Oceanfront is a typical and important sea surface feature that is reported to be associated with marine ecosystems and can be used as a reference for locating fishing grounds. Frontal zone extraction is often performed using a gradient threshold to classify image pixels and the result can sometimes contain too many spikes and become chaotic, leading to a negative effect for visual interpretation. And most conventional methods that focus on extracting the ridges of fronts struggle with false fronts due to imperfect data. Also, choosing appropriate thresholds for them is another dilemma, which sometimes leads to too many frontal ridges in unwanted areas or too little than needed in the region of interest. To meet the needs for visual interpretation and automatic front detection in significant frontal areas, a novel method based on deep learning is proposed in this letter. In this method, a deep learning model with U-Net architecture was designed to detect and locate significant frontal zones in grayscale sea surface temperature (SST) images. Then, an area threshold was adopted to filter the output of the model to improve the result. To demonstrate the effect of the proposed method, it was applied to an example SST image. The results show that the proposed method can not only merge messy fronts but also capture the overall patterns of frontal zones and work with conventional methods to get a better frontal ridge extraction result.

To address the increasing demand for bridge height information in modern navigation management, we proposed a method for extracting bridge height information based on Gaofen-2 satellite images. In response to the lack of systematic research on bridge height inversion in existing studies, particularly in optical remote sensing technology, we filled this research gap. We thoroughly analyzed the spatial relationship among the sun, satellites, and bridges and proposed the key steps for bridge height inversion based on a geometric model. We also elaborated on the calculation method for determining the height from the bridge surface to the water surface. To verify the effectiveness of the method, we used the Jiaozhou Bay Bridge as a case study, analyzed data from the Gaofen-2 image, and compared the results with actual bridge height data. The experimental results demonstrated that the method achieved high accuracy when the satellite observation orientation was consistent with the bridge alignment, with an absolute error of 0.18 m and a relative error of 0.36%. Even with some differences in the observation orientation, the proposed method still exhibited good adaptability, especially in the inversion of bridge heights over water bodies, and effectively corrected the impact of tidal level changes on height extraction. We provided a viable approach for bridge height information extraction using optical remote sensing images in the future and offered efficient technical support for remote sensing applications in complex environments.