【摘要】 为提高螺栓连接的检测效率，充分利用计算机视觉高效方便等特点，提出一种基于计算机视觉的螺栓松动角度测量方法.该方法包括图像获取、图像预处理、边缘检测和直线识别、角度计算四步.首先获取螺栓图像，用透视变换和图像灰度化技术对图像预处理，然后用Canny边缘检测算法检测边缘和Hough变换识别边缘直线，最后计算螺栓角度.设计了一个螺栓模型验证该方法的可行性，实验结果表明，该方法可以高效准确识别5°以上的螺栓松动，且最大误差仅为5%,满足实际工程精度要求，具有良好应用前景.更多还原

【Abstract】 In order to improve the detection efficiency of bolt connections and make full use of the efficiency and convenience of computer vision, a method for measuring bolt loosening angle based on computer vision is proposed, which includes four steps: image acquisition, image preprocessing, edge detection and line recognition, and angle calculation. Firstly, the bolt image is acquired, the image is preprocessed with perspective transformation and image grayscale. Then, the edge is detected by Canny edge detection algorithm and straight line is recognized by Hough transform. Finally, the bolt angle is calculated. A bolt model is designed to verify the feasibility of the method, and the experimental results show that the method can efficiently and accurately recognize the bolt looseness above 5°, with a maximum error of only 5%, which meets the accuracy requirements of actual engineering and has good application prospects.更多还原