소수 데이터의 신경망 학습에 의한 카메라 보정
Camera Calibration Using Neural Network with a Small Amount of Data
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
When a camera is employed for 3D sensing, accurate camera calibration is vital as it is a prerequisite for the subsequent steps of the sensing process. Camera calibration is usually performed by complex mathematical modeling and geometric analysis. On the other contrary, data learning using an artificial neural network can establish a transformation relation between the 3D space and the 2D camer image without explicit camera modeling. However, a neural network requires a large amount of accurate data for its learning. A significantly large amount of time and work using a precise system setup is needed to collect extensive data accurately in practice. In this study, we propose a two-step neural calibration method that is effective when only a small amount of learning data is available. In the first step, the camera projection transformation matrix is determined using the limited available data. In the second step, the transformation matrix is used for generating a large amount of synthetic data, and the neural network is trained using the generated data. Results of simulation study have shown that the proposed method as valid and effective.
Abstract
When a camera is employed for 3D sensing, accurate camera calibration is vital as it is a prerequisite for the subsequent steps of the sensing process. Camera calibration is usually performed by complex mathematical modeling and geometric analysis. On the other contrary, data learning using an artificial neural network can establish a transformation relation between the 3D space and the 2D camer image without explicit camera modeling. However, a neural network requires a large amount of accurate data for its learning. A significantly large amount of time and work using a precise system setup is needed to collect extensive data accurately in practice. In this study, we propose a two-step neural calibration method that is effective when only a small amount of learning data is available. In the first step, the camera projection transformation matrix is determined using the limited available data. In the second step, the transformation matrix is used for generating a large amount of synthetic data, and the neural network is trained using the generated data. Results of simulation study have shown that the proposed method as valid and effective.
참고문헌 (13)
- T. Jadhav, "Volumetric estimation using 3D reconstruction method for grading of fruits", Multimed. Tools Appl., 78(2), pp.1613~1634 (2019)
- R. Tsai, "A versatile camera calibration technique for highaccuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses", IEEE J. Robot. Autom., 3(4), pp.323~344 (1987)
- L. Song, "Survey on camera calibration technique", Proc. IEEE Int. Conf. Intell. Hum. Mach. Syst. Cybern. (2013)
- Q. Wang, "Review on camera calibration", Proc. Chin. Control Decis. Conf., pp.3354~3358 (2010)
- S. Walczak, "Advanced Methodologies and Technologies in Artificial Intelligence, Computer Simulation, and Human-Computer Interaction", pp.40-532018~ (2018), IGI Global
- D. -M. Woo, "An efficient method for camera calibration using multilayer perceptron type neural network", Proc. Int. Conf. Future Comput. Commun., pp.358~362 (2009)
- J. Xiong, "A novel method of stereo camera calibration using BP neural network", Appl. Mech. Mater., 29-32, pp.2692~2697 (2010)
- Q. Memon, "Camera calibration and threedimensional world reconstruction of stereo-vision using neural networks", Int. J. Syst. Sci., 32(9), pp.1155~1159 (2001)
- B. Chen, "Stereo vision calibration based on GMDH neural network", Appl. Opt., 51(7), pp.841~845 (2012)
- X. Chen, "The research of camera distortion correction based on neural network", Proc. Chin. Control Decis. Conf., pp.596~601 (2011)
- Y. Do, "Camera calibration where practical uncertainties exist in camera model and calibration data", Proc. IEEE Conf. Mechatron. Mach. Vis. Pract., pp.491~495 (2001)
- Y. Do, "Neural camera calibration using a limited number of data", Proc. Korean Sens. Soc. Conf., 29, pp.217~ (2018)
- M. T. Hagan, "Training feedforward networks with the Marquardt algorithm", IEEE Trans. Neural Netw., 5(6), pp.989~993 (1994)