Among the various traffic accidents, the proportion of traffic accidents caused by the reduction of visibility caused by bad weather such as smog is increasing year by year, so the detection of visibility in bad weather has become an urgent problem to be solved. According to the different ways of extracting features, this paper not only divides the visibility detection methods into visual inspection methods, instrument and equipment detection methods and image algorithm detection methods, but also summarizes the development process of visibility detection methods. On the basis of analyzing and comparing the visibility detection methods based on deep learning, it is proposed that the introduction of the latest deep learning algorithm into visibility detection is the focus of follow-up research. Finally, the shortcomings and limitations of existing visibility detection methods are summarized, and the direction of further research in the future is pointed out.