Wavelet Transform for Visibility Analysis in Fog Situations

In this article a new technique for the estimation of the distance of visibility in fog conditions is presented. It is based on a psychovisual model and on contrast estimation with wavelet transform. For this application, specific B–spline wavelets are introduced in order to have a good space and frequency localization and to enable a fast implementation. Using images stemming from situations on motorways, this technique is compared to a direct local contrast calculation.

[1]  P. Thompson,et al.  Effect of contrast on human speed perception , 1992 .

[2]  Richard A. Young,et al.  GAUSSIAN DERIVATIVE MODEL FOR MACHINE VISION: VISUAL CORTEX SIMULATION. , 1986 .

[3]  D. C. Van Essen,et al.  Concurrent processing streams in monkey visual cortex , 1988, Trends in Neurosciences.

[4]  Jeroen Hogema.  Evaluation of an automatic fog-warning system , 1996 .

[5]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[6]  Dennis M. Healy,et al.  Contrast enhancement via multiscale gradient transformation , 1994, Proceedings of 1st International Conference on Image Processing.

[7]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Michael Unser,et al.  On the asymptotic convergence of B-spline wavelets to Gabor functions , 1992, IEEE Trans. Inf. Theory.

[9]  Tomaso A. Poggio,et al.  On Edge Detection , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.