| 904 | 56 | 73 |
| 下载次数 | 被引频次 | 阅读次数 |
随着航天技术、计算机技术以及图像处理技术的发展,遥感图像的分辨率越来越高,覆盖范围也越来越广,高分辨率的遥感影像在军事侦察、地质勘探和国土资源等领域的应用也越来越广泛。"高分一号"作为我国"高分专项"系列卫星的首星,其图像处理技术对于其他高分影像处理具有重大的借鉴意义。针对"高分一号"遥感影像目标检测的问题,通过深度学习神经网络设计和优化,实现在遥感影像中准确检测机场、操场等基础设施目标。实验结果表明,深度学习网络用于遥感目标检测,具有良好的准确度和鲁棒性,从而为国产高分系列遥感卫星的应用提供多样化技术支持。
Abstract：With the development of aerospace technology,computer technology and image processing technology,the resolution of remote sensing images is getting higher and higher,and the coverage is wider and wider.High-resolution remote sensing images are widely used in military reconnaissance,geological prospecting,land resources and many other areas.GF1 is the first satellite of China's high resolution special program series,whose image processing technology is of great reference for other remote sensing image processing applications.Through the deep learning neural network design and optimization,GF1 remote sensing images can be used to detect the airport,playground and other infrastructure objectives accurately.Experimental results show that the deep learning network is used for remote sensing target detection with good accuracy and robustness.It provides a variety of technical support for the domestic high-score series of remote sensing satellite applications.
[1]王鑫.基于选择性视觉注意机制的遥感图像机场检测[D].上海:复旦大学,2012.
[2]陈金凤,程乾.高分1号融合光谱特征提取杭州湾河口沿岸湿地典型植被信息方法研究[J].杭州师范大学学报(自然科学版),2015,14(1):39-43.
[3]牛新,窦勇,张鹏,等.基于深度学习的光学遥感机场与飞行器目标识别技术[J].大数据,2016,5(1):54-67.
[4]LECUN Y,BOSER B,DENKER J S,et al.Backpropagation Applied to Handwritten Zip Code Recognition[J].Neural Computation,2008,1(4):541-551.
[5]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
[6]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,2015,37(9):1904-1916.
[7]GIRSHICK R.Fast R-CNN[C]∥IEEE International Conference on Computer Vision,IEEE,2015:1440-1448.
[8]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks[C]∥Neural Information Processing Systems,2015:1-3.
[9]UIJLINGS J R R,SANDE K E A V D,GEVERS T,et al.Selective Search for Object Recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[10]ZITNICK C L,DOLLAR P.Edge Boxes:Locating Object Proposals from Edges[M].Proceedings of the European Conference on Computer Vision,2014:391-405.
[11]CHENG M M,ZHANG Z,LIN W Y,et al.BING:Binarized Normed Gradients for Objectness Estimation at 300 fps[C]∥IEEE International Conference on Computer Vision.IEEE,2014:3286-3293.
[12]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]∥IEEE International Conference on Computer Vision,IEEE,2016:779-788.
[13]DENG J,DONG W,SOCHER R,et al.Image Net:A Largescale Hierarchical Image Database[C]∥IEEE International Conference on Computer Vision and Pattern Recognition,IEEE,2009:248-255.
[14]田子恒.基于遥感图像的桥梁目标检测方法研究[D].长春:东北大学,2012.
[15]王岳环,宋云峰,陈君灵.高分辨率遥感图像中油库的检测识别[J].华中科技大学学报(自然科学版),2011,39(2):110-112.
[16]帅通,师本慧,张霞,等.高分遥感舰船目标SIFT特征的提取与匹配[J].无线电工程,2015,45(11):48-51.
[17]HE K,ZHANG X,REN S,et al.Identity Mappings in Deep Residual Networks[C]∥Proceedings of the European Conference on Computer Vision,2016:630-645.
[18]DUMOULIN V,VISIN F.AGuide to Convolution Arithmetic for Deep Learning[J].ar Xiv:1603.07285[cs.CV],2016.
[19]SPRINGENBERG J T,DOSOVITSKIY A,BROX T,et al.Striving for Simplicity:The All Convolutional Net[C]∥International Conference on Learning Representations,2015.
[20]JIA Y,SHELHAMER E,DONAHUE J,et al.Caffe:Convolutional Architecturefor Fast Feature Embedding[J].ar Xiv:1408.5093[cs.CV],2014.
[21]季艳,鲁克文,张英慧.海量遥感数据分布式集群化存储技术研究[J].计算机科学与探索,2017(9):1398-1404.
基本信息:
DOI：
中图分类号:TP751
引用信息:
[1]王港,陈金勇,高峰等.基于深度学习的遥感影像基础设施目标检测研究[J].无线电工程,2018,48(03):219-224.
基金信息:
海洋公益性行业科研专项基金资助项目(201505002);; 中国电子科技集团公司航天信息应用技术重点实验室开放基金资助项目(EX166290025)