【摘要】 在许多流体对象工业生产场合，普遍存在着装液步骤。液面与容器顶端的距离反映出了容器内液体的体积和深度信息，对生产流程的判别有着重大意义。传统的液面高度检测大多采用内嵌传感器，这些传感器需要深入到容器内部，日积月累的腐蚀会导致其检测偏差甚至失效。考虑到容器大多是各方受力均匀的圆柱体，故从容器俯侧视图观测，液面与容器顶部都呈椭圆形边缘。采用数字相机对容器俯侧视角进行拍摄，并进行图像处理，得其边缘图信息，利用椭圆拟合算法得出液面和容器顶部椭圆模型参数，计算两个椭圆在同短轴方向上的高度差，即可得出液面和容器顶部之间的距离。更多还原

【Abstract】 In many industrial production occasions of fluid object, there is a common liquid loading step. The distance between the liquid level and the top of the container reflects the volume and depth of the liquid in the container, which is of great significance to the identification of the production process. Traditional liquid level detection mostly uses embedded sensors,these sensors need to go deep into the container, the accumulated corrosion will lead to the detection deviation or even failure.Considering that most of the containers are cylinders with uniform force on all sides, the liquid level and the top of the container are elliptical edges from the top view of the container. The digital camera is used to capture the angle of view of the container from the downward side, and the image processing is carried out to obtain the edge image information. The ellipse fitting algorithm is used to obtain the model parameters of the liquid level and the top of the container, and the height difference of the two ellipses in the direction of the same minor axis is calculated to obtain the distance between the liquid level and the top of the container.更多还原