基于Mask R-CNN算法的遥感图像处理技术及其应用

doi:10.11896/jsjkx.190900119

计算机科学 ›› 2020, Vol. 47 ›› Issue (10): 151-160.doi: 10.11896/jsjkx.190900119

• 计算机图形学&多媒体 • 上一篇下一篇

基于Mask R-CNN算法的遥感图像处理技术及其应用

凌晨¹, 张鑫彤^2,3, 马雷²

1 军事科学院系统工程研究院后勤科学与技术研究所北京100166
2 中国科学院自动化研究所北京100190
3 河北工业大学人工智能与数据科学学院天津300401

收稿日期:2019-09-18 修回日期:2019-12-11 出版日期:2020-10-15 发布日期:2020-10-16
通讯作者: 马雷(lei.ma@ia.ac.cn)
作者简介:179897839@qq.com
基金资助:
国家自然科学青年基金(61806199)

Remote Sensing Image Processing Technology and Its Application Based on Mask R-CNN Algorithms

LING Chen¹, ZHANG Xin-tong^2,3, MA Lei²

1 Institute of Logistics Science and Technology,Beijing 100166,China
2 Institute of Automation,Chinese Academy of Science,Beijing 100190,China
3 School of Artificial Intelligence,Hebei University of Technology,Tianjin 300401,China

Received:2019-09-18 Revised:2019-12-11 Online:2020-10-15 Published:2020-10-16
About author:LING Chen, born in 1979,B.S.,assistant researcher.His research interests include internet of things and big data intelligence analysis.
MA Lei,born in 1980,Ph.D,associate professor.His main research interests include intelligent interpretation of remote sensing images.
Supported by:
Youth Program of National Natural Science Foundation of China (61806199)

摘要/Abstract

摘要： 遥感技术的发展使得遥感影像被应用于农业、军事等诸多领域,而深度学习方法的融入使得该项技术在目标检测、场景分类、语义分割方面取得了重大突破。与自然场景下的舰船检测不同,遥感图像中的舰船为俯视图,舰船较为密集,且容易与港口混合。当前对舰船检测的输出结果主要是检测框,缺少对舰船掩码的输出,使得无法全面分析出模型存在的不足;同时,由于遥感图像中的舰船停靠密集,容易产生漏检问题。为解决上述问题,利用Mask R-CNN对舰船进行目标检测,较全面地分析模型的训练情况、掩码和检测框的输出结果;通过对目标边缘的学习及参数的调整,使模型与舰船目标相适应。通过实验分析得出了适用于舰船检测的网络模型参数,从而有效降低了舰船停靠密集所产生的误检和漏检问题。

关键词: Mask R-CNN算法, 舰船目标检测, 深度学习, 遥感图像处理技术, 影像提取与识别

Abstract: With the development of remote sensing,there are many fields using remote sensing image,such as agriculture,military and so on.At the same time,deep learning,now,is applying in computer vision and image processing widely.It is successful in object detection,classification and semantic segmentation.Unlike fighting ship detection in natural scenes,fighting ships in remote sensing images are overhead views,dense and easy to mix with ports.The main result on fighting ship is taking bounding box as output,which is lacking the mask of the fighting ship,so may not analyzing the weakness in model.Meanwhile,because of the tight fighting ships in remote sensing images,there are easy to have missed detection.For solving the problems,this paper uses Mask R-CNN to detect fighting ships,analyzing training situation and the results of mask and bounding box.By learning the edges of objects and modifying parameter,making model more suitable to fighting ship.After experiment,it can be concluded that the appropriate parameters can effectively reduce the false positive and false negatives caused by compact berthing of fighting ships.

Key words: Deep learning, Image extraction and recognition, Mask R-CNN algorithm, Remote sensing image processing technology, Warship detection

中图分类号:

TP751

凌晨, 张鑫彤, 马雷. 基于Mask R-CNN算法的遥感图像处理技术及其应用[J]. 计算机科学, 2020, 47(10): 151-160. https://doi.org/10.11896/jsjkx.190900119

LING Chen, ZHANG Xin-tong, MA Lei. Remote Sensing Image Processing Technology and Its Application Based on Mask R-CNN Algorithms[J]. Computer Science, 2020, 47(10): 151-160. https://doi.org/10.11896/jsjkx.190900119

参考文献

[1]WU H B,HE Z,LI W J.Image Edge Detection Based on Improved Sobel Operator and Embedded Realization[J].Machine Tool & Hydraulics,2009,37(10):133-136.
[2]WANG N,LI X,An improved edge detection algorithm based on the Canny operator[J].Journal of Shenzhen University (Science and Engineering),2005,22(2):149-153.
[3]LIN X F,DING X Q,WU Y S,Theoretical Analysis of Confidence Estimation of Nearest Neighbor Classifier[J].Chinese Science Bulletin,1998,43(3):322-325.
[4]YANG G D,GUO C,ZHANG X Q.Research on Geometric Correction Method of GF-2 Image[J].Geomatics & Spatial Information Technology,2018,41(10):25-27.
[5]CHEN J W,CHANG S L,ZHANG Y Y.Multiscale time domain full waveform inversion based on cubic convolution interpolation[J].Journal of China Coal Society,2018,41(10):25-27.
[6]FU Z F,ZENG Z Y,ZHANG Z L.Wavelet and IHS transform combined to realize band fusion of ETM images[J].GEO-Information Science,2005,7(4):29-32.
[7]ZHANG X,ZHOU W,DUAN Z M.Convolutional sparse auto-encoder for image super-resolution reconstruction[J].Infrared and Laser Engineering.2019,48(1):324-330.
[8]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[9]KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNetClassification with Deep Convolutional Neural Networks[C]//NIPS.Curran Associates Inc.,2012:1097-1105.
[10]SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2016:2818-2826.
[11]YANG L,SU L H,WU B G,et al.Target Detection Algorithm of Hyperspectral Remote Sensing Imagery Combined with CEM[J].Journal of Chongqing University of Technology(Natural Science),2017(12):152-156,178.
[12]WANG W X,FU Y T,DONG F,et al.Remote sensing ship detection technology based on DoG preprocessing and shape features[C]//2017 3rd IEEE International Conference on Compu-ter and Communications (ICCC).2017.
[13]BI F K,CHEN J,ZHUANG Y,et al.A model based hierarchical method for inshore ship detection in high-resolution remote sensing images[C]//2017 IEEE International Geoscience and Remote Sensing Symposium(IGARSS).2017.
[14]HUANG J,JIANG Z G,ZHANG H P.Region proposal for ship detection based on structured forests edge method[C]//2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).2017.
[15]XIE X Y,Xu Q,Lei H.Fastership detection from optical satellite images based on ship distribution probability analysis[C]//International Workshop on Earth Observation & Remote Sen-sing Applications.IEEE,2016.
[16]LIU S T,JIANG K H,LIU Z X.Ship Target Detection of Aerial Reconnaissance Image Base on Region Covariance and bhicetness[J].Systems Engineering and Elecornics,2019(5).
[17]YE G Q,ZHA X,LI H B.High Resolution Remote Sensing Image Ship Detection Based on Visual Significance[J].Hydrographic Surveying And Charting,2018,38(4):51-55.
[18]YANG G,WEI P Z,DENG X.Detection Method of Ships inPort Based on SIFT Characteristics[J].Electronic Technology &Software Engineering 2017(5).
[19]ZHOU Y G,WANG P,GAO Y H.Remote Sensing Image Classi-fication with Bag-of-Visual-Words Model[J].Journal of Chongqing University of Technology(Natural Science),2015,29(5):71-77.
[20]HUANG J,JIANG Z G,ZHANG H P,et al.Ship object detection in remote sensing images using convolutional neural networks[J].Journal of Beijing University of Aeronautics and Astronautics,2017,43(9):132-139.
[21]ZOU Z,SHI Z.Ship Detection in Spaceborne Optical Image with SVD Networks[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(10):5832-5845.
[22]CHEN L Q,SHI W X,FAN E C.Ship detection in optical remote sensing images based on multi-class learning[J].Journal of Huazhong University of Science and Technology(NaturalScien-ce Edition),2019(5).
[23]ZHANG X,A method for ship detection and recognition in port area based on template matching and deep learning[J].Information Technology & Informatization,2019(4):59-63.
[24]ZHAO C H,ZHOU Y.Ship Target Detection and Recognition Based on Improved Faster R-CNN Algorithm[J].Journal of Shenyang University(Natural Science),2018,30(5).
[25]WU F,ZHOU Z Q,WANG B.Inshore Ship Detection Based on Convolutional Neural Network in Optical Satellite Images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(11):4005-4015.
[26]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2016,39(6):1137.
[27]LIN T Y,PIOTR D,GIRSHICK R,et al.Feature Pyramid Networks for Object Detection[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2017:2117-2125.
[28]WOLF C,JOLION J M.Object count Area Graphs for the Evaluation of Object Detection and Segmentation Algorithms[J].International Journal on Document Analysis and Recognition,2006,8(4):280-296.

相关文章 15

[1]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[5]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[6]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[7]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[8]	侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[9]	周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[10]	苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[11]	胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[12]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[13]	刘伟业, 鲁慧民, 李玉鹏, 马宁. 指静脉识别技术研究综述 Survey on Finger Vein Recognition Research 计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056
[14]	孙福权, 崔志清, 邹彭, 张琨. 基于多尺度特征的脑肿瘤分割算法 Brain Tumor Segmentation Algorithm Based on Multi-scale Features 计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217
[15]	康雁, 徐玉龙, 寇勇奇, 谢思宇, 杨学昆, 李浩. 基于Transformer和LSTM的药物相互作用预测 Drug-Drug Interaction Prediction Based on Transformer and LSTM 计算机科学, 2022, 49(6A): 17-21. https://doi.org/10.11896/jsjkx.210400150

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于Mask R-CNN算法的遥感图像处理技术及其应用

Remote Sensing Image Processing Technology and Its Application Based on Mask R-CNN Algorithms

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0