• Home
• Program
• Social Events
• Program at a Glance
• Keynote Speakers
• Presentation Guidelines
• Author Centre
• Important Dates
• Committees
• Sponsors and Exhibitors
• Registration Information
• Conference Venue
• Travel Information
• Contact

11:30   Data analysis and algorithms Chair: Geurt Jongbloed 11:30 20 mins FINDING THE OPTIMAL BACKGROUND SUBTRACTION ALGORITHM FOR EUROHOCKEY 2015 VIDEO David Higham, John Kelley, Chris Hudson, Simon Goodwill Abstract: Background subtraction is a classic step in a vision-based localization and tracking workflow. Previous studies have compared background subtraction algorithms on publicly available datasets; however comparisons were made only with manually optimized parameters. The aim of this research was to identify the optimal background subtraction algorithm for a set of field hockey videos captured at EuroHockey 2015. Particle Swarm Optimization was applied to find the optimal background subtraction algorithm. The objective function was the F-score, i.e. the harmonic mean of precision and recall. The precision and recall were calculated using the output of the background subtraction algorithm and gold standard labeled images. The training dataset consisted of 15 x 13 second field hockey video segments. The test data consisted of 5 x 13 second field hockey video segments. The video segments were chosen to be representative of the teams present at the tournament, the times of day the matches were played and the weather conditions experienced. Each segment was 960 pixels x 540 pixels and had 10 ground truth labeled frames. Eight commonly used background subtraction algorithms were considered. Results suggest that a background subtraction algorithm must use optimized parameters for a valid comparison of performance. Particle Swarm Optimization is an appropriate method to undertake this optimization. The optimal algorithm, Temporal Median, achieved an F-score of 0.791 on the test dataset, suggesting it generalizes to the rest of the video footage captured at EuroHockey 2015. 11:50 20 mins ACTIVITY RECOGNITION IN SURFING – A COMPARATIVE STUDY BETWEEN HIDDEN MARKOV MODEL AND SUPPORT VECTOR MACHINE Hannes Höttinger, Franziska Mally, Stefan Litzenberger, Anton Sabo Abstract: The given project describes a comparative study between two different machine learning approaches, the Hidden Markov Model (HMM) and Support Vector Machines (SVMs), for activity recognition in surfing, aiming to distinguish surfing from other non-traditional (non-surfing) movements. The Hidden Markov Model has been introduced as a probabilistic or statistical framework for time-varying processes [1], whereas the Support Vector Machine algorithm is probably the most widely used kernel learning algorithm [2]. Human activities are classified by using only one Inertial Measurement Unit (IMU) worn on the chest. A feature set extracted from the raw sensor data is used in the classification process. Feature transformation, in respect of dimensional reduction is implemented with Principal Component Analysis (PCA). A performance comparison of the classification models is provided in terms of their correct differentiation rates and confusion matrices, as well as their preprocessing and training requirements. 5-fold cross validation is employed to validate the classifiers. The results indicate that the HMM results in a higher classification accuracy of 91.4% compared to the SVM with an accuracy of 83.4%. The algorithm is capable of classifying time-varying motions from input data of an IMU worn during a surfing session. Moreover, the surfing style between subjects differs widely from left to right waves, right to left waves, goofy or regular footed and the execution itself. However, the implementation of the wave-model allows to train only one data set including every wave data collected and must not separate the data into different forms of execution. References: [1] Rabiner, L., Juang, B. (1986). An Introduction to Hidden Markov Models. IEEE ASSP Magazine, 3, pp.4–16. [2] Bottou, L., Lin, C.-J. (2007). Support vector machine solvers. Large scale kernel machines, pp.301–320. Massachusetts Institute of Technology. 12:10 20 mins ASSESSING HUMAN-FLUID-STRUCTURE INTERACTION FOR THE INTERNATIONAL MOTH Joseph Banks, Laura Marimon-Giovannetti, Joshua Taylor, Stephen Turnock Abstract: The International Moth is an ultra-lightweight foiling dinghy class. Foil deflections and dynamic sailor-induced motions are identified as two key areas relating to foiling moth performance that are currently ignored in Velocity Prediction Programs (VPP). The impact of foil deflections is assessed by measuring the tip deflection and twist deformation of a T-foil from an International Moth. The full field deformation due to an applied load is measured using Digital Image Correlation (DIC). The foil’s structural properties can then be determined based on the measured structural response. The deformations are then calculated for an estimated steady sailing force distribution on the T-foil and their impact on performance is evaluated. To investigate the impact of dynamic sailor motions a system is developed that allows a sailor’s dynamic pose to be captured when out on the water by determining the orientations of key body segments using inertial sensors. It is validated against measured hiking moments and is demonstrated to work out on the water whilst sailing. Both these studies pave the way towards developing a Dynamic VPP for the international Moth, which can include unsteady human and foil interactions.