阮顺领;文帅;卢才武;江松;

• 1:西安建筑科技大学管理学院
• 2:西安市智慧工业感知计算与决策重点实验室
• 3:西安建筑科技大学资源工程学院

摘要(Abstract)：

干滩长度是尾矿库安全管理的重要指标之一，针对传统干滩图像分割方法存在的工作量大、分割边界粗糙等问题，提出了一种基于多尺度空间特征PSPNet的干滩分割检测模型，模型总体分为预处理—特征提取—目标分割3个阶段。在预处理阶段，采用暗通道先验方法对采集到的有雾图像进行去雾处理；在特征提取阶段，采用DenseNet169作为骨干架构网络提取干滩的多尺度特征；在干滩目标分割阶段，首先引入密集空洞金字塔卷积和金字塔池化结构以增大感受野，然后利用高分辨率特征图将干滩图像恢复至原尺寸，最后对生成的干滩掩膜图像进行边界提取，以实现对干滩长度的测定。结果表明，相对于传统图像分割算法，该模型简化了前期预处理工作量，相比传统的语义分割精度MIoU提高了7.89%,PA提高了8.11%。因此该模型在复杂环境下对干滩长度数据提取具有较好的监测能力和泛化能力，能够为利用机器视觉监测尾矿坝干滩长度提供新的思路。

关键词(KeyWords)： 安全工程;尾矿库;干滩长度;多尺度特征;PSPNet

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(51974223,51774228);; 陕西省自然科学基础研究计划项目(2019JM-492)

作者(Authors): 阮顺领;文帅;卢才武;江松;

DOI: 10.13637/j.issn.1009-6094.2020.1828

参考文献(References)：

• [1] 陈善刚，苏军，袁子清，等.尾矿库安全在线监测技术探讨[J].有色金属(选矿部分),2011(3):64-67.CHEN S G,SU J,YUAN Z Q,et al.On line monitoring technology for tailings pond safety[J].Nonferrous Metals (Mineral Processing Section),2011(3):64-67.
• [2] 张诚，王建国.一种具有轨迹自动巡航的干滩测量方法[J].西安工业大学学报，2020,40(1):109-113.ZHANG C,WANG J G.A dry beach measurement method with automatic cruise trajectory[J].Journal of Xi'an Technological University,2020,40(1):109-113.
• [3] 张玉磊，牛昱光，李晓新.基于数字图像处理技术的尾矿坝干滩长度监测[J].矿业研究与开发，2013,33(6):106-108.ZHANG Y L,NIU Y G,LI X X.Digital image processing technology for monitoring the length of dry beach of tailings dam[J].Mining Research and Development,2013,33(6):106-108.
• [4] 胡军，刘泽北，胡珊.基于视觉测量的尾矿库干滩长度监测[J].工业安全与环保，2014,40(11):1-4.HU J,LIU Z B,HU S.Monitoring the length of dry beach of tailings pond based on visual measurement[J].Industrial Safety and Environmental Protection,2014,40(11):1-4.
• [5] 黄青松，李青，张金锋，等.基于图像分割的尾矿坝干滩长度监测[J].计算机测量与控制，2016,24(1):67-70.HUANG Q S,LI Q,ZHANG J F,et al.Image segmentation-based dry bank length monitoring of tailings dam[J].Computer Measurement and Control,2016,24(1):67-70.
• [6] 黄云，邓非，胡玉雷，等.近景摄影测量在干滩监测中的应用[J].测绘地理信息，2016,41(3):33-37.HUANG Y,DENG F,HU Y L,et al.Application of close-up photogrammetry in dry beach monitoring[J].Journal of Geomatics,2016,41(3):33-37.
• [7] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(4):640-651.
• [8] EICKEN T V,BASU A,BUCH V,et al.U-net:a user-level network interface for parallel and distributed computing (includes URL)[J].Acm Sigops Operating Systems Review,1995,29(5):40-53.
• [9] BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:a deep convolutional encoder decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
• [10] ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,America,Jul 21-26,2017.Hawaii:IEEE Xplore,2017:2881-2890.
• [11] CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV).Munich,Germany:Springer,2018:801-818.
• [12] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the 2016 Conference on Computer Vision and Pattern Recognition.New York:Institute of Electrical and Electronics Engineers,2016:770-778.
• [13] HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
• [14] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the 2016 Conference on Computer Vision and Pattern Recognition.New York:Institute of Electrical and Electronics Engineers,2016:770-778.
• [15] HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(9):1904-1916.
• [16] ZHANG W Z,LU G Q,ZHANG S C,et al.Self-paced hybrid dilated convolutional neural networks[J].Multimedia Tools and Applications,2020,4:1-13.