Self-Tuning of a Sunlight-Deflickering Filter for Moving Scenes Underwater

EMANUEL TRABES; MARIO A. JORDÁN

Cordoba

Workshop; 2015 XVI Workshop on Information Processing and Control; 2015

This work deals with the design of a real-time ap-proach for automatic parameter tuning in a deflickering processof videos of a moving landscape scene underwater perturbedwith sunlight waves. The tuner performs a continuous parameteroptimization inside a basic filter, which employes feedback inorder to improve the performance. Also it is able to adaptthe optimum to eventual changing of the scenario conditions.Moreover, issues like the parameter sensitivity and loop stabilityare addressed equally. The results have been illustrated by meansof a worked-out case-study employing real film material of ascenario underwater. The approach was motivated by the SLAMapplications with monocamera vision-based vehicles underwaterand simple hardware implementations in FPGA structures.