3D Foot Reconstruction from image sequence

In this paper, a new method is proposed for 3D foot reconstruction using video captured by mobile phone. This method is addressed with the Scale-Invariant Feature Transformation followed by feature matching to generate consistent tracks. These tracks are further processed to generate3D points in terms of structure-from-motion. The accuracy of the proposed method is evaluated by comparing the difference between traditional measurements and 3D model measurements. The experiment result proves that a 3D foot model can be generated via this simple and efficient approach, and the accuracy is sufficient for foot measurement.