A fast bottom-up approach toward three-dimensional human pose estimation using an array of cameras

• A novel fast approach for three-dimensional (3D) human pose reconstruction is proposed.
• Inspired by optical 3D reconstruction methods the proposed method opens a new framework to pose estimation.
• Reduction in computational time and complexity by using only key features.
• Easily tracking rapid variations in action.

In this paper, employing recorded images of multiple cameras, we propose a novel fast approach for three-dimensional (3D) human pose reconstruction. Opening a new framework to the pose estimation application, the proposed method is inspired by optical 3D reconstruction algorithms conventionally used for integral imaging. Thanks to the fact that the pose estimation can be carried out by using only key features of the raw recorded images, the computation time and the complexity of our method are considerably reduced. Furthermore, utilizing the here proposed algorithm, rapid variations in actions can be easily tracked. The validity of the proposed method is demonstrated by several experimental results in different postures.