Adaptive implicit-Camera Calibration in photogrammetry using Anfis


Besdok E., Civicioglu P.

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS, cilt.4251, ss.606-613, 2006 (SCI-Expanded) identifier

Özet

Camera Calibration (CC) is required in many Photogrammetry and Computer-Vision applications, where 3D information is extracted from images and CC is also employed for pose determination of imaging sensors. In this paper, a novel implicit-CC model (ICC) based on Adaptive Neuro Fuzzy Inference System has been introduced. The ICC is particularly useful for back-projection in the applications that do not require internal and external camera calibration parameters in addition to the expert knowledge. The ICC supports multi-view back-projection in intelligent-photogrammetry. In this paper, the back-projection performance of the ICC has been compared with the Modified Direct-Linear-Transformation (MDLT) on real-images in order to evaluate the success of the proposed ICC. Extensive simulation results show that the ICC achieves a better performance than the MDLT in the 3D reconstruction of scene.