This chapter deals with shadow modelling and its utilities in shadow detection and weather estimation in out-door space. Noting the diuse skylight is scattered by particles in the atmosphere, we view the skylight, which casts the shadow, as a linear combination of scattered sunlight obeying Rayleigh scattering and Mie theory. Thus, we propose a ratio on the shadow-sunlit boundary which only depends on atmospheric condition. This ratio recasts recovering the shadow areas into a clustering setting making use of active contours. It also allows a metric to be formulated that indicates the degree to which a scene is overcast. We illustrate the utility of the method for purposes of detecting shadows and weather estimation in real-world imagery, provide time complexity results and compare against a number of alternatives elsewhere in the literature.
Handbook of Pattern Recognition and Computer Vision, 5th Edition, 15 Mar 2016, ISBN: 978-981 4656258