Ooid characteristic extraction mathod of carbonate rocks based on superpixel image segmentation algorithm
JIANG Liwei1, LIU Di2, ZHANG Yang1, ZHANG Yunying1, TAO Zhi1
1. Artificial Intelligence Research Center of China Petroleum Exploration and Development Research Institute, Beijing 10083; 2. Geophysical Technology Research Center, BGP Inc., CNPC, Zhuozhou, Hebei 072751, China
Abstract:Carbonate rocks are a crucial reservoir for oil and gas. The identification of thin section characteristics of carbonate rocks often relies heavily on manual annotation,which is time-consuming and subjective. With the rapid development of machine learning and other technologies,converting existing images into digital images for segmentation,classification,and feature extraction can efficiently improve research and reduce costs. Thus,two me-thods are compared and studied for extracting ooid characteristic of carbonate rocks. One method is based on traditional image segmentation processing algorithms,and the other is based on SLIC superpixel segmentation algorithms. The experimental results show that the superpixel segmentation algorithm has advantages over traditional segmentation algorithms in terms of accuracy,extraction rate,and other aspects.
李景霞,张立新,杨丽.矿物岩石学[M].四川成都:电子科技大学出版社,2014. LI Jingxia,ZHANG Lixin,YANG Li.Mineralogy and Petrology[M].China Press University of Electronic Science & Technology,Chengdu,Sichuan,2014.
[2]
钱一雄,何治亮,陈代钊,等. 塔北埃迪卡拉系奇格布拉克组多类型共生鲕粒特征及其成因探讨[J].古地理学报,2023,25(1): 5674. QIAN Yixiong,HE Zhiliang,CHEN Daizhao,et al. Characteristics and genesis of various oolites in the Ediacaran Qigebulake formation in northern Tarim basin[J].Journal of Palaeogeography,2023,25(1): 56-74.
[3]
刘烨,吕锦涛. 基于超像素与半监督的岩石图像分割与识别[J].工程科学与技术,2023,55(2): 171-183. LIU Ye,LYU Jintao. Semisupervised rock image segmentation and recognition based on superpixel[J].Advanced Engineering Sciences,2023,55(2): 171-183.
[4]
叶榆,程超,蒋裕强,等. 川东飞仙关组鲕粒滩岩性识别及其分布特征[J/OL].沉积学报: 120
[20230605].https:∥doi.org/10.14027/j.issn.10000550.2022.089. YE Yu,CHENG Chao,JIANG Yuqiang,et al. Lithological identification and distribution characteristics of oolitic beach in Feixianguan Formation,eastern Sichuan[J].Acta Sedimentologica Sinica: 120
芦盛玉,钟志,蔡忠贤,等.基于卷积神经网络的碳酸盐岩岩相预测[C].2020年中国地球科学联合学术年会论文集,2020,5961. LU Shengyu,ZHONG Zhi,CAI Zhongxian,et al. Carbonate rock facies prediction based on convolutional neural network[C].Proceedings of the 2020 China Earth Science Joint Academic Annual Conference,2020,5961.
[6]
余晓露,叶恺,杜崇娇,等. 基于卷积神经网络的碳酸盐岩生物化石显微图像识别[J].石油实验地质,2021,43(5): 880885,895. YU Xiaolu,YE Kai,DU Chongjiao,et al. Microscopic recognition of micro fossils in carbonate rocks based on convolutional neural network[J].Petroleum Geology and Experiment,2021,43(5): 880885,895.
[7]
白林,魏昕,刘禹,等. 基于VGG模型的岩石薄片图像识别[J].地质通报,2019,38(12): 20532058. BAI Lin,WEI Xin,LIU Yu,et al. Rock thin section image recognition and classification based on VGG model[J].Geologcal Bulletin of China,2019,38(12): 20532058.
[8]
张安定.遥感原理与应用题解[M].北京: 科学出版社,2016. ZHANG Anding. Explanation of Principles and Applications of Remote Sensing[M].Science Press,Beijing,2016.