Single camera estimation of microswimmer depth with a convolutional network

Abstract

A number of techniques have been developed to measure the three-dimensional trajectories of protists, which require special experimental setups, such as a pair of orthogonal cameras. On the other hand, machine learning techniques have been used to estimate the vertical position of spherical particles from the defocus pattern, but they require the acquisition of a labeled dataset with finely spaced vertical positions. Here we describe a simple way to make a dataset of Paramecium images labeled with vertical position from a single 5 minutes movie, based on a tilted slide setup. We used this dataset to train a simple convolutional network to estimate the vertical position of Paramecium from conventional bright field images. As an application, we show that this technique has sufficient accuracy to study the surface following behavior of Paramecium (thigmotaxis).