6533b86efe1ef96bd12cb2d7

RESEARCH PRODUCT

Application of Genetic Algorithms to 3-D Shape Reconstruction in an Active Stereo Vision System

Albert DipandaSanghyuk WooFranck Marzani

subject

Matching (graph theory)Computer sciencebusiness.industryMachine visionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONProcess (computing)Image processingIterative reconstructionSet (abstract data type)StereopsisGenetic algorithmComputer visionArtificial intelligencebusiness

description

In this paper, a new method for reconstructing 3-D shapes is proposed. It is based on an active stereo vision system composed of a camera and a light system which projects a set of structured laser rays on the scence to be analyzed. The depth information is provided by matching the laser rays and the corresponding spots appearing in the image. The matching task is performed by using Genetic Algorithms (GAs). The process converges towards the optimum solution which proves that GAs can effectively be used for this problem. An efficient 3-D reconstruction method is introduced. The experimental results demonstrate that the proposed approach is stable and provides high accuracy 3-D object reconstruction.

yearjournalcountryeditionlanguage
2001-01-01
https://doi.org/10.1007/3-540-44745-8_32