Search Results (3)

The density of fog is directly related to visibility and is one of the decision-making criteria for airport flight management and highway traffic management. Estimating fog density based on images and videos has been a popular research topic in recent years. However, the fog density estimated results based on images should be further evaluated and analyzed by combining weather information from other sensors. The data obtained by different sensors often need to be aligned in terms of time because of the difference in acquisition methods. In this paper, we propose a video and a visibility data alignment method based on temporal consistency for data alignment. After data alignment, the fog density estimation results based on images and videos can be analyzed, and the incorrect estimation results can be efficiently detected and corrected. The experimental results show that the new method effectively combines videos and visibility for fog density estimation. Full article

Accurate lane detection is an essential function of dynamic traffic perception. Though deep learning (DL) based methods have been widely applied to lane detection tasks, such models rarely achieve sufficient accuracy in low-light weather conditions. To improve the model accuracy in foggy conditions, a new approach was proposed based on monocular depth prediction and an atmospheric scattering model to generate fog artificially. We applied our method to the existing CULane dataset collected in clear weather and generated 107,451 labeled foggy lane images under three different fog densities. The original and generated datasets were then used to train state-of-the-art (SOTA) lane detection networks. The experiments demonstrate that the synthetic dataset can significantly increase the lane detection accuracy of DL-based models in both artificially generated foggy lane images and real foggy scenes. Specifically, the lane detection model performance (F1-measure) was increased from 11.09 to 70.41 under the heaviest foggy conditions. Additionally, this data augmentation method was further applied to another dataset, VIL-100, to test the adaptability of this approach. Similarly, it was found that even when the camera position or level of brightness was changed from one dataset to another, the foggy data augmentation approach is still valid to improve model performance under foggy conditions without degrading accuracy on other weather conditions. Finally, this approach also sheds light on practical applications for other complex scenes such as nighttime and rainy days. Full article

The aim of this paper is to investigate the various effects of climate conditions on outdoor insulators in coastal areas as a result of saline contamination under acidic and normal cold fog, determining significant electrical and physico-chemical changes on the insulator surface and considering the effect of discharge current, electric field distribution and surface roughness. To replicate similar conditions near the shoreline, experimental investigations have been carried out on insulation materials with the combined application of saline contamination and acidic or normal cold fog. The test samples included silicone rubber (SiR), ethylene propylene diene monomer (EPDM) and high-density polyethylene (HDPE), which were used as reference. The materials are of the same composition as those used in real-life outdoor high voltage insulators. All samples were aged separately in an environmental chamber for 150 h for various saline contaminations combined with acidic and normal cold fog, and were generated by means of the adopted experimental setup. This analysis represented conditions similar to those existing near the shoreline exposed to saline and acid spray during winter and early spring. Electric field and discharge current along polymeric samples were examined under acidic and normal cold fog. Fourier transform infrared (FTIR) spectroscopy and scanning electron microscopic (SEM) were used to probe the physico-chemical changes on the samples surface and investigate the hydrophobicity recovery property after aging tests. Finally, a comparative study was carried out on polymeric samples before and after being exposed to the acidic and normal cold fog based on the results obtained from the experiment. Research data may provide references for the better prediction of surface degradation as well as for the better material coating and design of external insulation. Full article