基于光照约束的AGV视觉导引非均匀光照增强方法  

A Method for Enhancing Non-uniform Illumination of Vision-guided Automatic Guided Vehicle with Illumination Constraints

作　　者：杨旭[1] 楼佩煌[1] 武星[1] 喻俊[1] 

机构地区：[1]南京航空航天大学机电学院,南京210016

出　　处：《机械科学与技术》2013年第12期1752-1757,共6页Mechanical Science and Technology for Aerospace Engineering

基　　金：国家自然科学基金项目(61105114);江苏省科技支撑计划项目(BE2010189);江苏省六大人才高峰项目(A类)资助

摘　　要：为解决视觉导引AGV采用环形LED阵列光源照明方式时产生的非均匀光照和高光问题,提出了一种基于光照约束的图像处理方法。首先建立了远场景环形LED光源的光照模型,根据单色漫反射模板图像,采用Levenberg-marquardt法估计出光照模型的参数,再通过基于平均辐照度的归一化方法去除非均匀光照的影响,并对彩色图像中需增强的颜色色度分量进行补色以解决高光现象。实验结果表明:该方法能有效提高图像处理过程中路径特征提取的可靠性。To reduce the non-uniform illumination and high light caused by the coaxial annular LED array light used for a vision-guided automatic guided vehicle, an image processing technique for non-uniform illumination with illumination constraints is proposed. Firstly, the illumination model of the coaxial annular LED array light is estab- lished; the parameters of the model are estimated by using the nonlinear least squares Levenberg-Marquardt algo- rithm for the monochromatic diffuse reflection template image. Another method based on irradiance average normali- zation 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 our method can effectively improve the reliability of feature extraction for guide path.

关 键 词：图像处理 自动导引车 最小二乘法 光照模型 可靠性 

分 类 号：TP242.2[自动化与计算机技术—检测技术与自动化装置]