Video playback is currently the primary method coaches and athletes use in sports training to give feedback on the athlete’s form and timing. Athletes will commonly record themselves using a phone or camera when practicing a sports movement, such as shooting a basketball, to then send to their coach for feedback on how to improve. In this work, we present Augmented Coach, an augmented reality tool for coaches to give spatiotemporal feedback through a 3-dimensional point cloud of the athlete. The system allows coaches to view a pre-recorded video of their athlete in point cloud form, and provides them with the proper tools in order to go frame by frame to both analyze the athlete’s form and correct it. The result is a fundamentally new concept of an interactive video player, where the coach can remotely view the athlete in a 3-dimensional form and create annotations to help improve their form. We then conduct a user study with subject matter experts to evaluate the usability and capabilities of our system. As indicated by the results, Augmented Coach successfully acts as a supplement to in-person coaching, since it allows coaches to break down the video recording in a 3-dimensional space and provide feedback spatiotemporally. The results also indicate that Augmented Coach can be a complete coaching solution in a remote setting. This technology will be extremely relevant in the future as coaches look for new ways to improve their feedback methods, especially in a remote setting.

Video playback is currently the primary method coaches and athletes use in sports training to give feedback on the athlete’s form and timing. Athletes will commonly record themselves using a phone or camera when practicing a sports movement, such as shooting a basketball, to then send to their coach for feedback on how to improve. In this work, we present Augmented Coach, an augmented reality tool for coaches to give spatiotemporal feedback through a 3-dimensional point cloud of the athlete. The system allows coaches to view a pre-recorded video of their athlete in point cloud form, and provides them with the proper tools in order to go frame by frame to both analyze the athlete’s form and correct it. The result is a fundamentally new concept of an interactive video player, where the coach can remotely view the athlete in a 3-dimensional form and create annotations to help improve their form. We then conduct a user study with subject matter experts to evaluate the usability and capabilities of our system. As indicated by the results, Augmented Coach successfully acts as a supplement to in-person coaching, since it allows coaches to break down the video recording in a 3-dimensional space and provide feedback spatiotemporally. The results also indicate that Augmented Coach can be a complete coaching solution in a remote setting. This technology will be extremely relevant in the future as coaches look for new ways to improve their feedback methods, especially in a remote setting.

Video playback is currently the primary method coaches and athletes use in sports training to give feedback on the athlete's form and timing. Athletes will commonly record themselves using a phone or camera when practicing a sports movement, such as shooting a basketball, to then send to their coach for feedback on how to improve. In this work, we present Augmented Coach, an augmented reality tool for coaches to give spatiotemporal feedback through a 3-dimensional point cloud of the athlete. The system allows coaches to view a pre-recorded video of their athlete in point cloud form, and provides them with the proper tools in order to go frame by frame to both analyze the athlete's form and correct it. The result is a fundamentally new concept of an interactive video player, where the coach can remotely view the athlete in a 3-dimensional form and create annotations to help improve their form. We then conduct a user study with subject matter experts to evaluate the usability and capabilities of our system. As indicated by the results, Augmented Coach successfully acts as a supplement to in-person coaching, since it allows coaches to break down the video recording in a 3-dimensional space and provide feedback spatiotemporally. The results also indicate that Augmented Coach can be a complete coaching solution in a remote setting. This technology will be extremely relevant in the future as coaches look for new ways to improve their feedback methods, especially in a remote setting.

This paper discusses the process of creating and testing the haptic feedback wearable that utilizes a sweeping Light Detection and Ranging sensor. This design comes as an extension to the capstone project for electrical engineers. The design works by attaching a LiDAR sensor to a sweeping servo motor, and whenever an object is detected by the sensor, a motor will vibrate to notify the user that an object is nearby. The design incorporates four motors so that the user will have a sense of where an obstacle is coming from and be able to navigate around that obstacle. The design was tested for its accuracy in distance and angle measurement, its efficiency when it came to processing the data, and the uncertainty of the sensor due to beam spreading. Plotting the results for the distance and angle accuracy showed that the design is capable of accurate measurements. The implementation of the code was also very efficient and had no issues with latency when processing the data from the sensor. There was also uncertainty at the larger ranges for the sensor.

The purpose of this project is to create a useful tool for musicians that utilizes the harmonic content of their playing to recommend new, relevant chords to play. This is done by training various Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) on the lead sheets of 100 different jazz standards. A total of 200 unique datasets were produced and tested, resulting in the prediction of nearly 51 million chords. A note-prediction accuracy of 82.1% and a chord-prediction accuracy of 34.5% were achieved across all datasets. Methods of data representation that were rooted in valid music theory frameworks were found to increase the efficacy of harmonic prediction by up to 6%. Optimal LSTM input sizes were also determined for each method of data representation.