FastHand: Fast monocular hand pose estimation on embedded systems

@article{An2021FastHandFM,
  title={FastHand: Fast monocular hand pose estimation on embedded systems},
  author={Shan An and Xiajie Zhang and Dong Wei and Haogang Zhu and Jianyu Yang and Konstantinos A. Tsintotas},
  journal={J. Syst. Archit.},
  year={2021},
  volume={122},
  pages={102361}
}
[PDF] Semantic Reader
2 Citations

Figures and Tables from this paper

2 Citations

VTONShoes: Virtual Try-on of Shoes in Augmented Reality on a Mobile Device

This paper proposes an efficient framework to detect, classify, and recover 6-DoF pose of shoes from the captured images and then accurately render the 3D shoe model on the screen in realtime and in full degrees of freedom.

Joint-Aware Action Recognition for Ambient Assisted Living

This work exploits state-of-the-art data-driven classifiers and compares their efficiency in action recognition based on a specific set of joints or coordinates, i.e., the x, y and z-axis, and investigates the capacity of such a joint analysis and its ability to deliver an enhanced pose-based action recognition system.

References

SHOWING 1-10 OF 45 REFERENCES

Large-scale Multiview 3D Hand Pose Dataset

SRHandNet: Real-Time 2D Hand Pose Estimation With Simultaneous Region Localization

A novel method for real-time 2D hand pose estimation from monocular color images, which is named as SRHandNet, to simultaneously regress the hand region of interests and hand keypoints for a given color image, and iteratively take the hand RoIs as feedback information for boosting the performance of hand key points estimation with a single encoder-decoder network architecture.

Attention! A Lightweight 2D Hand Pose Estimation Approach

This article presents a novel Convolutional Neural Network architecture, reinforced with a Self-Attention module, which can be deployed on an embedded system due to its lightweight nature with just 1.9 Million parameters.

Learning to Estimate 3D Hand Pose from Single RGB Images

A deep network is proposed that learns a network-implicit 3D articulation prior that yields good estimates of the 3D pose from regular RGB images, and a large scale 3D hand pose dataset based on synthetic hand models is introduced.

GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB

This work proposes a novel approach for the synthetic generation of training data that is based on a geometrically consistent image-to-image translation network, and uses a neural network that translates synthetic images to "real" images, such that the so-generated images follow the same statistical distribution as real-world hand images.

Hand Pose Estimation via Latent 2.5D Heatmap Regression

This paper proposes a new method for 3D hand pose estimation from a monocular image through a novel 2.5D pose representation that implicitly learns depth maps and heatmap distributions with a novel CNN architecture.

3D Hand Pose Estimation from Single Depth Images with Label Distribution Learning

  • Yuanfei XuXupeng Wang
  • Computer Science
    2020 IEEE International Conference on Embedded Software and Systems (ICESS)
  • 2020
A deep regression network is proposed, which learns the hand feature space from the point cloud and includes a specific label distribution learning network that achieves the state-of-the-art performance on MSRA dataset.

Robust 3 D Hand Pose Estimation From Single Depth Images Using MultiView CNNs

A novel multi-view convolutional neural network (CNN)-based approach for 3D hand pose estimation that is superior to the state-of-the-art methods on two challenging data sets and validates that the proposed approach has good generalization ability.

Robust 3D Hand Pose Estimation From Single Depth Images Using Multi-View CNNs

A novel multi-view convolutional neural network (CNN)-based approach for 3D hand pose estimation that is superior to the state-of-the-art methods on two challenging data sets and validates that the proposed approach has good generalization ability.

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images

This paper introduces the first large-scale, multi-view hand dataset that is accompanied by both 3D hand pose and shape annotations and proposes an iterative, semi-automated `human-in-the-loop' approach, which includes hand fitting optimization to infer both the 3D pose andshape for each sample.