Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds
Radar-based human pose estimation has focused on improving learning algorithms while representing the body as unconstrained keypoint coordinates. We address the underexplored dimension of anatomical fidelity by integrating a full-body skeletal model into a differentiable, end-to-end trainable radar-based pose estimation framework, in which the pose network is supervised through forward kinematics while subject-specific geometry is fitted beforehand. Subject-specific body segment proportions are predicted from radar point cloud features to scale a biomechanical skeleton. A motion prediction network maps temporal radar sequences to generalized coordinates, and differentiable forward kinematics converts predicted joint angles into 3D positions. A contact classification loss encourages physically plausible foot-ground interaction. Under leave-one-subject-out cross-validation on 11 healthy participants performing rehabilitation exercises, the framework achieves 6.456 +/- 1.759 cm mean per-joint position error (MPJPE), 8.083 +/- 0.884 degrees mean per-joint angle error (MPJAE), 0.935 +/- 0.009 contact classification F1, and 3.4 +/- 1.3 % scaling error. This proof-of-concept study demonstrates the feasibility of recovering interpretable biomechanical descriptors from a single low-cost radar sensor in a controlled laboratory setting, a prerequisite for future clinical motion analysis.
Code (0)
등록된 구현이 없습니다.
Tasks
Pose EstimationPoint CloudsSimilar Papers 제목 키워드 기반
Hybrid 3D Human Pose Estimation with Monocular Video and Sparse IMUs
Temporal 3D human pose estimation from monocular videos is a challenging task in human-centered computer vision due to the depth ambiguity of 2D-to-3D lifting. To improve accuracy and address occlusion issues, inertial s…
3D Human Pose EstimationPose EstimationNeural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture
Due to the visual ambiguity, purely kinematic formulations on monocular human motion capture are often physically incorrect, biomechanically implausible, and can not reconstruct accurate interactions. In this work, we fo…
DecoderLearning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation
Virtual models of human gait, or digital twins, offer a promising solution for studying mobility without the need for labor-intensive data collection. However, challenges such as the sim-to-real gap and limited adaptabil…
Imitation LearningPhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time
Marker-less 3D human motion capture from a single colour camera has seen significant progress. However, it is a very challenging and severely ill-posed problem. In consequence, even the most accurate state-of-the-art app…
DuoGesture: Neuro-Inspired and Biomechanically Informed Dual-Stream Co-Speech Gesture Generation
Co-speech gesture generation requires both semantic expressivity and biomechanically plausible rhythmic motion. Existing holistic gesture models mix lexically grounded semantic gestures with frequent prosody-aligned beat…
Gesture Generation