【摘要】 基于二维图像的机器视觉检测技术因其高效性已经在众多领域中应用。但机器视觉检测技在检测倾斜物体的平面时,测量精度主要受其镜头和景深的限制,且难于获取精确的聚焦位置。采用满足Scheimpflug条件的移轴相机校准倾斜平面的模糊成像。经实验表明,15°～40°范围的倾斜平面重投影平均误差从0.05增至1像素,移轴相机校准后可以使重投影误差降低到0.075以下,大幅度提高了倾斜平面的成像质量。更多还原

【Abstract】 Machine vision detection technology based on two-dimensional images has been applied in many fields due to its high efficiency.However,when machine vision detection technology detects the plane of inclined objects,the measurement accuracy is mainly limited by its lens and depth of field,and it is difficult to obtain accurate focus position.In this paper,a axis-shifting camera satisfying Scheimpflug condition is used to calibrate the fuzzy imaging of inclined plane.The experimental results show that the average reprojection error of the inclined plane in the range of 15°～40° increases from 0.05 to 1 pixel,and the axis-shifting camera can reduce the reprojection error by less than 0.075,which greatly improves the imaging quality of the inclined plane.更多还原