Fusion of combined stereo and spectral series for obtaining 3D information
Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications, Proceedings of SPIE 6974, 2008.
SPIE Defense and Security: Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications, Orlando, Florida, USA, March 16 - 20, 2008
This contribution presents a fusion method for combined stereo and spectral series gained with a camera array with the main purpose of obtaining 3D information. In order to register the images, regions are used as invariant elements with respect to varying gray values. The approach uses their characteristics like size, position and shape for registration. The regions are identified employing the watershed transformation. The fusion problem is modeled with energy functionals that are to be optimized. Using the implemented algorithm, several scenes have been reconstructed. The experimental results show that the proposed method delivers reliable and accurate dense depth maps.