计算机与数字工程2019，Vol.47Issue(12)：3041-3044,3058,5.DOI:10. 3969/j. issn. 1672-9722. 2019. 12. 020
基于分块的帧差法和混合高斯算法的油田作业区入侵检测
Intrusion Dection in Oilfield Operation Area Based on Block Three Frame Difference and Gaussian Mixture Modeling Algorithm
摘要
Abstract
In view of the problem of real-time monitoring of illegal intrusion in oilfield telephoto operation area,a mixed Gauss model algorithm,which combines image rules partitioning with three frame difference method and adaptive background updat?ing is proposed. First of all,it is image rules partitioning,and then the adjacent frame sub block extracts the intrusion target rough contour of block by three frame difference method. The results of the set threshold and frame difference block are compared to judge invasion target and background blocks. Finally the adaptive updating mixed Gauss model algorithm for the intrusion target blocks is put to use,calculating the results of blocks frame difference and background difference,and the final invasion target is got.Through the video series detection,the experiments show that the algorithm is suitable for the oilfield telephoto operation area and can com?pletely extract the invading target and meet the actual demand. What's more it is good in real-time and robustness.关键词
图象规则分块/相邻帧子块帧差法/自适应更新/混合高斯模型Key words
image rule block/three frame difference method of blocking/adaptive updating/mixed Gaussian model分类
信息技术与安全科学引用本文复制引用
龚安,牛博,史海涛..基于分块的帧差法和混合高斯算法的油田作业区入侵检测[J].计算机与数字工程,2019,47(12):3041-3044,3058,5.基金项目
国家油气重大专项(编号:2017ZX05013-001)资助. （编号:2017ZX05013-001）
