Automatic 3D model reconstruction using voxel coding and pose integration

摘要

Automatic reconstruction of a complete 3D model of a complex object is presented. The complete 3D model is reconstructed by integrating two 3D models which are reconstructed from different poses of the object. For each pose of the object, a 3D model is reconstructed by combining stereo image analysis, shape from silhouettes, and a volumetric integration technique. Stereo image analysis and shape from silhouettes techniques complement each other to reconstruct an accurate and noise-resistant 3D model. For a reliable volumetric integration of multiple partial shapes, a voxel coding technique is introduced. The voxel coding technique facilitates a selection of consistent partial shapes for shape integration. In order to reconstruct all visible surfaces of a complex object with concavities and holes, two 3D models from different poses of the object are reconstructed and integrated to obtain the complete 3D model. A voxel coding technique is again used during pose integration. Experimental results on a real object demonstrate that our approach has advantages and is effective.