Title :
Optical Aberration Correction by Divide-and-Learn for Accurate Camera Calibration
Author_Institution :
Electron. Control Major, Sch. of Electron. & Electr. Eng., Daegu Univ., Gyoungsan, South Korea
Abstract :
The accuracy of three dimensional vision depends heavily on the accuracy of camera calibration. A major source of calibration error is the system nonlinearity due mainly to optical aberration. Although there are various physical models that have been employed to correct the nonlinear image distortion due to the aberration, it is uncertain practically that which model best fits a given optical system. In this paper, an intelligent learning technique to correct errors from the nonlinear optics is proposed. Data errors are first divided into small groups using k-means clustering algorithm, and an error correction function is approximated by training a small neural network that is allocated to each divided group. Compared with conventional methods, the proposed method showed higher accuracy in our tests.
Keywords :
aberrations; calibration; cameras; computer vision; distortion; error correction; learning (artificial intelligence); neural nets; pattern clustering; accurate camera calibration; calibration error; divide-and-learn; error correction function; intelligent learning technique; k-means clustering algorithm; neural network; nonlinear image distortion; optical aberration correction; three dimensional vision; Adaptive optics; Calibration; Cameras; Nonlinear distortion; Nonlinear optics; Optical distortion; Optical imaging; camera calibration; divide-and-conquer; neural networks; optical aberration; three dimensional vision;
Conference_Titel :
Computational Science and Computational Intelligence (CSCI), 2014 International Conference on
Conference_Location :
Las Vegas, NV
DOI :
10.1109/CSCI.2014.37