Generalized Optical Flow Model for Scattering Media

Abstract

This paper proposes a novel methodology to estimate the optical flow in scattering media, which consists on new formulation based on the classical Horn-Schunk approach and the optical image formation model. Our formulation is able to deal with the hard problem of tracking points in a medium where there is absorption and scattering effects. This approach generalizes assumptions of the Horn-Schunk model in order to tackle both non-scattering and scattering media. Our approach uses the Dark Channel Prior to estimate the scene transmission, which attains a significant improvement in the optical flow estimation in scattering media. We show that our approach outperformed state-of-the-art models and we provide a detailed analysis of our technique that shows its applicability to image sequences acquired both in simulated and real scenes.

Diagnostics and prognostics of multi-mode failure scenarios in miter gates using multiple data sources and a dynamic Bayesian network

“…Correspondingly, a simplified digital image model is developed to represent the process of obtaining the displacement measurements from images (a "measurement model") using the optical flow method. Given the fact that Drews et al (2014) found turbidity increases the error of optical flow fields and Madjidi and Negahdaripour (2006) proved that the low-contrast photo underestimates the magnitude of the optical flow field, the model down-sizes the displacement measurements and assigns a noise that represents the noise level of photos taken underwater. This noise also accounts for environmental factors such as camera vibration and light source movement over a lock filling event.…”