A hand pose tracking benchmark from stereo matching

By Jiawei Zhang, Jianbo Jiao, Mingliang Chen, Liangqiong Qu, Xiaobin Xu, Qingxiong Yang. 2017

98 citations recorded by the source corpus.

In this paper we establish a long-term 3D hand pose tracking benchmark1. It contains 18,000 stereo image pairs as well as the ground-truth 3D positions of palm and finger joints from different scenarios. Meanwhile, to accurately segment hand from stereo images, we propose a novel stereo-based hand segmentation and depth estimation algorithm specially tailored for hand tracking here. The experiments indicate the effectiveness of the proposed algorithm by demonstrating that its tracking performance is comparable to the use of an active depth sensor under various of challenging scenarios.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Jitendra Malik
4. Jianfei Cai
5. Xiaogang Wang
6. Ming-Hsuan Yang
7. Junsong Yuan
8. Cordelia Schmid

In Human-Computer Interaction

1. Jun Liu
2. Jianfei Cai
3. Junsong Yuan
4. Liuhao Ge
5. Yujun Cai
6. Dominik Kulon
7. Mubbasir Kapadia
8. Xi Peng

Citations in the corpus

• Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks (2019, methodology): “Results on STB Dataset.”
• Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild (2020, background): “(STB) contains 15,000 training images of a single subject performing random poses and counting gestures with 5 different backgrounds and a test set of 3,000 images with the same background [59].”
• Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge (2020, methodology): “Especially, we move the root joint location from palm center to wrist of each hand in STB.”