Gesture Recognition

Late 2020, Late 2022

A gesture recognition algorithm first developed as a practice project, utilizing some graph comparison method from various academic sources, transposing them into python. Later it was applied to an interactive arts project and altered to accept full body gesture recognition.

computer-vision

python

single-reference

quick-deployment

art-application

hand-recognition

body-recognition

GitHub Model Credit

Gesture Recognition Demo

Teach the algorithm your gestures, then watch it recognize them live.

References

Reuter, M., Wolter, F.-E., & Peinecke, N. (2006). Laplace-Beltrami Spectra as "Shape-DNA" of Surfaces and Solids. Computer-Aided Design, 38(4), 342–366. doi:10.1016/j.cad.2005.10.011
Wilson, R. C. & Zhu, P. (2008). A Study of Graph Spectra for Comparing Graphs and Trees. Pattern Recognition, 41(9), 2833–2841. doi:10.1016/j.patcog.2008.03.011
von Luxburg, U. (2007). A Tutorial on Spectral Clustering. Statistics and Computing, 17(4), 395–416. arXiv:0711.0189
Zhang, F., Bazarevsky, V., et al. (2020). MediaPipe Hands: On-device Real-time Hand Tracking. CVPR Workshop on CV for AR/VR. arXiv:2006.10214
Yan, S., Xiong, Y., & Lin, D. (2018). Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. AAAI 2018. arXiv:1801.07455