Understanding the locomotion of insects is important both from a neurological perspective and for developing bio-inspired walking robots. To obtain quantitative information about leg movements during insect locomotion, advanced image-analysis methods are required.

The goal of this project is to develop algorithms for extracting the position of the leg segments and their joints in high-speed videos of fruit flies. The project will be divided in two main parts:

1) a modeling part, where the student will have to generate realistic synthetic videos of leg motion;

2) an analysis part, where the student will have to implement different tracking approaches and test them against the synthetic videos.

Eventually, the best method will be incorporated into a complete tracking framework and applied to images of real flies.

The project will primarily be supervised at the Biomedical Imaging Group (EPFL), in close interaction with the Laboratory of Intelligent Systems (EPFL) and in collaboration with the Benton Lab (UNIL).