Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment
This work addresses pose estimation for dance gaming platforms, offering a solution to limitations in existing RGB and RGB-Depth methods, though it is incremental in applying event cameras to this specific domain.
The authors tackled the problem of human pose estimation in dynamic, low-light dance environments by developing YeLan, an event camera-based 3D system that outperformed baseline models with robustness against clothing, motion, and lighting variations.
As a beloved sport worldwide, dancing is getting integrated into traditional and virtual reality-based gaming platforms nowadays. It opens up new opportunities in the technology-mediated dancing space. These platforms primarily rely on passive and continuous human pose estimation as an input capture mechanism. Existing solutions are mainly based on RGB or RGB-Depth cameras for dance games. The former suffers in low-lighting conditions due to the motion blur and low sensitivity, while the latter is too power-hungry, has a low frame rate, and has limited working distance. With ultra-low latency, energy efficiency, and wide dynamic range characteristics, the event camera is a promising solution to overcome these shortcomings. We propose YeLan, an event camera-based 3-dimensional high-frequency human pose estimation(HPE) system that survives low-lighting conditions and dynamic backgrounds. We collected the world's first event camera dance dataset and developed a fully customizable motion-to-event physics-aware simulator. YeLan outperforms the baseline models in these challenging conditions and demonstrated robustness against different types of clothing, background motion, viewing angle, occlusion, and lighting fluctuations.