In order to solve the problem that the edge correction effect of fish-eye image is poor, we proposed a radial de-distortion method. The mapping relationship between the distortion point and the aberration point in the image coordinate system is established by the division model based on the radial distortion. We also setup ideal pattern to extract the target position of correction. Aiming at the problem of low degree of automation and low accuracy in the process of mosaic, the integrated corner detection method is used to automatically extract the coordinate position of the corner points in the calibration pattern. Aiming at the problem that the brightness of each region is inconsistent and the transition effect is not good, the ring fusion method is designed to fuse the image. The experimental results show that the proposed algorithm has the average pixel error of 1.792, the accuracy and efficiency of corner extraction is 100%, which effectively improve the automation degree of the algorithm.
CITATION STYLE
Zhang, Y., Zhang, X., Gao, H., & Liu, Y. (2019). Image mosaic intelligent vehicle around view monitoring system based on ring fusion method. In Advances in Intelligent Systems and Computing (Vol. 760, pp. 407–418). Springer Verlag. https://doi.org/10.1007/978-981-13-0344-9_35
Mendeley helps you to discover research relevant for your work.