Incremental Learning Method for Unified Camera Calibration

Abstract

AbstractThe camera model could be approximated by a set of linear models defined on a set of local receptive fields regions. Camera calibration could then be a learning procedure to evolve the size and shape of every receptive field as well as parameters of the associated linear model. For a multi-camera system, its unified model is obtained from a fusion procedure integrated with all linear models weighted by their corresponding approximation measurements. The 3-D measurements of the multi-camera vision system are produced from a weighted regression fusion on all receptive fields of cameras. The resultant calibration model of a multi-camera system is expected to have higher accuracy than either of them. Simulation and experiment results illustrate effectiveness and properties of the proposed method. Comparisons with the Tsai’s method are also provided to exhibit advantages of the method.KeywordsWeighted RegressionCorner PointReconstruction ErrorCamera CalibrationIncremental LearnThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.