3D Modeling of Objects by Using Resilient Neural Network

Abstract

Camera Calibration (CC) is a fundamental issue for Shape-Capture, Robotic-Vision and 3D Reconstruction in Photogrammetry and Computer Vision. The purpose of CC is the determination of the intrinsic parameters of cameras for metric evaluation of the images. Classical CC methods comprise of taking images of objects with known geometry, extracting the features of the objects from the images, and minimizing their 3D backprojection errors. In this paper, a novel implicit-CC model (CC-RN) based on Resilient Neural Networks has been introduced. The CC-RN is particularly useful for 3D reconstruction of the applications that do not require explicitly computation of physical camera parameters in addition to the expert knowledge. The CC-RN supports intelligent-photogrammetry, photogrammetron. In order to evaluate the success of the proposed implicit-CC model, the 3D reconstruction performance of the CC-RN has been compared with two different well-known implementations of the Direct Linear Transformation (DLT). Extensive simulation results show that the CC-RN achieves a better performance than the well-known DLTs in the 3D backprojection of scene.