar (GPR) technology is widely used in road disease detection due to its advantages of nondestructiveness, rapidness, and high resolution. Traditionally, one-time 2D GPR detection cannot obtain the 3D spatial changes of subgrades. Thus, we developed a road subgrade monitoring method based on the time-lapse full-coverage (TLFC) 3D GPR technique by focusing on solving the key problems of time and spatial position mismatches in experimental data. Moreover, we used the time zero consistency correction, 3D data combination, and spatial position matching methods, as they greatly improve the 3D imaging quality of underground spaces. Finally, the time-lapse attribute analysis method was used in the TLFC 3D GPR data to obtain detailed characteristics and an overall rule of the dynamic subgrade change. Overall, this research proves that TLFC 3D GPR is an optimal choice for road subgrade monitoring.

Traditional nonintelligent signal control systems are typically used in road traffic signal systems, which cannot provide optimal guidance and have low traffic efficiency during rush hour. This study proposes a traffic signal phase dynamic timing optimization strategy based on a time convolution network and attention mechanism to improve traffic efficiency at intersections. The corresponding optimization was performed after predicting traffic conditions with different impacts using the digital twinning technique. This method uses a time-convolution network to extract the cross-time nonlinear characteristics of traffic data at road intersections. An attention mechanism was introduced to capture the relationship between the importance distribution and duration of the historical time series to predict the traffic flow at an intersection. The interpretability and prediction accuracy of the model was effectively improved. The model was tested using traffic flow data from a signalized intersection in Shangrao, Jiangxi Province, China. The experimental results indicate that the model generated by training has a strong learning ability for the temporal characteristics of traffic flow. The model has high prediction accuracy, good optimization results, and wide application prospects in different scenarios.

Oil spills lead to catastrophic problems. In most oil spill cases, the spatial and temporal intractability of the detriment cannot be neglected, and problems related to economic, social and environmental factors constantly appear for a long time. Remote sensing has been widely used as a powerful means to conduct oil spill detection. Optical polarization remote sensing, thriving in recent years, shows a novel potential for oil spill detection. This paper provides a demonstration of the use of open-source POLDER/PARASOL polarization time-series data to detect oil spill. The Deepwater Horizon oil spill, one of the largest oil spill disasters, is utilized to explore the potential of optical polarization remote sensing for oil spill detection. A total of 24 feature combinations are organized to quantitatively study the positive effect of adding polarization information and the appropriate way to describe polarization characteristics. Random forest classifier models are trained with different combinations, and the results are assessed by 10-fold cross-validation. The improvement from adding polarization characteristics is remarkable ((average) accuracy: +0.51%; recall: +2.83%; precision: +3.49%; F₁ score: +3.01%, (maximum) accuracy: +0.80%; recall: +5.09%; precision: +6.92%; F₁ score: +4.72%), and coupling between the degree of polarization and the phase angle of polarization provides the best description of polarization information. This study confirms the potential of optical polarization remote sensing for oil spill detection, and some detailed problems related to model establishment and polarization feature characterization are discussed for the further application of polarization information.

The prediction of parking space availability plays a crucial role in information systems providing parking guidance. However, controversy persists regarding the efficiency and accuracy of mainstream time series prediction methods, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). In this study, a comparison was made between a temporal convolutional network (TCN) based on CNNs and a long short-term memory (LSTM) network based on RNNs to determine an appropriate baseline for predicting parking space availability. Subsequently, a multi-head attention (MAT) mechanism was incorporated into an LSTM network, attempting to improve its accuracy. Experiments were conducted on three real and two synthetic datasets. The results indicated that the TCN achieved the fastest convergence, whereas the MAT-LSTM method provided the highest average accuracy, namely 0.0330 and 1.102 × 10⁻⁶, on the real and synthetic datasets, respectively. Furthermore, the improved MAT-LSTM model accomplished an increase of up to 48% in accuracy compared with the classic LSTM model. Consequently, we concluded that RNN-based networks are better suited for predicting long-time series. In particular, the MAT-LSTM method proposed in this study holds higher application value for predicting parking space availability with a higher accuracy.

As the amount of ground-penetrating radar (GPR) data increases significantly with the high demands of nondestructive detection methods under urban roads, a method suitable for time-lapse data dynamic monitoring should be developed to quickly identify targets on GPR profiles and compare time-lapse datasets. This study conducted a field experiment aiming to monitor one backfill pit using three-dimensional GPR (3D GPR), and the time-lapse data collected over four months were used to train U-Net, a fast neural network based on convolutional neural networks (CNNs). Consequently, a trained network model that could effectively segment the backfill pit from inline profiles was obtained, whose Intersection over Union (IoU) was 0.83 on the test dataset. Moreover, segmentation masks were compared, demonstrating that a change in the southwest side of the backfill pit may exist. The results demonstrate the potential of machine learning algorithms in time-lapse 3D GPR data segmentation and dynamic monitoring.