A method of circle detection using multi-sector based is put forward on OpenCV, for the demand of machine vision in industrial practice and assembly line.A brief introduction of OpenCV is given firstly, the principle of this circle detection and the detection steps are described in detail.The experimental results show that detect circles correctly in a higher interference.Compared with Randomized Hough Transform (RHT), This method has higher detection rate and has lower computational overhead.%针对工业控制现场和生产流水线上对机器视觉的需求,提出了一种基于OpenCV的多扇区圆检测方法.首先对OpenCV做了简单介绍,给出了多扇区圆检测的原理与检测步骤,然后经过实验表明,在较高的干扰下仍能将圆形准确无误的检测出来,与随机Hough变换相比,有较高的识别准确率和较小的计算开销.
展开▼