RT info:eu-repo/semantics/article
T1 Model-based real-time non-rigid tracking
A1 Bronte Palacios, Sebastián
A1 Bergasa Pascual, Luis Miguel
A1 Pizarro Pérez, Daniel
A1 Barea Navarro, Rafael
K1 NRSfM
K1 SfM
K1 Non-rigid reconstruction
K1 PTAM
K1 Tracking
K1 SfT
K1 Electrónica
K1 Electronics
AB This paper presents a sequential non-rigid reconstruction method that recovers the 3D shape and the camera pose of a deforming object from a video sequence and a previous shape model of the object. We take PTAM (Parallel Mapping and Tracking), a state-of-the-art sequential real-time SfM (Structure-from-Motion) engine, and we upgrade it to solve non-rigid reconstruction. Our method provides a good trade-off between processing time and reconstruction error without the need for specific processing hardware, such as GPUs. We improve the original PTAM matching by using descriptor-based features, as well as smoothness priors to better constrain the 3D error. This paper works with perspective projection and deals with outliers and missing data. We evaluate the tracking algorithm performance through different tests over several datasets of non-rigid deforming objects. Our method achieves state-of-the-art accuracy and can be used as a real-time method suitable for being embedded in portable devices.
PB MDPI
SN 1424-8220
YR 2017
FD 2017-09-19
LK http://hdl.handle.net/10017/43130
UL http://hdl.handle.net/10017/43130
LA eng
NO Ministerio de Economía y Competitividad
DS MINDS@UW
RD 16-abr-2024