Research Of Counting Methods About Oil-pipes In The Process Of Oil Exploitation

This paper is a practical research project of oil-pipes’counting in LiaoHe oil-field. I have proposed technical methods on counting of oil-pipes. I have done much research on digital image processing, splice, fusion and tubing count recognition. And I have found reasonable solutions on this problem, and realized accurate counting of oil-pipes.In the image processing parts, I have researched the image enhancement and morphological transformation. I have also researched the edge detection algorithms, such as Roberts operator, Sobel operator, Prewitt operator, Krisch operator and Gauss-Laplace operator.In the part of image splice and fusion, this paper use three set of line scanning camera to get the tubing end image, and facus on the contrasted of MORAVEC operator, HARRIS operator and Sift operator. After considering these operators, I have employ Sift operators to detect feature points, and using the method of coming into and get out gradually to join the image together. In the round recognition and counting, this paper used the improved Hough transform, and obtain circles’center coordinates and round radius.In the part of tubing counting, this paper has added OpenCV to provide image detection, image processing library, which could realize very rich functionality. And it has realized image processing and computer vision in many common algorithm. And finally it will cooperate Vb.net and VC++together, which will achieved the count of tubing.Furthermore, in this paper, a large numbers of experiments have been done about the system, which includes a variety of contrast experiment on different conditions. These experiments show that through the reasonable choose of light source, reasonable camera position and efficient arrangement image matching algorithm, and finally achieved the count of tubing.