Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests

By Leandro Miranda, Thales Vieira, Dimas Martínez Morera, Thomas Lewiner, Antônio Wilson Vieira, Mario Fernando Montenegro Campos. 2012

89 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, 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. Fei Han
2. Hao Zhang
3. William A. Hoff
4. Brian Reily
5. Guo-qing Guo
6. Wenbin Chen
7. Y. Zhu
8. Pau Climent-Pérez

In Control and Systems Engineering

1. Pau Climent-Pérez
2. José Ramón Padilla-López
3. Francisco Flórez-Revuelta
4. William A. Hoff
5. Brian Reily
6. Fei Han
7. Y. Zhu
8. J. Laviola

In Human-Computer Interaction

1. Guo-qing Guo
2. Wenbin Chen
3. Fei Han
4. Hao Zhang
5. Y. Zhu
6. Pau Climent-Pérez
7. José Ramón Padilla-López
8. Francisco Flórez-Revuelta

Citations in the corpus

• Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Many other existing human representations are also based on low-level skeleton-based features [117], [118], [119], [123], [134], [139], [140], [141], [154], [157], [158], [162], [200] without modeling the hierarchy of the data.”
• Fusing Spatiotemporal Features and Joints for 3D Action Recognition (2013, methodology): “Similarly, Miranda et al. [11] used the pose descriptor in a torso-based coordinate system and the SVM classifier to learn key poses and a decision forest is used to recognize the action classes.”
• 3D Gestural Interaction: The State of the Field (2013, background): “[109] Decision forest with key pose learning 10 91.”
• Evolutionary joint selection to improve human action recognition with RGB-D devices (2014, methodology): “(L2-norm) (Azary & Savakis, 2012) 76.60% 75.61% 89.47% 80.56% Keyposes and Decision Forests (Miranda et al., 2012) 93.5% 52% 95.4% 80.30% Histograms of 3D Joints (Xia et al., 2012) 87.98% 85.48% 63.46% 78.97% Bag of 3D Points (Li et al., 2010) 72.9% 71.9% 79.2% 74.67% Bag of key poses and DTW…”
• Fusing Multiple Features for Depth-Based Action Recognition (2015, background): “0% Key Pose Learning [Miranda et al. 2012] 80.”
• A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, methodology): “For example, Miranda et al. [59] perform a random selection of half of the actors as training set and the other half as validation set.”