摘要
针对声波测井成像图噪声多、图像模糊导致的反射体自动识别困难、依赖专家识别、费时耗力等问题,提出反射体自动识别方法。通过高斯混合模型将像素点按颜色进行聚类,拆分为多通道子图,筛选有效子图进行组合;基于局部连通性进行粗降噪;以连通区域内像素点数量为基准进行精细降噪,最终完成反射体区域的像素级精确识别。整个过程完全自动化,在油田开发所用声波成像图上进行实验,实现反射体区域像素级精确识别,极大地提高了开发效率。
The acoustic logging images are quite blurry with a lot of noise,which makes the automatic detection of reflectors difficult.It is time-consuming and labor-consuming to rely on expert recognition.Therefore,a completely automatic detection process is proposed.Each pixel in the logging images was solely split into one color cluster through the Gaussian mixture model to build multi-channel sub-images.The sub-images including reflectors were combined together.The coarse noise reduction was performed based on local connectivity,and the fine noise reduction was performed based on the number of pixels in the connected area.The accurate pixel-level detection of the reflector area was completed.The entire process was fully automated.Experiments were performed on the acoustic logging images used in oil-field development.This method achieved accurate pixel-level detection of the reflector area,which greatly improved development efficiency.
作者
李昕
陈晓莹
李珊
庄春喜
李盛清
Li Xin;Chen Xiaoying;Li Shan;Zhuang Chunxi;Li Shengqing(College of Computer Science and Technology,China University of Petroleum,East China,Qingdao 266580,Shandong,China;School of Geosciences,China University of Petroleum,East China,Qingdao 266580,Shandong,China)
出处
《计算机应用与软件》
北大核心
2024年第2期222-228,共7页
Computer Applications and Software
基金
中石油重大科技项目(ZD2019-183-004)
中央高校基本科研业务费专项资金项目(20CX05019A)。
关键词
测井
声波成像图
反射体
高斯混合模型
自动识别
精确识别
Well logging
Acoustic logging image
Reflector
Gaussian mixture model
Automatic detection
Accurate detection
