Corpus ID: 236318126

Human Pose Estimation from Sparse Inertial Measurements through Recurrent Graph Convolution

@article{Puchert2021HumanPE,
  title={Human Pose Estimation from Sparse Inertial Measurements through Recurrent Graph Convolution},
  author={Patrik Puchert and Timo Ropinski},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.11214}
}
We propose the adjacency adaptive graph convolutional long-short term memory network (AAGC-LSTM) for human pose estimation from sparse inertial measurements, obtained from only 6 measurement units. The AAGC-LSTM combines both spatial and temporal dependency in a single network operation. This is made possible by equipping graph convolutions with adjacency adaptivity, which also allows for learning unknown dependencies of the human body joints. To further boost accuracy, we propose longitudinal… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 48 REFERENCES
Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time
TLDR
A novel deep neural network capable of reconstructing human full body pose in real-time from 6 Inertial Measurement Units (IMUs) worn on the user's body using a bi-directional RNN architecture is demonstrated. Expand
Discriminative Human Full-Body Pose Estimation from Wearable Inertial Sensor Data
TLDR
This paper uses Gaussian Process Regression to learn the person-specific functional relationship between the sensor measurements and full-body pose, and proposes a SVM-based scheme to classify the activities based on inertial sensor data. Expand
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
TLDR
A novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. Expand
Semantic Graph Convolutional Networks for 3D Human Pose Regression
TLDR
The proposed Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data that learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. Expand
Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs
TLDR
This work addresses the problem of making human motion capture in the wild more practical by making use of a realistic statistical body model that includes anthropometric constraints and using a joint optimization framework to fit the model to orientation and acceleration measurements over multiple frames. Expand
STAR: Sparse Trained Articulated Human Body Regressor
TLDR
This work defines per-joint pose correctives and learns the subset of mesh vertices that are influenced by each joint movement that results in more realistic deformations and significantly reduces the number of model parameters to 20% of SMPL. Expand
Outdoor human motion capture using inverse kinematics and von mises-fisher sampling
TLDR
This paper introduces a novel hybrid HMC system that combines video input with sparse inertial sensor input, and proposes an efficient sampling procedure where the particles are derived analytically using inverse kinematics on the orientation cues. Expand
Human Pose Estimation from Video and IMUs
TLDR
This work proposes a hybrid tracker that combines video with a small number of inertial units to compensate for the drawbacks of each sensor type and obtains drift-free and accurate position information from video data and gets accurate limb orientations and good performance under fast motions from inertial sensors. Expand
Occlusion-Aware Networks for 3D Human Pose Estimation in Video
TLDR
This work introduces an occlusion-aware deep-learning framework that outperforms state-of-the-art methods on Human 3.6M and HumanEva-I datasets and introduces a ``Cylinder Man Model'' to approximate the occupation of body parts in 3D space. Expand
Human Pose Estimation-Based Real-Time Gait Analysis Using Convolutional Neural Network
TLDR
This work presents an approach where human pose estimation is combined with a CNN for classification between normal and abnormal gait of a human with an ability to provide information about the detected abnormalities form an extracted skeletal image in real-time. Expand
...
1
2
3
4
5
...