An image enhancement method for non-uniform illumination with illumination constraints for vision-guided AGV

摘要

To reduce the non-uniform illumination and high light caused by the coaxial annular LED array light used for vision-based automated guided vehicle, an image enhancement method for non-uniform illumination with illumination constraints is proposed, Firstly, the illumination model of the coaxial annular LED array light is established, the parameters of the model are estimated by using the nonlinear least squares Levenberg-Marquardt algorithm for the monochromatic diffuse reflection template image. Another method based on irradiance average normalization is proposed to remove the influence of non-uniform illumination. In order to reduce the high light, the chrominance of color image that should be enhanced is complemented. The experimental results show that the proposed method can effectively improve the robustness of image enhancement for vision guidance.