Bachelors Thesis in collaboration with Robotics Research Lab at UC3M (Jan - Sep 2021)
Objective and process:
This project aimed to develop a gesture recognition system utilizing a specialized Intel Realsense camera to capture images of hand gestures and extract their meaning. To accomplish this, I conducted a thorough investigation into current state-of-the-art systems and various machine learning algorithms to determine the best approach for the application and data at hand.
Challenges:
Throughout the project, I faced numerous challenges due to limited guidance from my project tutor. However, I persevered and acquired a wealth of knowledge in machine learning and virtual reality, which has greatly aided my personal and professional growth. Specifically, I gained a deep understanding of how deep-sensing cameras operate and how convolutional neural networks are trained to recognize gestures.
Results:
Ultimately, I successfully created the application required for gesture detection, and this work has the potential to be applied to various serious games and virtual reality assistance applications being developed at Robotics Lab. Overall, this project not only allowed me to develop technical skills but also taught me valuable lessons in resilience and independent learning.