MLSurf : Surfer Motion Characterization Using Machine Learning Techniques

Abstract: Wave surfing is a popular sport that requires minimal financial investment, while it can still be enjoyable from the very first attempt. At the same time, the demand for smart devices that enhance the experience of doing sports by analyzing and evaluating the activities is growing. For surf sport, there are some solutions that are able to collect statistics about activities being done during a surf session, but none of them is able to recognize specific maneuvers that are performed during wave riding. The goal of this Master Thesis is to improve a currently existing surf activity monitoring solution by extending it with the ability to identify the two most common surf maneuvers during a wave riding session, namely cutback and snap. The solution is using the user’s smartphone to collect IMU sensor data and feed it to a classification pipeline. The implemented algorithm takes raw sensor data as an input, performs various preprocessing steps, splits the input stream into segments, extracts features from these segments and feed them into a hierarchical classification tree. The implemented pipeline is able to classify non-maneuver, cutback and snap segments with 78% accuracy on a self-collected dataset.