Practicable camera modeling technique applying fuzzy modeling for 3D sensing based on stereo vision

Recently, the 3D sensing technique using multiple cameras has been applied to various areas such as visualization, motion capturing, and so on. However, improvement of the camera model calibration is indispensible for more precise measurement. In this study, we propose a practicable fuzzy modeling approach for 3D sensing utilizing the configuration of the stereo vision. A distance between a sensing target and the camera is used for structuring the fuzzy model for cameras considering optical projection characteristics. In our approach, the weighted least mean square error method is successfully applied considering fuzzy partition to formulate the fuzzy model. Then iterative calculations for solving the inverse problem of the camera fuzzy model are performed to attain measured coordinates. Through sensing experiments of stereo vision measurement based on the proposed approach, we showed the performance of the model was drastically improved compared with the conventional modeling approach.