Three-Dimensional Human Pose Estimation from Sparse IMUs through Temporal Encoder and Regression Decoder

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 7; p. 3547
• Main Authors: Liao, Xianhua, Dong, Jiayan, Song, Kangkang, Xiao, Jiangjian
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 28-03-2023; MDPI
• Subjects: Algorithms; Analysis; Biomechanical Phenomena; Calibration; Datasets; Deep learning; encoder–decoder; Human body; human kinematics hierarchy; Human motion; Humans; Inertial platforms; Kinematics; Motion; Motion capture; Movement; Neural networks; Neural Networks, Computer; Performance evaluation; Pose estimation; Position errors; regression decoder; Sensors; Shaking; sparse IMUs; Teaching methods; temporal convolutional encoder; Three dimensional analysis; Three dimensional motion; three-dimensional human pose; Topology; regression decoder; three-dimensional human pose; human kinematics hierarchy; temporal convolutional encoder; encoder–decoder; sparse IMUs
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23073547

Three-dimensional (3D) pose estimation has been widely used in many three-dimensional human motion analysis applications, where inertia-based path estimation is gradually being adopted. Systems based on commercial inertial measurement units (IMUs) usually rely on dense and complex wearable sensors and time-consuming calibration, causing intrusions to the subject and hindering free body movement. The sparse IMUs-based method has drawn research attention recently. Existing sparse IMUs-based three-dimensional pose estimation methods use neural networks to obtain human poses from temporal feature information. However, these methods still suffer from issues, such as body shaking, body tilt, and movement ambiguity. This paper presents an approach to improve three-dimensional human pose estimation by fusing temporal and spatial features. Based on a multistage encoder-decoder network, a temporal convolutional encoder and human kinematics regression decoder were designed. The final three-dimensional pose was predicted from the temporal feature information and human kinematic feature information. Extensive experiments were conducted on two benchmark datasets for three-dimensional human pose estimation. Compared to state-of-the-art methods, the mean per joint position error was decreased by 13.6% and 19.4% on the total capture and DIP-IMU datasets, respectively. The quantitative comparison demonstrates that the proposed temporal information and human kinematic topology can improve pose accuracy.