Choi, Y.; Choe, H.-G.; Choi, J.Y.; Kim, K.T.; Kim, J.-B., and Kim, N.-I., 2018. Automatic sea fog detection and estimation of visibility distance on CCTV. In: Shim, J.-S.; Chun, I., and Lim, H.S. (eds.), Proceedings from the International Coastal Symposium (ICS) 2018 (Busan, Republic of Korea). Journal of Coastal Research, Special Issue No. 85, pp. 881–885. Coconut Creek (Florida), ISSN 0749-0208.
Sea fog is one of the major maritime disasters and thus causes social costs such as transport accidents, mainly due to the reduction of visibility. However, the optical fog sensors are heavily cost so that sea fog detection system is generally difficult to install in practical applications. In this paper, we present a new technique for detecting sea fog and measuring visibility distances using Closed-circuit television (CCTV). Our research is focused on the problem of detecting daytime sea fog and estimating visibility distances in an automatic way. To this end, we exploit that (1) the image analysis based on the HSL (Hue, Saturation, and Lightness) color model is effective for evaluating the density of sea fog and (2) the movement detection system relying on the variance of the pixel values is capable of deciding the visibility distances. The proposed method has advantage of being readily applicable to the widely used CCTV system without additional devices. This paper also explores the possibility of sea fog detection using deep-learning framework. In our method, Deep Convolution Neural Network (DCNN) end-to-end learning solution has been designed and tested for evaluating sea fog detection performance in the course of popular artificial intelligence framework.