Biophysics-inspired hydrodynamic imaging

Contact person: Dr. Sietse van Netten

Mechano-sensory arrays, inspired by the sensory modality of the fish lateral line, are designed, built and tested. These artificial flow sensing arrays consist of all-optical flow sensors, capable of measuring fluid flow ranging from tens of micrometers- to meters per second, and have been tested in increasingly realistic environments (lab, pool, and under harsh benthic conditions). Previous biophysical investigations have revealed several aspects of lateral line signal processing in fish for hydrodynamic imaging. We have now demonstrated a similar use of the arrays for artificial hydrodynamic imaging of submerged moving objects: Velocity profiles measured along the flow sensing arrays convey adequate hydrodynamic information to not only localize moving objects but also to instantaneously detect their movement direction as well as to classify their shapes.We compare diverse strategies, ranging from neural networks (MLP, CNN, ELM, ESN, LSTM), beamforming, template-matching algorithms and (bio)physics-based methods to further investigate efficient ways of artificial hydrodynamic imaging.