Abstract
Human pose estimation and tracking in real-time from multi-sensor systems is essential for many applications. Combining multiple heterogeneous sensors increases opportunities to improve human motion tracking. Using only a single sensor type, e.g., inertial sensors, human pose estimation accuracy is affected by sensor drift over longer periods. This paper proposes a human motion tracking system using lidar and inertial sensors to estimate 3D human pose in real-time. Human motion tracking includes human detection and estimation of height, skeletal parameters, position, and orientation by fusing lidar and inertial sensor data. Finally, the estimated data are reconstructed on a virtual 3D avatar. The proposed human pose tracking system was developed using open-source platform APIs. Experimental results verified the proposed human position tracking accuracy in real-time and were in good agreement with current multi-sensor systems.
Highlights
Sensors 2021, 21, 2340. https://Many studies have investigated accurately estimating and tracking three-dimensional (3D) objects in real-time using single or multiple sensor systems [1,2,3]
Significant milestones have been achieved for tracking human pose using depth, inertial, vision, light detection and ranging sensor systems, and more recently, heterogeneous multi-sensor systems [5]
We demonstrate its feasibility and effectiveness by comparing proposed multi-sensor pose tracking with other multiple fusion methods
Summary
Many studies have investigated accurately estimating and tracking three-dimensional (3D) objects in real-time using single or multiple sensor systems [1,2,3]. Significant milestones have been achieved for tracking human pose using depth, inertial, vision, light detection and ranging (lidar) sensor systems, and more recently, heterogeneous multi-sensor systems [5]. Three-dimensional lidar sensor applications have expanded dramatically over the last few decades [14], including robotics, autonomous vehicles, HCI, and human pose detection and tracking. The proposed system provides a more feasible and robust system for human pose estimation with accurate detection, tracking, and reconstruction on a virtual avatar using multiple sensors (Lidar and IMUs) on an open-source platform. Track position and orientation using multiple heterogeneous sensors and Reconstruct human motion on a 3D Avatar.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have