Two-dimensional anisotropic Gaussian-Laplace filter design for visibility distance estimation under foggy weather

摘要

In order to fully take advantage of structural information of an inflection point line (IPL), we heuristically present a new Two-dimensional anisotropic Gaussian-Laplace filter (AGLF) to detect the inflection point line. Based on the AGLF, a novel and real-time algorithm for calculating visibility distance under foggy weather is proposed. The performance of the proposed method is experimentally validated by using ten test video sequences which are captured in real world. The experimental results demonstrate that our algorithm provides accurate visibility distance estimation through quantitative evaluations.