3D Pose Nowcasting: Forecast the Future to Improve the Present
This work addresses the need for precise 3D pose understanding in human-robot collaboration scenarios, offering a novel approach that enhances accuracy for applications like robotics and human monitoring.
The paper tackles the problem of accurately estimating 3D poses for human-robot collaboration by proposing a vision-based system that uses depth data and introduces Pose Nowcasting, which improves current pose estimation by forecasting future poses, achieving accurate and real-time performance on two datasets.
Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years. A critical component useful for realizing this collaborative paradigm is the understanding of human and robot 3D poses using non-invasive systems. Therefore, in this paper, we propose a novel vision-based system leveraging depth data to accurately establish the 3D locations of skeleton joints. Specifically, we introduce the concept of Pose Nowcasting, denoting the capability of the proposed system to enhance its current pose estimation accuracy by jointly learning to forecast future poses. The experimental evaluation is conducted on two different datasets, providing accurate and real-time performance and confirming the validity of the proposed method on both the robotic and human scenarios.