论文部分内容阅读
针对标准遗传算法在摄像机标定参数非线性优化过程中,易出现过早收敛和停滞现象的问题,提出一种新的摄像机标定参数优化方法。首先,采用非线性的归一化几何排名函数与随机遍历抽样法混合作为选择方法,对遗传算法进行改进;然后,采用改进的遗传算法对摄像机标定参数进行非线性优化;最后,将其与标准遗传算法进行标定参数非线性优化对比实验,实验结果表明:算法平均绝对误差低于标准遗传算法,且图像主点坐标更接近参考值,能较好地缓解过早收敛和停滞现象,提高了标定精度。
Aiming at the problem of premature convergence and stagnation of standard genetic algorithm (GA) in the process of nonlinear calibration of camera calibration parameters, a new method of camera calibration parameters optimization is proposed. Firstly, the non-linear normalized geometric ranking function and random traversal sampling method are used as the selection method to improve the genetic algorithm. Then, the improved genetic algorithm is used to optimize the calibration parameters of the camera. Finally, The experimental results show that the average absolute error of the algorithm is lower than that of the standard genetic algorithm, and the coordinate of the main point of the image is closer to the reference value, which can better alleviate the phenomenon of premature convergence and stagnation and improve the calibration Accuracy.