首页 > 论文 > 光学学报 > 40卷 > 15期(pp:1528003--1)

多层感知卷积神经网络的国产多光谱影像分类

Domestic Multispectral Image Classification Based on Multilayer Perception Convolutional Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

联合像元谱段信息与空间结构特征,提出一种适用于多光谱遥感影像像素级分类的多层感知卷积神经网络(MPCNet),并基于吉林1号光谱卫星(Jilin-1GP)影像,在印度纳西克研究区对地表覆盖分类算法进行性能测试。为保证实验的高可靠性,在相同时间段结合Landsat8、Sentinel-2A及HJ-1A影像进行同步分类来定性与定量评估。除此之外,选取三个当前流行算法支持向量机(SVM)、LightGBM、浅层卷积神经网络(CNN)进行算法性能比较。实验结果表明,在Jilin-1GP影像上的总体分类精度可达94.0%~95.8%,Kappa系数达到0.932~0.948。相比准确率较高的浅层CNN,MPCNet的总体分类精度提升3.7个百分点。

Abstract

In this study, a multilayer perception convolutional neural network (MPCNet) was proposed for the pixel-level classification of multispectral remote sensing images, which combines the spectral information and spatial structure features of pixels. The performance of a land-cover-classification algorithm was tested based on the Jilin-1 spectral satellite (Jilin-1GP) images in the Nashik research area, India. To ensure high reliability of the experiment, the Landsat8, Sentinel-2A, and HJ-1A images were used within the same time interval for synchronized classification to perform qualitative and quantitative evaluations. Moreover, three current popular algorithms, namely, support vector machine(SVM), LightGBM, and shallow convolutional neural network(CNN), were selected to compare the algorithm performance. The experimental results indicate that the overall classification accuracy on the Jilin-1GP images can reach 94.0%-95.8%, and the Kappa coefficient can reach 0.932-0.948. The overall classification accuracy of the MPCNet increase by 3.7 percentage compared with that of the shallow CNN, which exhibits high accuracy.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP751.1

DOI:10.3788/AOS202040.1528003

所属栏目:遥感与传感器

基金项目:国家重点研发计划重点专项;

收稿日期:2020-04-01

修改稿日期:2020-05-06

网络出版日期:2020-08-01

作者单位    点击查看

朱瑞飞:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
马经宇:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012
李竺强:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012
王栋:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
安源:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
钟兴:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
高放:长光卫星技术有限公司吉林省卫星遥感应用技术重点实验室, 吉林 长春 130012
孟祥玉:吉林省国土资源调查规划研究院, 吉林 长春 130061

联系人作者:李竺强(skybelongtous@foxmail.com)

备注:国家重点研发计划重点专项;

【1】Tong Q X, Zhang B, Zhang L F. Current progress of hyperspectral remote sensing in China [J]. Journal of Remote Sensing. 2016, 20(5): 689-707.
童庆禧, 张兵, 张立福. 中国高光谱遥感的前沿进展 [J]. 遥感学报. 2016, 20(5): 689-707.

【2】Goetz A F H. Three decades of hyperspectral remote sensing of the earth: a personal view [J]. Remote Sensing of Environment. 2009, 113: S5-S16.

【3】Xu G H, Liu Q H, Chen L F, et al. Remote sensing for China''''s sustainable development: opportunities and challenges [J]. Journal of Remote Sensing. 2016, 20(5): 679-688.
徐冠华, 柳钦火, 陈良富, 等. 遥感与中国可持续发展: 机遇和挑战 [J]. 遥感学报. 2016, 20(5): 679-688.

【4】Zheng Y, Wu B F, Zhang M. Estimating the above ground biomass of winter wheat using the Sentinel-2 data [J]. Journal of Remote Sensing. 2017, 21(2): 318-328.
郑阳, 吴炳方, 张淼. Sentinel-2数据的冬小麦地上干生物量估算及评价 [J]. 遥感学报. 2017, 21(2): 318-328.

【5】Li X W, Shi H, Zhang Y, et al. Cyanobacteria blooms monitoring in Taihu lake based on the Sentinel-2A satellite of European space agency [J]. Environmental Monitoring in China. 2018, 34(4): 169-176.
李旭文, 侍昊, 张悦, 等. 基于欧洲航天局“哨兵-2A”卫星的太湖蓝藻遥感监测 [J]. 中国环境监测. 2018, 34(4): 169-176.

【6】Samaniego L, Bardossy A, Schulz K. Supervised classification of remotely sensed imagery using a modified k-NN technique [J]. IEEE Transactions on Geoscience and Remote Sensing. 2008, 46(7): 2112-2125.

【7】Cui B D. Remote sensing image classification based on SVM classifier [J]. Computer Engineering and Applications. 2011, 47(27): 189-191.
崔炳德. 支持向量机分类器遥感图像分类研究 [J]. 计算机工程与应用. 2011, 47(27): 189-191.

【8】Xie D F, Zhang J S, Pan Y Z, et al. Fusion of MODIS and Landsat 8 images to generate high spatial-temporal resolution data for mapping autumn crop distribution [J]. Journal of Remote Sensing. 2015, 19(5): 791-805.
谢登峰, 张锦水, 潘耀忠, 等. Landsat 8和MODIS融合构建高时空分辨率数据识别秋粮作物 [J]. 遥感学报. 2015, 19(5): 791-805.

【9】Lin W P, Wang C Y, Chu D P, et al. Extraction of fall crop types based on spectral analysis [J]. Transactions of the Chinese Society of Agricultural Engineering. 2006, 22(9): 128-132.
林文鹏, 王长耀, 储德平, 等. 基于光谱特征分析的主要秋季作物类型提取研究 [J]. 农业工程学报. 2006, 22(9): 128-132.

【10】Hu Y, Liu L Y, Peter C, et al. Landsat time-series land cover mapping with spectral signature extension method [J]. Journal of Remote Sensing. 2015, 19(4): 648-656.
胡勇, 刘良云, Peter C, 等. 光谱特征扩展的时间序列Landsat数据地表覆盖分类 [J]. 遥感学报. 2015, 19(4): 648-656.

【11】Yang B, Cao C X, Xing Y, et al. Automatic classification of remote sensing images using multiple classifier systems [J]. Mathematical Problems in Engineering. 2015, 1-10.

【12】Yu P X, Zhou X, Liu S H, et al. Feature extraction and recognition of erosion gully based on remote sensing image in the black soil region in Northeast China [J]. Journal of Remote Sensing. 2018, 22(4): 611-620.
于佩鑫, 周询, 刘素红, 等. 东北黑土区侵蚀沟遥感影像特征提取与识别 [J]. 遥感学报. 2018, 22(4): 611-620.

【13】Li Z Q, Zhu R F, Gao F, et al. Hyperspectral remote SensingImage classification based on three-dimensional convolution neural network combined with conditional random field optimization [J]. Acta Optica Sinica. 2018, 38(8): 0828001.
李竺强, 朱瑞飞, 高放, 等. 三维卷积神经网络模型联合条件随机场优化的高光谱遥感影像分类 [J]. 光学学报. 2018, 38(8): 0828001.

【14】Paoletti M E, Haut J M, Plaza J, et al. A new deep convolutional neural network for fast hyperspectral image classification [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2018, 145: 120-147.

【15】Zhou W X, Newsam S, Li C M, et al. PatternNet: a benchmark dataset for performance evaluation of remote sensing image retrieval [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2018, 145: 197-209.

【16】Kan X, Zhang Y H, Cao T, et al. Snow cover recognition for Qinghai-Tibetan Plateau using deep learning and multispectral remote sensing [J]. Acta Geodaetica et Cartographica Sinica. 2016, 45(10): 1210-1221.
阚希, 张永宏, 曹庭, 等. 利用多光谱卫星遥感和深度学习方法进行青藏高原积雪判识 [J]. 测绘学报. 2016, 45(10): 1210-1221.

【17】Pan B, Shi Z W, Xu X. MugNet: deep learning for hyperspectral image classification using limited samples [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2018, 145: 108-119.

【18】Zhang Z X, Wang X, Wen Q K, et al. Research progress of remote sensing application in land resources [J]. Journal of Remote Sensing. 2016, 20(5): 1243-1258.
张增祥, 汪潇, 温庆可, 等. 土地资源遥感应用研究进展 [J]. 遥感学报. 2016, 20(5): 1243-1258.

【19】Ke G L, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree . [C]//Advances in Neural Information Processing Systems 30, December 4-9, 2017, Long Beach, CA, USA. New York: Curran Associate. 2017.

【20】Szegedy C, Ioffe S, Vanhoucke V, et al. -08-23)[2020-03-28] [EB/OL]. inception-ResNet, the impact of residual connections on learning. 2016, org/abs/1602: 07261.Szegedy C, Ioffe S, Vanhoucke V, et al. -08-23)[2020-03-28] [EB/OL]. inception-ResNet, the impact of residual connections on learning. 2016, org/abs/1602: 07261.

【21】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition . [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 770-778.

【22】Gong P, Wang J, Yu L, et al. Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data [J]. International Journal of Remote Sensing. 2013, 34(7): 2607-2654.

【23】Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and Stochastic optimization [J]. The Journal of Machine Learning Research. 2011, 12(7): 257-269.

【24】Zhong P, Wang R S. Learning conditional random fields for classification of hyperspectral images [J]. IEEE Transactions on Image Processing. 2010, 19(7): 1890-1907.

【25】Zhao J, Zhong Y F, Zhang L P. Detail-preserving smoothing classifier based on conditional random fields for high spatial resolution remote sensing imagery [J]. IEEE Transactions on Geoscience and Remote Sensing. 2015, 53(5): 2440-2452.

【26】Xia M, Cao G, Wang G Y, et al. Remote sensing image classification based on deep learning and conditional random fields [J]. Journal of Image and Graphics. 2017, 22(9): 1289-1301.
夏梦, 曹国, 汪光亚, 等. 结合深度学习与条件随机场的遥感图像分类 [J]. 中国图象图形学报. 2017, 22(9): 1289-1301.

【27】Kr?henbühl P, Koltun V. Efficient inference in fully connected CRFs with Gaussian edge potentials . [C]//Advances in Neural Information Processing Systems 24, December 3-6, 2011, Granada, Spain. New York: Curran Associate. 2011.

引用该论文

Zhu Ruifei,Ma Jingyu,Li Zhuqiang,Wang Dong,An Yuan,Zhong Xing,Gao Fang,Meng Xiangyu. Domestic Multispectral Image Classification Based on Multilayer Perception Convolutional Neural Network[J]. Acta Optica Sinica, 2020, 40(15): 1528003

朱瑞飞,马经宇,李竺强,王栋,安源,钟兴,高放,孟祥玉. 多层感知卷积神经网络的国产多光谱影像分类[J]. 光学学报, 2020, 40(15): 1528003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF