AUTOMATED PHOTOGRAMMETRIC NETWORK DESIGN USING GENETIC ALGORITHMS

The process of placing cameras in order to perform photogrammetric tasks is called photogrammetric network design, and an important aspect in planning is to achieve an optimal spatial distribution of the network cameras. This paper describes the automation of the photogrammetric network design process thorough the use of genetic algorithms. Cameras should be placed in order to satisfy a set of interrelated and competing constraints when planning a photogrammetric network. Furthermore, when the object is three-dimensional, a combinatorial problem occurs. Genetic algorithms are stochastic optimization techniques, which have proved useful for solving computationally difficult problems with high combinatorial results. EPOCA (Evolving Positions of Cameras), the system based on genetic algorithms, was implemented using a three-dimensional computer-aided design interface. The system provides the attitude of each camera in the network, taking into account the imaging geometry, as well as several major constraints such as visibility, convergence angle, and workspace constraint. EPOCA is capable of producing configurations reported in the photogrammetric literature. It can also design networks for several adjoining planes and complex objects with good configurations in terms of the camera distribution and ray inclination.