基于主动学习的油气管道沿线地物变化检测(4)
表1 不同变化检测算法的精度Table 1 Accuracy of different change detection methods算法总体精度Kappa系数虚检率漏检率误检像元 70.463 20.446 90.515 84 50.496 10.245 20.587 037 40.496 80.282 70.571 238 70.539 50.239 00.536 035 448本文方法0.947 70.703 60.197 90.326 225 608
3 结论
针对油气管道外界环境越来越复杂、外界环境变化引起的油气管道泄漏事故频发等现象,研究了基于卫星遥感的油气管道沿线地物变化检测算法。为综合利用非监督变化检测和监督变化检测各自的优点,在提高变化检测的自动化程度减少训练样本标注成本的同时,提高变化检测的精度。构建了基于主动学习的半监督变化检测算法,在该算法结构中,为了充分利用分类器挖掘信息的能力,利用GBDT、kNN和ET构建了分类器集成结构,并且利用边缘采样的主动学习方法进行训练样本的增选。通过实验结果可知,该变化检测框架在减少训练样本标注的同时,提高了变化检测的精度,可以有效检测油气管道沿线地物变化情况。为了验证算法的有效性,利用两景基于ZY-3影像的融合后高分辨率遥感影像进行实验,通过对比实验结果可知本文构建的变化检测算法不仅减少了训练样本标注成本,而且精度优于其他方法。
1 曲志刚, 封 皓, 靳世久, 等. 基于支持向量机的油气管道安全监测信号识别方法[J]. 天津大学学报, 2009, 42(5): 465-470.
Qu Zhigang, Feng Hao, Jin Shijiu, et al. An SVM-based recognition method for safety monitoring signals of oil and gas pipeline[J]. Journal of Tianjin University, 2009, 42(5): 465-470.
2 杜 慧. 基于SVM的多特征自适应融合变化检测[J]. 测绘与空间地理信息, 2019, 42(6): 149-152.
Du Hui. Multi-feature adaptive fusion detection based on SVM[J]. Geomatics & Spatial Information Technology, 2019, 42(6): 149-152.
3 杨 俨. 资源三号卫星遥感影像城市地表覆盖分类方法研究[D]. 重庆: 西南大学, 2016.
Yang Yan. Study on method of urban area land cover classification based on ZY-3[D]. Chongqing: Southwest University, 2016.
4 张良培, 武 辰. 多时相遥感影像变化检测的现状与展望[J]. 测绘学报, 2017, 46(10): 1447-1459.
Zhang Liangpei, Wu Chen. Advance and future development of change detection for multi-temporal remote sensing imagery[J]. Acta GeodaeticaetCartographica Sinica, 2017, 46(10): 1447-1459.
5 Xiao P F, Zhang X L, Wang D G, et al. Change detection of built-up land: a framework of combining pixel-based detection and object-based recognition[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2016, 119: 402-414.
6 张 伟, 郑 柯, 唐 娉, 等. 深度卷积神经网络特征提取用于地表覆盖分类初探[J]. 中国图象图形学报, 2017, 22(8): 1144-1153.
Zhang Wei, Zheng Ke, Tang Ping, et al. Land cover classification with features extracted by deep convolutional neural network[J]. Journal of Image and Graphics, 2017, 22(8): 1144-1153.
7 黄 维, 黄进良, 王立辉, 等. 基于PCA的变化向量分析法遥感影像变化检测[J]. 国土资源遥感, 2016, 28(1): 22-27.
Huang Wei, Huang Jinliang, Wang Lihui, et al. Remote sensing image change detection based on change vector analysis of PCA component[J]. Remote Sensing For Land & Resources, 2016, 28(1): 22-27.
8 Peng D F, Zhang Y J. Object-based change detection method using refined Markov random field[J]. Journal of Applied Remote Sensing, 2017, 11(1): -.
9 Wang X, Liu S C, Du P J, et al. Object-based change detection in urban areas from high spatial resolution images based on multiple features and ensemble learning[J]. Remote Sensing, 2018, 10(2): 276-289.
10 严 明, 曹 国, 夏 梦. 基于水平集演化和支持向量机分类的高分辨率遥感图像自动变化检测[J]. 哈尔滨理工大学学报, 2019, 24(1): 78-84.
Yan Ming, Cao Guo, Xia Meng. Automatic change detection of high resolution remote sensing images based on level set evolution and support vector machine classification[J]. Journal of Harbin University of Science and Technology, 2019, 24(1): 78-84.
11 赵 敏. 结合多尺度特征和主动学习的高分遥感影像变化检测[D]. 徐州: 中国矿业大学, 2018.
Zhao Min. Change detection of high resolution remote sensing imagery combining multi-scale feature and active learning[D]. Xuzhou: China University of Mining and Technology, 2018.
12 Hu T, Huang X, Li J Y, et al. A novel co-training approach for urban land cover mapping with unclear landsat time series imagery[J]. Remote Sensing of Environment, 2018, 217: 144-157.
13 赵 敏, 赵银娣. 面向对象的多特征分级CVA遥感影像变化检测[J]. 遥感学报, 2018, 22(1): 119-131.
Zhao Min, Zhao Yindi. Object-oriented and multi-feature hierarchical change detection based on CVA for high-resolution remote sensing imagery[J]. Journal of Remote Sensing, 2018, 22(1): 119-131.
文章来源:《油气储运》 网址: http://www.yqcyzz.cn/qikandaodu/2021/0222/367.html
上一篇:油气储运设备的管理、维护举措分析
下一篇:油气储运过程中仪表自动化技术的应用