Camera Calibration Optimization Algorithm Based on Nutcracker Optimization Algorithm

Camera calibration is a core task in computer vision. Traditional calibration methods usually achieve approximate solutions due to the complexity of solving nonlinear equations, resulting in reprojection errors. This article proposes a camera calibration optimization algorithm based on the Starling-Inspired Strategy optimization algorithm, which improves calibration accuracy and stability by combining chaotic mapping and sine cosine optimization strategies. First, we constructed a real camera calibration image dataset that includes various calibration scenarios and calculated the initial values of camera calibration parameters based on Zhang's calibration method. Then, we established a reprojection error model to evaluate the accuracy of the calibration parameters. Finally, we reduced the reprojection error through a hybrid optimization method based on the Steller Jay optimization algorithm. Experimental results show that our algorithm significantly reduces the reprojection error and improves the camera calibration accuracy.