Extraction of Bicycle Crash Kinematics from Videos Using Machine Learning


openposegif
Pose estimation example using OpenPose. Example bicycle crash

It is extremely difficult to obtain motion data of bicycle crashes for a number of reasons. But this kind of data would be very useful in understanding why falls and crashes occur during bicycling. Understanding the mechanisms are key to preventing injuries and death of bicyclists. It is a bit easier to find and collect video data of crashes and there are a number of new technologies that make it easier to extract kinematic motion and pose data from videos using machine learning (e.g. DeepLabCut, OpenPose, Anipose). The TU Delft Bicycle lab has a reasonably large set of training data of typical (non-crash) bicycling that can be used to build the video to kinematics predictive models. The goal of this project would be to collect a large set of bicycle crash videos, build a model that can extract the kinematics of both the bicycle and the rider, and show that accurate kinematics can be acquired.

How to Apply

Send an email to j.k.moore@tudelft.nl with the title of the project in the subject line. Include an approximately half-page motivation letter explaining why you want to work in the Bicycle Lab on this project, what relevant skills you have, and your current resume or C.V.