With the development of intelligent transportation systems, the demand for automatic recognition and monitoring of critical road safety infrastructure has been increasing. Particularly in high-risk road sections such as mountainous areas and steep downhill stretches, Emergency Escape Ramps (EERs) play a crucial role in preventing severe accidents caused by out-of-control vehicles. Accurate detection of these ramps is essential for enhancing road traffic safety. To address the limitations of existing methods, such as inadequate segmentation accuracy and poor robustness in object detection, this paper proposes a new model (HR-YOLO) that integrates the HR-Net model with an improved YOLOv12 model. To support the segmentation and detection of emergency escape ramp scenarios, we constructed a custom dataset consisting of 411 annotated images across 8 categories. This dataset reflects typical road environments and object types encountered in emergency ramp areas, providing a reliable foundation for model training and evaluation. The HR-Net achieves a mIoU and mPA of 85.50% and 91.23%, respectively. The YOLOv12 network attains a mAP and F1 score of 78.7% and 75.9%, respectively, for unsegmented images. The YOLOv12 model enhanced with Coordinate Attention (CAYOLOv12) is combined with the HR-Net model. Compared to the standalone YOLOv12 model, the HR-YOLO model improves mAP and F1 scores by 10% and 9.6%, respectively. The proposed approach provides an efficient and reliable technological solution for the intelligent recognition of key infrastructure in traffic safety monitoring systems.
To address the challenges in new power systems, such as wind and photovoltaic curtailment and insufficient energy storage incentives, caused by imbalances in the regulation of power supply and demand, the academic community has proposed the substitute power product (SPP) market, which is based on the trading of prescribed generation shapes over defined periods. However, there is currently no literature addressing the optimization strategies for market participants within the SPP market trading model. To fill this gap, this study introduces, for the first time, an energy storage planning and optimization operation strategy for wind and photovoltaic energy stations within this market framework. First, the basic trading process and related concepts of the SPP market are introduced. Then, based on the operational logic of the SPP market, a multi-stage energy storage planning and operation strategy is proposed for wind and photovoltaic stations. This strategy integrates a two-level model with a multi-scenario stochastic planning model to optimize the storage capacity and power allocation of renewable energy stations under uncertainty. Subsequently, relevant metrics for the SPP market are introduced, and these metrics are used to quantitatively analyze the feasibility of cooperation among different renewable energy stakeholders in the market. Finally, the impact of regulation power prices on the decision-making of renewable energy stations participating in the SPP market is explored. The findings of this study provide new energy producers with a preliminary optimization solution for energy storage configuration and operation under the new trading model, promoting their participation in the SPP market and contributing to the acceleration of the low-carbon transformation of power systems.