基于深度学习的SSD模型尾矿库自动提取

doi:10.7523/j.issn.2095-6134.2020.03.009

中国科学院大学学报 ›› 2020, Vol. 37 ›› Issue (3): 360-367.DOI: 10.7523/j.issn.2095-6134.2020.03.009

基于深度学习的SSD模型尾矿库自动提取

闫凯^1,2, 沈汀¹, 陈正超¹, 闫弘轩¹

1. 中国科学院遥感与数字地球研究所, 北京 100094;
2. 中国科学院大学电子电气与通信工程学院, 北京 100094

收稿日期:2019-01-02 修回日期:2019-03-27 发布日期:2020-05-15
通讯作者: 陈正超
基金资助:
中国科学院A类战略性先导科技专项（XDA19080302）资助

Automatic extraction of tailing pond based on SSD of deep learning

YAN Kai^1,2, SHEN Ting¹, CHEN Zhengchao¹, YAN Hongxuan¹

1. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China;
2. School of Electronic Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, China

Received:2019-01-02 Revised:2019-03-27 Published:2020-05-15

摘要/Abstract

摘要： 针对华北地区尾矿库自动提取问题，将基于深度学习的SSD目标检测模型应用于遥感图像尾矿库提取。首先标记华北地区2 000个样本，随机挑选1 500个作为训练样本，剩余样本作为测试样本，验证模型的检测精度。分析卷积层对应感受野与图像中尾矿库尺寸关系，发现原始SSD模型漏检误检大型尾矿库。改进SSD模型结构，提出增加额外卷积层的策略，提高对大型尾矿库目标的检测精度。实验表明，在置信度阈值为0.3时，改进的SSD模型相比原始模型，检测精确率提高10.0%，召回率提高14.4%，提高了大型尾矿库检测精度。验证了基于深度学习的SSD目标检测模型自动提取尾矿库的可行性以及改进算法的有效性。

关键词: 深度学习, 目标检测, 尾矿库, SSD模型, 感受野

Abstract: In order to automatically extract tailing ponds in North China, the SSD target detection model based on deep learning is applied to extract tailing ponds from remote sensing images. Firstly, 2 000 samples in North China were labeled as the foundation of database. 1 500 samples were randomly selected as training samples, and the remaining samples were used as test samples to verify the detection accuracy of the model. By using the original SSD model, the targets of large tailing ponds can not be detected accurately. In this work the relationship between the corresponding receptive field of convolution layer and the size of tailing reservoir in image was analyzed. Moreover, in order to improve the detection accuracy of the model for large-scale tailing pond targets, we modified the structure of SSD model by introducing an extra convolution layer. Experiments show that, compared with the original SSD model, the modified SSD model improves the detection accuracy by 10% and the recall rate by 14.4% at 0.3 confidence level. The detection accuracy for large tailing ponds is also improved. In this work, the feasibility of automatic extraction of tailing reservoir based on deep learning SSD model and the effectiveness of the modified algorithm were verified.

Key words: deep learning, object detection, tailing pond, SSD model, receptive field

中图分类号:

TP753

闫凯, 沈汀, 陈正超, 闫弘轩. 基于深度学习的SSD模型尾矿库自动提取[J]. 中国科学院大学学报, 2020, 37(3): 360-367.

YAN Kai, SHEN Ting, CHEN Zhengchao, YAN Hongxuan. Automatic extraction of tailing pond based on SSD of deep learning[J]. , 2020, 37(3): 360-367.

参考文献

[1] 门永生,柴建设.我国尾矿库安全现状及事故防治措施[J].中国安全生产科学技术,2009,5(1):48-52.
[2] 侯兴玉.我国尾矿库现状及问题分析[J].现代矿业,2013(10):1-4.
[3] 郝利娜,张志,何文熹,等.鄂东南尾矿库高分辨率遥感图像识别因子研究[J].国土资源遥感,2012(3):154-158.
[4] 强建华.陕西省尾矿库遥感调查与环境影响分析[J].金属矿山,2013(10):112-115.
[5] 高永志,初禹,梁伟.黑龙江省矿集区尾矿库遥感监测与分析[J].国土资源遥感,2015,27(1):160-163.
[6] Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[7] 田玮,朱廷劭.基于深度学习的微博用户自杀风险预测[J].中国科学院大学学报,2018,35(1):131-136.
[8] Zhu X X, Tuia D, Mou L, et al. Deep learning in remote sensing:a comprehensive review and list of resources[J]. IEEE Geoscience and Remote Sensing Magazine, 2017, 5(4):8-36.
[9] Cheng G, Han J. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016,117(7):11-28.
[10] 吴蔚澜,蔡猛,田垚,等.低数据资源条件下基于Bottleneck特征与SGMM模型的语音识别系统[J].中国科学院大学学报,2015,32(1):97-102.
[11] Xu K F, Lei B, Zhang Y T. Retrieval of land surface emissivity using spectral and texture features based on neural network[J]. Journal of University of Chinese Academy of Sciences, 2018,35(1):102-108.
[12] 李松,魏中浩,张冰尘,等. 深度卷积神经网络在迁移学习模式下的SAR目标识别[J].中国科学院大学学报,2018,35(1):75-83.
[13] 朱思捷,雷斌,吴一戎.基于稠密卷积神经网络的遥感图像自动色彩校正[J].中国科学院大学学报,2019,36(1):93-100.
[14] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems. Curran Associates Inc,2012:1106-1114.
[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] Girshick R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015:1440-1448.
[17] Redmon J, Divvala S, Girshick R, et al. You only look once:unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition, 2016:779-788.
[18] Liu W, Anguelov D, Erhan D, et al. SSD:single shot multiBox detector[C]//European Conference on Computer Vision, 2016:21-37.
[19] Ren S, He K, Girshick R. Faster R-CNN:towards real-time object detection with region proposal networks[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[20] Szegedy C, Liu N W, Jia N Y, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2015:1-9.
[21] Erhan D, Szegedy C, Toshev A, et al. Scalable object detection using deep neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2013:2147-2154.
[22] 田永清,王安建,余克忍,等.山西省五台山-恒山地区脉状金矿成矿的地球动力学[J].华北地质矿产杂志,1998(4):301-456.
[23] Fawcett T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2005, 27(8):861-874.

基于深度学习的SSD模型尾矿库自动提取

Automatic extraction of tailing pond based on SSD of deep learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	席彦新, 计璐艳, 耿修瑞. 一种多时相遥感图像多目标检测算法[J]. 中国科学院大学学报, 2021, 38(4): 503-510.
[2]	黄萍萍, 王峰, 向俞明, 尤红建. 基于V-CSK视频遥感卫星运动目标检测跟踪方法[J]. 中国科学院大学学报, 2021, 38(3): 392-401.
[3]	周龙, 王伟强, 吕科. FACR：一种快速且准确的车辆识别器[J]. 中国科学院大学学报, 2021, 38(1): 130-136.
[4]	李森, 彭玲, 胡媛, 池天河. 基于FD-RCF的高分辨率遥感影像耕地边缘检测[J]. 中国科学院大学学报, 2020, 37(4): 483-489.
[5]	陈国炜, 刘磊, 郭嘉逸, 潘宗序, 胡文龙. 基于生成对抗网络的半监督遥感图像飞机检测[J]. 中国科学院大学学报, 2020, 37(4): 539-546.
[6]	卢凯旋, 李国清, 陈正超, 昝露洋, 李柏鹏, 高建威. 基于负样本多通道优化SSD网络的钢铁厂提取[J]. 中国科学院大学学报, 2020, 37(3): 352-359.
[7]	宋旭鸣, 沈逸飞, 石远明. 基于深度学习的智能移动边缘网络缓存[J]. 中国科学院大学学报, 2020, 37(1): 128-135.
[8]	刘洋, 罗晨希, 罗铁坚. 和积网络的性质分析及其有效性验证算法[J]. 中国科学院大学学报, 2020, 37(1): 136-143.
[9]	袁益琴, 何国金, 王桂周, 江威, 康金忠. 背景差分与帧间差分相融合的遥感卫星视频运动车辆检测方法[J]. 中国科学院大学学报, 2018, 35(1): 50-58.
[10]	王艳霞, 张毅. 机载单天线SAR动目标检测与参数估计[J]. 中国科学院大学学报, 2012, (2): 227-233.
[11]	宁忠磊, 王宏琦, 张正. 一种基于协方差矩阵的自动目标检测方法[J]. 中国科学院大学学报, 2010, 27(3): 370-375.