Measuring ball spin by image registration

Toru Tamaki, Takahiko Sugino, Masanobu Yamamoto

Institutional Repositories DataBase (IRDB) · 2004 · 23 citations · 5 references

Full text

Open access

Concepts

Abstract

We propose a method for measuring a spin of a ball accurately by the image registration with a 3D model. The proposed method estimates the parameters of the transformation between two images containing a known shape object with depth information. The GaussNewton method is used to minimize the residuals of intensities of the two images, and the rotation and the translation are estimated. Experimental results using real images of a spinning ball demonstrate the robustness of the proposed method.

References

5