基于多尺度形变特征卷积网络的高分辨率遥感影像目标检测

doi:10.11947/j.AGCS.2018.20170595

测绘学报 ›› 2018, Vol. 47 ›› Issue (9): 1216-1227.doi: 10.11947/j.AGCS.2018.20170595

基于多尺度形变特征卷积网络的高分辨率遥感影像目标检测

邓志鹏, 孙浩, 雷琳, 周石琳, 邹焕新

国防科技大学电子科学学院, 湖南长沙 410073

收稿日期:2017-10-17 修回日期:2018-05-02 出版日期:2018-09-20 发布日期:2018-09-26
通讯作者: 周石琳 E-mail:slzhou＠nudt.edu.cn
作者简介:邓志鹏(1990-),男,博士生,研究方向为机器学习,计算机视觉,遥感图像解译。E-mail:zpdeng@whu.edu.cn
基金资助:
国家自然科学基金（61303186）

Object Detection in Remote Sensing Imagery with Multi-scale Deformable Convolutional Networks

DENG Zhipeng, SUN Hao, LEI Lin, ZHOU Shilin, ZOU Huanxin

College of Electronic Science, National University of Defense Technology, Changsha 410073, China

Received:2017-10-17 Revised:2018-05-02 Online:2018-09-20 Published:2018-09-26
Supported by:
The National Natural Science Foundation of China (No. 61303186)

摘要/Abstract

摘要： 传统的基于滑窗搜索和人工设计特征相结合的目标检测方法难以适用于海量高分辨率遥感图像的目标检测任务。本文提出了一种基于多尺度形变特征卷积网络的目标检测方法，利用可形变卷积网络对具有尺度和方向变化的遥感图像目标进行特征提取，然后对多层残差模块提取出的形变特征进行区域预测和鉴别。具体模型包括两个子网络：①目标区域预测子网络用于从多层深度特征图提取目标候选区域；②目标区域鉴别子网络用于对目标候选区域进行分类和位置回归。本文在光学卫星图像10类目标数据集上对比了多种基于深度学习的目标检测算法，并将训练好的模型用于谷歌地球影像飞机坟场数据集和高分2号、吉林1号数据集的评估，试验结果表明本文方法能够快速准确地对多类目标进行检测，具有较好的稳健性和迁移性。

关键词: 遥感, 目标检测, 深度学习, 形变卷积层, 形变池化层

Abstract: Traditional target detection methods based on sliding window search paradigm and hand-craft based features are difficult to be applied to the multi-class target detection of very-high-resolution remote sensing images. In this paper,we proposed a deformable convolutional networks based multi-class target detection method by introducing deformable convolution layer and deformable RoI (Region-of-Interest) pooling layer. Specially,our method consists of two sub networks:a region proposal network aims to predict candidate regions from several layers with different filter size,and a region classification network for discrimination and regression. The quantitative comparison results on the challenging NWPU VHR-10 data set,large-scale Google Earth images, GF-2 and JL-1 images show that our method is more accurate and robust than existing algorithms.

Key words: remote sensing, object detection, deep learning, deformable convolutional layer, deformable pooling layer

中图分类号:

P237

邓志鹏, 孙浩, 雷琳, 周石琳, 邹焕新. 基于多尺度形变特征卷积网络的高分辨率遥感影像目标检测[J]. 测绘学报, 2018, 47(9): 1216-1227.

DENG Zhipeng, SUN Hao, LEI Lin, ZHOU Shilin, ZOU Huanxin. Object Detection in Remote Sensing Imagery with Multi-scale Deformable Convolutional Networks[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(9): 1216-1227.

参考文献

[1] CHENG Gong, HAN Junwei. A Survey on Object Detection in Optical Remote Sensing Images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117:11-28.
[2] 胡风明, 范学花, 杨汝良,等. 利用方向性粗糙度特征对SAR图像目标检测的研究[J]. 测绘学报, 2009, 38(3):229-235. DOI:10.3321/j.issn:1001-1595.2009.03.007. HU Fengming, FAN Xuehua, YANG Ruliang, et al. Study of Target Detection of SAR Image Using Directional Roughness Feature[J]. Acta Geodaetica et Cartographica Sinica, 2009, 38(3):229-235. DOI:10.3321/j.issn:1001-1595.2009.03.007.
[3] CHENG Gong, ZHOU Peicheng, HAN Junwei. Learning Rotation-invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12):7405-7415.
[4] QIU Shaohua, WEN Gongjian, LIU Jia, et al. Unified Partial Configuration Model Framework for Fast Partially Occluded Object Detection in High-resolution Remote Sensing Images[J]. Remote Sensing, 2018, 10(3):464.
[5] QIU Shaohua, WEN Gongjian, DENG Zhipeng, et al. Automatic and Fast PCM Generation for Occluded Object Detection in High-resolution Remote Sensing Images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10):1730-1734.
[6] QIU Shaohua, WEN Gongjian, FAN Yaxiang. Occluded Object Detection in High-resolution Remote Sensing Images using Partial Configuration Object Model[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(5):1909-1925.
[7] GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based Convolutional Networks for Accurate Object Detection and Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1):142-158.
[8] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago:IEEE Press, 2015:1440-1448.
[9] 许夙晖, 慕晓冬, 赵鹏, 等. 利用多尺度特征与深度网络对遥感影像进行场景分类[J]. 测绘学报, 2016, 45(7):834-840. DOI:10.11947/j.AGCS.2016.20150623. XU Suhui, MU Xiaodong, ZHAO Peng, et al. Scene Classification of Remote Sensing Image Based on Multi-scale Feature and Deep Neural Network[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(7):834-840. DOI:10.11947/j.AGCS.2016.20150623.
[10] 何小飞, 邹峥嵘, 陶超, 等. 联合显著性和多层卷积神经网络的高分影像场景分类[J]. 测绘学报, 2016, 45(9):1073-1080. DOI:10.11947/j.AGCS.2016.20150612. HE Xiaofei, ZOU Zhengrong, TAO Chao, et al. Combined Saliency with Multi-convolutional Neural Network for High Resolution Remote Sensing Scene Classification[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(9):1073-1080. DOI:10.11947/j.AGCS.2016.20150612.
[11] 许夙晖, 慕晓冬, 张雄美, 等. 结合对抗网络与辅助任务的遥感影像无监督域适应方法[J]. 测绘学报, 2017, 46(12):1969-1977. DOI:10.11947/j.AGCS.2017.20170291. XU Suhui, MU Xiaodong, ZHANG Xiongmei, et al. Unsupervised Remote Sensing Domain Adaptation Method with Adversarial Network and Auxiliary Task[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(12):1969-1977. DOI:10.11947/j.AGCS.2017.20170291.
[12] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montréal:MIT Press, 2015:91-99.
[13] 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. Las Vegas:IEEE, 2016:779-788.
[14] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD:Single Shot Multibox Detector[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam:Springer, 2016:21-37.
[15] DAI Jifeng, LI Yi, HE Kaiming, et al. R-Fcn:Object Detection Via Region-based Fully Convolutional Networks[C]//Advances in Neural Information Processing Systems 29. Barcelona:NIPS Press, 2016:379-387.
[16] TANG Tianyu, ZHOU Shilin, DENG Zhipeng, et al. Arbitrary-oriented Vehicle Detection in Aerial Imagery with Single Convolutional Neural Networks[J]. Remote Sensing, 2017, 9(11):1170.
[17] ZHANG Peng, NIU Xin, DOU Yong, et al. Airport Detection on Optical Satellite Images Using Deep Convolutional Neural Networks[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(8):1183-1187.
[18] YANG Yiding, ZHUANG Yin, BI Fukun, et al. M-FCN:Effective Fully Convolutional Network-based Airplane Detection Framework[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(8):1293-1297.
[19] LI Xiaobin, WANG Shengjin. Object Detection Using Convolutional Neural Networks in a Coarse-to-fine Manner[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(11):2037-2041.
[20] DENG Zhipeng, SUN Hao, ZHOU Shilin, et al. Toward Fast and Accurate Vehicle Detection in Aerial Images Using Coupled Region-based Convolutional Neural Networks[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(8):3652-3664.
[21] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE Press, 2016:770-778.
[22] JADERBERG M, SIMONYAN K, ZISSERMAN A. Spatial Transformer Networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems 28. Montréal:MIT Press, 2015:2017-2025.
[23] CAI Zhaowei, FAN Quanfu, FERIS R S, et al. A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam:Springer, 2016:354-370.
[24] LECUN Y, BOSER B, DENKER J S, et al. Backpropagation Applied to Handwritten Zip Code Recognition[J]. Neural Computation, 1989, 1(4):541-551.
[25] DAI Jifeng, QI Haozhi, XIONG Yuwen, et al. Deformable Convolutional Networks[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice:IEEE Press, 2017:1-13.
[26] NEUBECK A, GOOL L V. Efficient Non-maximum Suppression[C]//Proceedings of the 18th International Conference on Pattern Recognition. Hong Kong:IEEE Press, 2006:850-855.
[27] CHEN Tianqi, LI Mu, LI Yutian, et al. MXNnet:A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems[C]//Advances in Neural Information Processing Systems. Montréal:NIPS Press, 2015:1-16.

基于多尺度形变特征卷积网络的高分辨率遥感影像目标检测

Object Detection in Remote Sensing Imagery with Multi-scale Deformable Convolutional Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张祖勋, 姜慧伟, 庞世燕, 胡翔云. 多时相遥感影像的变化检测研究现状与展望[J]. 测绘学报, 2022, 51(7): 1091-1107.
[2]	王桥. 地表异常遥感探测与即时诊断方法研究框架[J]. 测绘学报, 2022, 51(7): 1141-1152.
[3]	张克非, 李浩博, 王晓明, 朱丹彤, 何琦敏, 李龙江, 胡安东, 郑南山, 李怀展. 地基GNSS大气水汽探测遥感研究进展和展望[J]. 测绘学报, 2022, 51(7): 1172-1191.
[4]	张良培, 何江, 杨倩倩, 肖屹, 袁强强. 数据驱动的多源遥感信息融合研究进展[J]. 测绘学报, 2022, 51(7): 1317-1337.
[5]	吴立新, 齐源, 毛文飞, 刘善军, 丁逸凡, 荆凤, 申旭辉. 多波段多极化被动微波遥感地震应用研究进展与前沿方向探索[J]. 测绘学报, 2022, 51(7): 1356-1371.
[6]	张兵, 杨晓梅, 高连如, 孟瑜, 孙显, 肖晨超, 倪丽. 遥感大数据智能解译的地理学认知模型与方法[J]. 测绘学报, 2022, 51(7): 1398-1415.
[7]	许强, 朱星, 李为乐, 董秀军, 戴可人, 蒋亚楠, 陆会燕, 郭晨. “天-空-地”协同滑坡监测技术进展[J]. 测绘学报, 2022, 51(7): 1416-1436.
[8]	程涛, 张洋, James Haworth. 基于网络和图的时空智能——概念、方法和应用[J]. 测绘学报, 2022, 51(7): 1629-1639.
[9]	李德仁, 王密, 杨芳. 新一代智能测绘遥感科学试验卫星珞珈三号01星[J]. 测绘学报, 2022, 51(6): 789-796.
[10]	龚健雅, 宦麟茜, 郑先伟. 影像解译中的深度学习可解释性分析方法[J]. 测绘学报, 2022, 51(6): 873-884.
[11]	张勤, 赵超英, 陈雪蓉. 多源遥感地质灾害早期识别技术进展与发展趋势[J]. 测绘学报, 2022, 51(6): 885-896.
[12]	李荣兴, 李国君, 冯甜甜, 沈强, 乔刚, 叶真, 夏梦莲. 基于光学遥感卫星影像的南极冰流速产品和方法研究综述[J]. 测绘学报, 2022, 51(6): 953-963.
[13]	程结海, 黄中意, 王建如, 何湜. 高空间分辨率遥感影像最优分割结果自动确定方法[J]. 测绘学报, 2022, 51(5): 658-667.
[14]	白坤, 慕晓冬, 陈雪冰, 朱永清, 尤轩昂. 融合半监督学习的无监督遥感影像场景分类[J]. 测绘学报, 2022, 51(5): 691-702.
[15]	龚健雅, 张觅, 胡翔云, 张展, 李彦胜, 姜良存. 智能遥感深度学习框架与模型设计[J]. 测绘学报, 2022, 51(4): 475-487.