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.

The accurate and rapid prediction of parking availability is helpful for improving parking efficiency and to optimize traffic systems. However, previous studies have suffered from limited training sample sizes and a lack of thorough investigation into the correlations among the factors affecting parking availability. The purpose of this study is to explore a prediction method that can account for multiple factors. Firstly, a dynamic prediction method based on a temporal convolutional network (TCN) model was confirmed to be efficient for ultra-short-term parking availability with an accuracy of 0.96 MSE. Then, an attention-enhanced TCN (A-TCN) model based on spatial attention modules was proposed. This model integrates multiple factors, including related dates, extreme weather, and human control, to predict the daily congestion index of parking lots in the short term, with a prediction period of up to one month. Experimental results on real data demonstrate that the MSE of A-TCN is 0.0061, exhibiting better training efficiency and prediction accuracy than a traditional TCN for the short-term prediction time scale.

The semantic segmentation of remote sensing images is vital for accurate surface monitoring and environmental assessment. Multimodal remote sensing images (RSIs) provide a more comprehensive dimension of information, enabling faster and more scientific decision-making. However, existing methods primarily focus on modality and spectral channels when utilizing spectral features, with limited consideration of their association to ground object types. This association, commonly referred to as the spectral characteristics of ground objects (SCGO), results in distinct spectral responses across different modalities and holds significant potential for improving the segmentation accuracy of multimodal RSIs. Meanwhile, the inclusion of redundant features in the fusion process can also interfere with model performance. To address these problems, a ground object spectral feature awareness network (SFANet) specifically designed for RSIs that effectively leverages spectral features by incorporating the SCGO is proposed. SFANet includes two innovative modules: (1) the Spectral Aware Feature Fusion module, which integrates multimodal features in the encoder based on SCGO, and (2) the Adaptive Spectral Enhancement module, which reduces the confusion from redundant information in the decoder. SFANet significantly improves the mIoU by 5.66% and 4.76% compared to the baseline on two datasets, outperforming existing multimodal RSIs segmentation networks by adaptively enhanced spectral feature awareness. SFANet demonstrates significant advancements over other multimodal RSIs segmentation networks and provides new perspectives for RSI-specific network design by incorporating spectral characteristics. This work offers new perspectives for the design of segmentation networks for RSIs.