遥感影像目标的尺度特征卷积神经网络识别法

doi:10.11947/j.AGCS.2019.20180393

测绘学报 ›› 2019, Vol. 48 ›› Issue (10): 1285-1295.doi: 10.11947/j.AGCS.2019.20180393

遥感影像目标的尺度特征卷积神经网络识别法

董志鹏¹, 王密^1,2, 李德仁^1,2, 王艳丽¹, 张致齐¹

1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
2. 地球空间信息协同创新中心, 湖北武汉 430079

收稿日期:2018-08-20 修回日期:2019-01-20 出版日期:2019-10-20 发布日期:2019-10-24
通讯作者: 王密 E-mail:wangmi@whu.edu.cn
作者简介:董志鹏(1991-),男,博士,研究方向为高分辨遥感影像处理及信息提取。E-mail:zhipengdong@foxmail.com
基金资助:
国家自然科学基金（61825103；91638301）

Object detection in remote sensing imagery based on convolutional neural networks with suitable scale features

DONG Zhipeng¹, WANG Mi^1,2, LI Deren^1,2, WANG Yanli¹, ZHANG Zhiqi¹

1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
2. Collaborative Innovation Center of Geospatial Technology, Wuhan 430079, China

Received:2018-08-20 Revised:2019-01-20 Online:2019-10-20 Published:2019-10-24
Supported by:
The National Natural Science Foundation of China(Nos. 61825103;91638301)

摘要/Abstract

摘要： 高分辨率遥感影像的目标检测与识别，是高分对地观测系统中影像信息自动提取及分析理解的重要内容。针对传统影像目标检测与识别算法中人工设计特征稳健性与普适性差的问题，本文提出基于高分辨率遥感影像目标尺度特征的卷积神经网络检测与识别方法。首先通过统计遥感影像目标的尺度范围，获得卷积神经网络训练与测试过程中目标感兴趣区域合适的尺度大小。然后根据目标感兴趣区域合适的尺度，提出基于高分辨率遥感影像目标尺度特征的卷积神经网络检测与识别架构。通过WHU-RSone数据集对本文卷积神经网络架构与Faster-RCNN架构对比测试验证。试验结果表明，本文架构ZF模型和本文架构VGG-16模型的mean average precision （mAP）分别比Faster-RCNN ZF模型和Faster-RCNN VGG-16模型提高8.17%和8.31%，本文卷积神经网络架构可获得良好的影像目标检测与识别效果。

关键词: 高分辨率遥感影像, 目标检测与识别, 深度学习, 卷积神经网络, 目标尺度

Abstract: Object detection and recognition in high spatial resolution remote sensing images (HSRI) is an important part of image information automatic extraction, analysis and understanding in high resolution earth observation system. The robustness and universality of traditional object detection and recognition algorithms using artificial design object feature are poor. To solve these problems, object detection and recognition in HSRI based on convolutional neural networks (CNN) with suitable scale features is proposed. Firstly, the suitable scale of the region of interest (ROI) of object is obtained by statistic the scale range of object in HSRI in the process of training and testing of CNN. Then, a CNN framework for object detection and recognition in HSRI is designed according to the suitable object ROI scale. The mean average precision (mAP) of the proposed CNN framework and Faster-RCNN is tested using the WHU-RSone data set. The experimental results show that the mAP of ZF model and VGG-16 model of the proposed CNN framework are 8.17% and 8.31% higher than that of Faster R-CNN ZF model and Faster R-CNN VGG-16 model, respectively. The proposed CNN framework can obtain good object detection and recognition results.

Key words: high resolution remote sensing image, object detection and recognition, deep learning, convolutional neural network, object scale

中图分类号:

P237

董志鹏, 王密, 李德仁, 王艳丽, 张致齐. 遥感影像目标的尺度特征卷积神经网络识别法[J]. 测绘学报, 2019, 48(10): 1285-1295.

DONG Zhipeng, WANG Mi, LI Deren, WANG Yanli, ZHANG Zhiqi. Object detection in remote sensing imagery based on convolutional neural networks with suitable scale features[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(10): 1285-1295.

参考文献 25

[1]	李德仁, 王密, 沈欣, 等. 从对地观测卫星到对地观测脑[J]. 武汉大学学报(信息科学版), 2017, 42(2):143-149. LI Deren, WANG Mi, SHEN Xin, et al. From earth observation satellite to earth observation brain[J]. Geomatics and Information Science of Wuhan University, 2017, 42(2):143-149.
[2]	董志鹏, 王密, 李德仁. 一种融合超像素与最小生成树的高分辨率遥感影像分割方法[J]. 测绘学报, 2017, 46(6):734-742. DOI:10.11947/j.AGCS.2017.20160514. DONG Zhipeng, WANG Mi, LI Deren. A high resolution remote sensing image segmentation method by combining superpixels with minimum spanning tree[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(6):734-742. DOI:10.11947/j.AGCS.2017.20160514.
[3]	刘婧, 李培军. 结合结构和光谱特征的高分辨率影像分割方法[J]. 测绘学报, 2014, 43(5):466-473. DOI:10.13485/j.cnki.11-2089.2014.0087. LIU Jing, LI Peijun. A high resolution image segmentation method by combined structural and spectral characteristics[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5):466-473. DOI:10.13485/j.cnki.11-2089.2014.0087.
[4]	高常鑫, 桑农. 基于深度学习的高分辨率遥感影像目标检测[J]. 测绘通报, 2014(S1):108-111. DOI:10.13474/j.cnki.11-2246.2014.0625. GAO Changxin, SANG Nong. Deep learning for object detection in remote sensing image[J]. Bulletin of Surveying and Mapping, 2014(S1):108-111. DOI:10.13474/j.cnki.11-2246.2014.0625.
[5]	CHENG Gong, HAN Junwei, GUO Lei, et al. Object detection in remote sensing imagery using a discriminatively trained mixture model[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 85(11):32-43.
[6]	张剑清, 佘琼, 潘励. 基于LBP/C纹理的遥感影像居民地变化检测[J]. 武汉大学学报(信息科学版), 2008, 33(1):7-11. ZHANG Jianqing, SHE Qiong, PAN Li. Change detection of residential area by remote sensing image based on LBP/C texture[J]. Geomatics and Information Science of Wuhan University, 2008, 33(1):7-11.
[7]	MORANDUZZO T, MELGANI F, DAAMOUCHE A. An object detection technique for very high resolution remote sensing images[C]//Proceedings of the 8th IEEE International Workshop on Systems, Signal Processing and Their Applications. Algiers, Algeria:IEEE, 2013:79-83.
[8]	BRENNING A, LONG Shilei, FIEGUTH P. Detecting rock glacier flow structures using Gabor filters and IKONOS imagery[J]. Remote Sensing of Environment, 2012, 125(10):227-237.
[9]	DOU Peng, CHEN Yangbo, YUE Haiyun. Remote-sensing imagery classification using multiple classification algorithm-based AdaBoost[J]. International Journal of Remote Sensing, 2018, 39(3):619-639.
[10]	YANG Guang, FANG Shenghui. Improving remote sensing image classification by exploiting adaptive features and hierarchical hybrid decision trees[J]. Remote Sensing Letters, 2017, 8(2):156-164.
[11]	曲景影, 孙显, 高鑫. 基于CNN模型的高分辨率遥感图像目标识别[J]. 国外电子测量技术, 2016, 35(8):45-50. QU Jingying, SUN Xian, GAO Xin. Remote sensing image target recognition based on CNN[J]. Foreign Electronic Measurement Technology, 2016, 35(8):45-50.
[12]	卢艺帆, 张松海. 基于卷积神经网络的光学遥感图像目标检测[J]. 中国科技论文, 2017, 12(14):1583-1589, 1633. LU Yifan, ZHANG Songhai. Object detection in optical remote sensing images with convolutional neural networks[J]. China Sciencepaper, 2017, 12(14):1583-1589, 1633.
[13]	何海威, 钱海忠, 谢丽敏, 等. 立交桥识别的CNN卷积神经网络法[J]. 测绘学报, 2018, 47(3):385-395. DOI:10.11947/j.AGCS.2018.20170265. HE Haiwei, QIAN Haizhong, XIE Limin, et al. Interchange recognition method based on CNN[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(3):385-395. DOI:10.11947/j.AGCS.2018.20170265.
[14]	郑卓, 方芳, 刘袁缘, 等. 高分辨率遥感影像场景的多尺度神经网络分类法[J]. 测绘学报, 2018, 47(5):620-630. DOI:10.11947/j.AGCS.2018.20170191. ZHENG Zhuo, FANG Fang, LIU Yuanyuan, et al. Joint multi-scale convolution neural network for scene classification of high resolution remote sensing imagery[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(5):620-630. DOI:10.11947/j.AGCS.2018.20170191.
[15]	伍广明, 陈奇, SHIBASAKI R, 等. 基于U型卷积神经网络的航空影像建筑物检测[J]. 测绘学报, 2018, 47(6):864-872. DOI:10.11947/j.AGCS.2018.20170651. WU Guangming, CHEN Qi, SHIBASAKI R, et al. High precision building detection from aerial imagery using a U-Net like convolutional architecture[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6):864-872. DOI:10.11947/j.AGCS.2018.20170651.
[16]	戴玉超, 张静, PORIKLI F, 等. 深度残差网络的多光谱遥感图像显著目标检测[J]. 测绘学报, 2018, 47(6):873-881. DOI:10.11947/j.AGCS.2018.20170633. DAI Yuchao, ZHANG Jing, PORIKLI F, et al. Salient object detection from multi-spectral remote sensing images with deep residual network[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6):873-881. DOI:10.11947/j.AGCS.2018.20170633.
[17]	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.
[18]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9):1904-1916.
[19]	GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile:IEEE, 2015:1440-1448.
[20]	REN Shaoqing, HE Kaiming, GIRSHICK R, et al. 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.
[21]	温奇, 李苓苓, 刘庆杰, 等. 基于视觉显著性和图分割的高分辨率遥感影像中人工目标区域提取[J]. 测绘学报, 2013, 42(6):831-837. WEN Qi, LI Lingling, LIU Qingjie, et al. A man-made object area extraction method based on visual saliency detection and graph-cut segmentation for high resolution remote sensing imagery[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(6):831-837.
[22]	沈佳洁, 潘励, 胡翔云. 可变形部件模型在高分辨率遥感影像建筑物检测中的应用[J]. 武汉大学学报(信息科学版), 2017, 42(9):1285-1291. SHEN Jiajie, PAN Li, HU Xiangyun. Building detection from high resolution remote sensing imagery based on a deformable part model[J]. Geomatics and Information Science of Wuhan University, 2017, 42(9):1285-1291.
[23]	ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland:Springer, 2014:818-833.
[24]	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the 3rd International Conference on Learning Representations. San Diego, California:[s.n.], 2015.
[25]	EVERINGHAM M, ESLAMI S M A, VAN GOOL L, et al. The Pascal visual object classes challenge:a retrospective[J]. International Journal of Computer Vision, 2015, 111(1):98-136.

遥感影像目标的尺度特征卷积神经网络识别法

Object detection in remote sensing imagery based on convolutional neural networks with suitable scale features

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 25

相关文章 15

编辑推荐

Metrics

本文评价

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	毛文婧, 王卫林, 焦利民, 刘安宝. 基于深度学习的中国连续空间覆盖PM_2.5浓度预报[J]. 测绘学报, 2022, 51(3): 361-372.
[7]	金飞, 官恺, 刘智, 韩佳容, 芮杰, 李庆高. 无监督密集匹配特征提取网络性能分析[J]. 测绘学报, 2022, 51(3): 426-436.
[8]	何直蒙, 丁海勇, 安炳琪. 高分辨率遥感影像建筑物提取的空洞卷积E-Unet算法[J]. 测绘学报, 2022, 51(3): 457-467.
[9]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[10]	张永生, 张振超, 童晓冲, 纪松, 于英, 赖广陵. 地理空间智能研究进展和面临的若干挑战[J]. 测绘学报, 2021, 50(9): 1137-1146.
[11]	艾廷华. 深度学习赋能地图制图的若干思考[J]. 测绘学报, 2021, 50(9): 1170-1182.
[12]	龚健雅, 许越, 胡翔云, 姜良存, 张觅. 遥感影像智能解译样本库现状与研究[J]. 测绘学报, 2021, 50(8): 1013-1022.
[13]	杨必胜, 韩旭, 董震. 适用于城市场景大规模点云语义标识的深度学习网络[J]. 测绘学报, 2021, 50(8): 1059-1067.
[14]	陶超, 阴紫薇, 朱庆, 李海峰. 遥感影像智能解译:从监督学习到自监督学习[J]. 测绘学报, 2021, 50(8): 1122-1134.
[15]	杨秋莲, 刘艳飞, 丁乐乐, 孟凡效. 高分影像场景分类的半监督深度卷积神经网络学习方法[J]. 测绘学报, 2021, 50(7): 930-938.