Commercial visibility sensors among meteorological sensors estimate the visibility distance based on transmission, backward scattering, and forward scattering principle. These optical visibility sensors yield comparatively accurate local visibility distance. However, it is still difficult to obtain comprehensive visibility information for a wide area, such as the coast or harbor due to the sensor structure using straightness and scattering properties of light. In this paper, we propose a novel visibility distance estimation method using dark channel prior (DCP) and distance map based on a camera image. The proposed method improves the local limit of optical visibility sensor and detects the visibility distance of a wide area more precisely. First, the dark channel for an input sea-fog image is calculated. The binary transmission image is obtained by applying a threshold to the estimated transmission from the dark channel. Then, the sum of the distance values of pixels, corresponding to the sea-fog boundary, is averaged, in order to derive the visibility distance. This paper also proposes a novel air-light and transmission estimation technique in order to extract the visibility distance for an abnormal sea-fog image, including any light source, such as sunlight, reflection light, and illumination light, etc. The estimated visibility distance was compared with optical visibility distance of an optical visibility sensor and their agreement was evaluated.

Sea fog is a natural phenomenon that reduces the visibility of manned vehicles and vessels that rely on the visual interpretation of traffic. Fog clearance, also known as fog dissipation, is a relatively under-researched area when compared with fog prediction. In this work, we first analyzed meteorological observations that relate to fog dissipation in Incheon port (one of the most important ports for the South Korean economy) and Haeundae beach (the most populated and famous resort beach near Busan port). Next, we modeled fog dissipation using two separate algorithms, classification and regression, and a model with nine machine learning and three deep learning techniques. In general, the applied methods demonstrated high prediction accuracy, with extra trees and recurrent neural nets performing best in the classification task and feed-forward neural nets in the regression task.

Sea fog can seriously affect schedules and safety by reducing visibility during marine transportation. Therefore, the forecasting of sea fog is an important issue in preventing accidents. Recently, in order to forecast sea fog, several deep learning methods have been applied to time series data consisting of meteorological and oceanographic observations or image data to predict fog. However, these methods only use a single image without considering meteorological and temporal characteristics. In this study, we propose a multi-modal learning method to improve the forecasting accuracy of sea fog using convolutional neural network (CNN) and gated recurrent unit (GRU) models. CNN and GRU extract useful features from closed-circuit television (CCTV) images and multivariate time series data, respectively. CCTV images and time series data collected at Daesan Port in South Korea from 1 March 2018 to 14 February 2021 by Korea Hydrographic and Oceanographic Agency (KHOA) were used to evaluate the proposed method. We compare the proposed method with deep learning methods that only consider temporal information or spatial information. The results indicate that the proposed method using both temporal and spatial information at the same time shows superior accuracy.