The rapid detection of distracted driving behaviors is crucial for enhancing road safety and preventing traffic accidents. Compared with the traditional methods of distracted-driving-behavior detection, the YOLOv8 model has been proven to possess powerful capabilities, enabling it to perceive global information more swiftly. Currently, the successful application of GhostConv in edge computing and embedded systems further validates the advantages of lightweight design in real-time detection using large models. Effectively integrating lightweight strategies into YOLOv8 models and reducing their impact on model performance has become a focal point in the field of real-time distracted driving detection based on deep learning. Inspired by GhostConv, this paper presents an innovative GhostC2f design, aiming to integrate the idea of linear transformation to generate more feature maps without additional computation into YOLOv8 for real-time distracted-driving-detection tasks. The goal is to reduce model parameters and computational load. Additionally, enhancements have been made to the path aggregation network (PAN) to amplify multi-level feature fusion and contextual information propagation. Furthermore, simple attention mechanisms (SimAMs) are introduced to perform self-normalization on each feature map, emphasizing feature maps with valuable information and suppressing redundant information interference in complex backgrounds. Lastly, the nine distinct distracted driving types in the publicly available SFDDD dataset were expanded to 14 categories, and nighttime scenarios were introduced. The results indicate a 5.1% improvement in model accuracy, with model weight size and computational load reduced by 36.7% and 34.6%, respectively. During 30 real vehicle tests, the distracted-driving-detection accuracy reached 91.9% during daylight and 90.3% at night, affirming the exceptional performance of the proposed model in assisting distracted driving detection when driving and contributing to accident-risk reduction.

Prompt detection of landslides is crucial for reducing the disaster risk and preventing landslides. However, landslide detection in practical applications still faces many challenges, such as the complexity of environmental backgrounds, the diversity of target scales, and the enormity of model weights. To address these issues, this paper proposes a lightweight LBE-YOLO model for real-time landslide detection. Firstly, a lightweight model is designed by integrating the GhostConv lightweight network with the YOLOv8n model. Inspired by GhostConv, this study innovatively designed the GhostC2f structure, which leverages linear thinking to further reduce the model parameters and computational burden. Additionally, the newly designed EGC2f structure, incorporating an attention mechanism, not only maintains the model’s lightweight characteristics but also enhances the network’s capability to extract valid information. Subsequently, the Path Aggregation Network (PAN) was optimized by introducing a bidirectional feature propagation mechanism to improve the model’s feature fusion ability. Additionally, the Bijie landslide dataset was expanded through data augmentation strategies, thereby further improving the model’s generalization capability. The experimental results indicate that, compared to the YOLOv8n model, the proposed model increased accuracy by 4.2%, while the model’s weight and computational load were reduced by 32.0% and 35.5%, respectively. This verifies the superiority of the LBE-YOLO model in landslide target detection, which will help mitigate the impacts of natural disasters.

Drones for road crack detection provide a real-time Cyber-Physical System (CPS) solution, improving road surface assessment for efficient highway maintenance. CPS integrates computational algorithms with physical components, offering advantages over traditional manual inspections, which are slow and prone to false positives, especially in complex environments. To address these challenges, this paper presents the LEE-YOLO model, a novel and lightweight solution that leverages drones within a CPS framework to enable efficient road crack detection. The model incorporates a streamlined network built upon the YOLOv8n model and introduces an innovative lightweight fusion structure, SGC2f, which uses grouped convolutions and linear operations to reduce model weight and complexity markedly. Additionally, the proposed Efficient Bidirectional Feature Pyramid Network (EBiFPN) optimizes output channel utilization within the feature network, enhancing the model’s capacity to detect targets at multiple scales. Furthermore, the Efficient Multi-Scale Attention (EMA) module in the model’s backbone layer is designed to reduce redundant data and improve the extraction of relevant features. Experimental results demonstrate that the LEE-YOLO model outperforms YOLOv8n, achieving a 4.3% higher precision and a 4.0% improvement in mean average precision (mAP). Importantly, it achieves a 43.5% reduction in weight and a 39.5% decrease in computational demand, effectively balancing performance and efficiency. These advancements significantly enhance the potential for drone applications in highway maintenance and detection within the Cyber-Physical Systems domain.

Remote Sensing Image-Text Retrieval (RSITR) is essential for bridging the gap between heterogeneous data modalities. Recently, Vision-Language Models such as CLIP have gained popularity and become a dominant paradigm in this field. However, the high semantic similarity in remote sensing scenes introduces substantial noise into the binary supervision of contrastive learning, making domain adaptation difficult. Existing methods mitigate this by introducing large-scale additional data, but at the expense of significant training cost. To address this, we propose DSD-RSITR, a Dynamic Self-Distillation Framework that improves learning efficiency and reduces reliance on extensive data. It maintains teacher encoders for both modalities to retain prior knowledge and predict semantic relations before alignment. A dynamic EMA strategy and adaptive distillation loss support rapid teacher refinement in early training stages and stronger supervision as training progresses. Experiments show that DSD-RSITR surpasses RemoteCLIP by 1.55% and 0.29% mR on RSICD and RSITMD, respectively, despite using only 4.7% and 2.1% of the training data. Code is available at: https://github.com/zzl0107/DSD-RSITR.