A fast and interactive implementation for camera pose registration and 3D point reconstruction over a physical surface is described in this paper. The method (called SRE—Smart Reverse Engineering) extracts from a continuous image streaming, provided by a single camera moving around a real object, a point cloud and the cam1era’s spatial trajectory. The whole per frame procedure follows three steps: camera calibration, camera registration, bundle adjustment and 3D point calculation. Camera calibration task was performed using a traditional approach based on 2-D structured pattern, while the Optical Flow approach and the Lucas-Kanade algorithm was adopted for feature detection and tracking. Camera registration problem was then solved thanks to the Essential Matrix definition. Finally a fast Bundle Adjustment was performed through the Levenberg-Marquardt algorithm to achieve the best trade-off between 3D structure and camera variations. Exploiting a PC and a commercial webcam, an experimental validation was done in order to verify precision in 3D data reconstruction and speed. Practical tests helped also to tune up several optimization parameters used to improve efficiency of most CPU time consuming algorithms, like Optical Flow and Bundle Adjustment. The method showed robust results in 3D reconstruction and very good performance in real-time applications.

Real-time 3D features reconstruction through monocular vision

Alfredo LIVERANI;
2010

Abstract

A fast and interactive implementation for camera pose registration and 3D point reconstruction over a physical surface is described in this paper. The method (called SRE—Smart Reverse Engineering) extracts from a continuous image streaming, provided by a single camera moving around a real object, a point cloud and the cam1era’s spatial trajectory. The whole per frame procedure follows three steps: camera calibration, camera registration, bundle adjustment and 3D point calculation. Camera calibration task was performed using a traditional approach based on 2-D structured pattern, while the Optical Flow approach and the Lucas-Kanade algorithm was adopted for feature detection and tracking. Camera registration problem was then solved thanks to the Essential Matrix definition. Finally a fast Bundle Adjustment was performed through the Levenberg-Marquardt algorithm to achieve the best trade-off between 3D structure and camera variations. Exploiting a PC and a commercial webcam, an experimental validation was done in order to verify precision in 3D data reconstruction and speed. Practical tests helped also to tune up several optimization parameters used to improve efficiency of most CPU time consuming algorithms, like Optical Flow and Bundle Adjustment. The method showed robust results in 3D reconstruction and very good performance in real-time applications.
Alfredo, Liverani; Francesco, Leali; Marcello, Pellicciari
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/100051
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? ND
social impact