IOSR Journal of Mechanical and Civil Engineering (IOSR-JMCE) e-ISSN: 2278-1684,p-ISSN: 2320-334X, Volume 13, Issue 1 Ver. IV(Jan. - Feb. 2016), PP 17-23 www.iosrjournals.org DOI: 10.9790/1684-13141723 www.iosrjournals.org 17 | Page Optimum Design For Close Range Photogrammetry Network Using Particle Swarm Optimization Technique Saad El-Hamrawy 1 , Hossam El-Din Fawzy 2 Mohamed Al-Tobgy 3 1 professor of Highway Engineering, Civil Engineering Department, Faculty of Engineering, Shebin El- Kom, Minufiya University, Egypt; 2 Lecturer, Civil Engineering Department, Faculty of Engineering, Kafr El-Sheikh University, Kafr El- Sheikh, Egypt; 3 Research and Teaching Assistant, Civil Engineering Department, Faculty of Engineering, Kafr El-Sheikh University, Kafr El-Sheikh, Egypt; Abstract: With the rapid development in close range photogrammetry and low cost of this technique, it is important to improve the accuracy of the result of this technique. For that, the main aim of that paper is using the Particle Swarm Optimization. The mathematical model of Particle Swarm Optimization for the close range photogrammetry network is developed. The experimental tests have been carried out to develop a Particle Swarm algorithm to determine the optimum camera station and evaluate the accuracy of the developed. Keywords: Close range photogrammetry network design, artificial intelligence and Particle Swarm Optimization. I. Introduction Close-range stereo photogrammetry is an accurate method of recording 3-D information about an object that results as well in an archival, high-resolution photographic base record of the object. We obtain highly accurate measurements through one of these networks. Close range photogrammetry network design has been divided into four design stages from which only the first three are used in close range photogrammetry[1].  Zero Order Design (ZOD): The datum problem – involves the choice of an optimal reference system for parameters and their variance-covariance matrix.  First Order Design (FOD): The configuration problem – involves the optimal positioning of points and the design of an optimal observation plan.  Second Order Design (SOD): The weight problem – involves the identification of optimal precision and distribution of observation.  Third Order Design (TOD): The densification problem – involves the optimal improvement of an existing network via the addition of observation or points. The order presented above is not fixed, although it is accepted by most geodesist and photogrammetrists as the chronological order for assisting network design problems. In practice the design problems are interrelated and solution of the various design problems may occur in different sequence. For example, addition of object points may be carried out in the FOD phase to strengthen the image configuration, however this process is essentially a TOD (densification) problem. It should be noted that the datum problem is not independent of the configuration problem. A change in the datum will influence the object point precision and the magnitude of such changes is dependent upon the imaging geometry. Hence, perior to evaluation of the datum definition, a good estimate of imaging geometry should be available. If, after the ZOD analysis, then the effect of such changes upon the datum definition should be determined, i.e. repeat the datum definition. In the design of close range photogrammetric network, the accuracy of the various solutions, with respect to the datum definition and imaging geometry, etc., is assessed on the assumption that only random errors are present on observations. In other words, the effect of the network, and only the network, upon estimates of the parameters is assessed. In such a case, where observations do not include systematic and gross errors, precision rather than accuracy estimates are required. [2] The close range photogrammetric network design is the process of optimizing a network configuration in terms of the accuracy of object-points. This design stage must provide an optimal imaging geometry and convergence angle for each set of points placed over a complex object. [3] II. Heuristic Optimization Algorithms Optimization has been an active area of research for several decades. As many real world optimization problems become increasingly complex, better optimization algorithms are always needed. Recently, meta- heuristic global optimization algorithms have become a popular choice for solving complex and intricate problems, which are otherwise difficult to solve by traditional methods [4]. The objective of optimization is to