深度学习自编码结合混合蛙跳算法提取农田高光谱影像端元
|
摘要
针对农田高光谱遥感影像端元提取和混合像元分解精度不高的问题,该文提出了利用深度学习自编码结合混合蛙跳算法的农田高光谱影像端元提取方法。首先,利用深度学习的栈式自编码模型对高光谱影像进行光谱特征提取,优选出备选端元集合;然后将影像端元提取问题转化为组合优化问题,设计了待优化的目标函数,通过混合蛙跳算法对目标函数进行优化从而实现对最佳端元组合的搜索;最后利用人工合成的不同信噪比农田高光谱数据和真实的农田高光谱影像,将该算法与3种现有的主要端元提取方法进行对比。试验结果表明,本文提出的端元提取算法对20、30和40 dB信噪比影像提取结果的平均光谱角分别达到0.106 88、0.030 32、0.009 94。对20、30和40 dB信噪比影像和真实影像提取结果的均方根误差分别达到0.050 8、0.015 9、0.005 1、0.006 7。与现有的主要端元提取方法相比,该方法具有端元提取精度高、对不同等级噪声鲁棒性好等优势,在农田高光谱遥感监测中具有广阔的应用前景。
Hyperspectral remote sensing image includes hundreds of narrow contiguous spectral bands with high spectral resolution, and can provides a contiguous spectral curve for each pixel, which is an important tool for the cropland monitoring in rapid and large-scale way. However, due to the contradiction between spectral resolution and spatial resolution, hyperspectral remote sensing image usually possesses relative low spatial resolution. Therefore, it is very important to mix various vegetation and soil at one pixel point for spectral decomposition in hyperspectral image and spectral unmixing of farmland. The first step in spectral unmixing is usually endmember extraction. Endmember extraction from a hyperspectral remote sensing image is to find some pixels(endmembers) and regard them as pure spectral reflectance of the vegetation and soil in the image to get the best accuracy of spectral unmixing results. So endmember extraction from hyperspectral remote sensing image can be regarded as a typical discrete optimization problem, which can be solved by swarm intelligence optimization algorithm. Before optimization, the spectral dimension of the image should be reduced by deep learning. In order to solve the problem of spectral unmixing of hyperspectral images, a method of extracting farmland endmember based on deep learning and shuffled frog leaping algorithm(SFLA) is proposed in this paper. Firstly, deep learning model named stacked auto encoders(SAE) was used to extract spectral features. SAE performs a non-linear transfer from the original spectral signals to a form with significant features and less dimensions. In the low-dimension space, the candidate endmembers were selected as the input of the SFLA. The purpose of extracting the candidate endmembers is to simplified the computational complexity in the next step. Secondly, the endmember extraction of hyperspectral image was transferred into the combinatorial optimization and the objective function was constructed, then the SFLA was used to optimize the objective functionto get the best combination of endmembers. The objective function in study was designed as the RMSE(root mean square error) between the real hyperspectral remote sensing image and the simulated hyperspectral remote sensing image using the endmembers and abundance after endmember extraction and spectral unmixing. Thirdly, 2 groups experiments were carried out on the synthetic hyperspectral datasets with 3 different SNR(signal to noise ratio, 20, 30 and 40 dB) and the real AVIRIS hyperspectral remote sensing dataset in Salinas region, respectively. In experiments, the experimental results of the proposed method was compared with that of 3 traditional methods for endmember extraction including the sequential maximum angle convex cone(SMACC), N-FINDR, Vertex Component Analysis(VCA). The results were evaluated by RMSE and spectral angle. The results showed that the RMSE was 0.050 8, 0.015 9, 0.005 1, 0.006 7 for 20, 30 and 40 dB dataset, and the real dataset, respectively. The average spectral angle was 0.106 88, 0.030 32, 0.009 94 for 20, 30 and 40 dB dataset respectively. The proposed method was better than traditional methods in terms of extraction accuracy, which had wide potential applications on cropland monitoring using hyperspectral remote sensing. The method proposed in this paper reduced the influence of the non-linear factors and the noise, better endmember extraction and spectral unmixing results(both less spectral angle and less RMSE) could be obtained, and the proposed method was robust when the noise of the image increased sharply. In conclusion, the endmember extraction method proposed by this study is of significant importance for the cropland monitoring using hyperspectral remote sensing and has a prosperous future for the application on the remote sensing of agriculture.
Hyperspectral remote sensing image includes hundreds of narrow contiguous spectral bands with high spectral resolution, and can provides a contiguous spectral curve for each pixel, which is an important tool for the cropland monitoring in rapid and large-scale way. However, due to the contradiction between spectral resolution and spatial resolution, hyperspectral remote sensing image usually possesses relative low spatial resolution. Therefore, it is very important to mix various vegetation and soil at one pixel point for spectral decomposition in hyperspectral image and spectral unmixing of farmland. The first step in spectral unmixing is usually endmember extraction. Endmember extraction from a hyperspectral remote sensing image is to find some pixels(endmembers) and regard them as pure spectral reflectance of the vegetation and soil in the image to get the best accuracy of spectral unmixing results. So endmember extraction from hyperspectral remote sensing image can be regarded as a typical discrete optimization problem, which can be solved by swarm intelligence optimization algorithm. Before optimization, the spectral dimension of the image should be reduced by deep learning. In order to solve the problem of spectral unmixing of hyperspectral images, a method of extracting farmland endmember based on deep learning and shuffled frog leaping algorithm(SFLA) is proposed in this paper. Firstly, deep learning model named stacked auto encoders(SAE) was used to extract spectral features. SAE performs a non-linear transfer from the original spectral signals to a form with significant features and less dimensions. In the low-dimension space, the candidate endmembers were selected as the input of the SFLA. The purpose of extracting the candidate endmembers is to simplified the computational complexity in the next step. Secondly, the endmember extraction of hyperspectral image was transferred into the combinatorial optimization and the objective function was constructed, then the SFLA was used to optimize the objective functionto get the best combination of endmembers. The objective function in study was designed as the RMSE(root mean square error) between the real hyperspectral remote sensing image and the simulated hyperspectral remote sensing image using the endmembers and abundance after endmember extraction and spectral unmixing. Thirdly, 2 groups experiments were carried out on the synthetic hyperspectral datasets with 3 different SNR(signal to noise ratio, 20, 30 and 40 dB) and the real AVIRIS hyperspectral remote sensing dataset in Salinas region, respectively. In experiments, the experimental results of the proposed method was compared with that of 3 traditional methods for endmember extraction including the sequential maximum angle convex cone(SMACC), N-FINDR, Vertex Component Analysis(VCA). The results were evaluated by RMSE and spectral angle. The results showed that the RMSE was 0.050 8, 0.015 9, 0.005 1, 0.006 7 for 20, 30 and 40 dB dataset, and the real dataset, respectively. The average spectral angle was 0.106 88, 0.030 32, 0.009 94 for 20, 30 and 40 dB dataset respectively. The proposed method was better than traditional methods in terms of extraction accuracy, which had wide potential applications on cropland monitoring using hyperspectral remote sensing. The method proposed in this paper reduced the influence of the non-linear factors and the noise, better endmember extraction and spectral unmixing results(both less spectral angle and less RMSE) could be obtained, and the proposed method was robust when the noise of the image increased sharply. In conclusion, the endmember extraction method proposed by this study is of significant importance for the cropland monitoring using hyperspectral remote sensing and has a prosperous future for the application on the remote sensing of agriculture.
引文
[1]Wu M,Huang W,Niu Z,et al.Fine crop mapping by combining high spectral and high spatial resolution remote sensing data in complex heterogeneous areas[J].Computers and Electronics in Agriculture,2017,139(6):1-9.
[2]杨红卫,童小华.中高分辨率遥感影像在农业中的应用现状[J].农业工程学报,2012,28(24):138-149.Yang Hongwei,Tong Xiaohua.Application status of middle and high resolution remote sensing images in agriculture[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2012,28(24):138-149.(in Chinese with English abstract)
[3]蓝金辉,邹金霖,郝彦爽,等.高光谱遥感影像混合像元分解研究进展[J].遥感学报,2018,22(1):13-27.Lan Jinhui,Zou Jinlin,Hao Yanshuang,et al.Research progress on ummixing of hyperspectral remote sensing imagery[J].Journal of Remote Sensing,2018,22(1):13-27.(in Chinese with English abstract)
[4]张成业,秦其明,陈理,等.高光谱遥感岩矿识别的研究进展[J].光学精密工程,2015,23(8):2407-2418.Zhang Chengye,Qin Qiming,Chen Li,et al.Research and development of mineral identification utilizing hyperspectral remote sensing[J].Optics and Precision Engineering,2015,23(8):2407-2418.(in Chinese with English abstract)
[5]Graceline Jasmine S,Pattabiraman V.Performance analysis of statistical-based pixel purity index algorithms for endmember extraction in hyperspectral imagery[J].Advances in Intelligent Systems and Computing.2018(645):10-21.
[6]Peter D B H,Wang X.Spectral representation of proton nmr spectroscopy for the pattern recognition of complex materials[J].Journal of Analysis and Testing,2017,1(2):1-10.
[7]王红军,熊俊涛,黎邹邹,等.基于机器视觉图像特征参数的马铃薯质量和形状分级方法[J].农业工程学报,2016,32(8):272-277.Wang Hongjun,Xiong Juntao,Li Zouzou,et al.Potato grading method of weight and shape based on imaging characteristics parameters in machine vision system[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2016,32(8):272-277(in Chinese with English abstract).
[8]Zhang C,Qin Q,Zhang T,et al.Endmember extraction from hyperspectral image based on discrete firefly algorithm(EE-DFA)[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,126(4):108-119.
[9]Makeev V V.Dividing a convex figure by a system of rays and inscribed polygons[J].Mathematics,2015,48(3):366-375.
[10]Plaza A,Plaza J,Martin G.Spatial-spectral endmember extraction from hyperspectral imagery using multi-band morphology and volume optimization[C].IEEE International Conference on Image Processing,2009(1):3721-3724.
[11]Gruninger J H,Ratkowski A J,Hoke M L.The sequential maximum angle convex cone(SMACC)endmember model[J].Proceedings of Spie,2004,5425(8):1-14.
[12]Berman M,Kiiveri H,Lagerstrom R,et al.ICE:a statistical approach to identifying endmembers in hyperspectral images[J].IEEE Transactions on Geoscience&Remote Sensing,2008,42(10):2085-2095.
[13]Manuel A,Hernandez C,Gallego J.A single individual evolutionary strategy for endmember search in hyperspectral images[J].Information Sciences,2004,161(3-4):181-197.
[14]Nascimento J M P,Dias J M B.Vertex component analysis:A fast algorithm to unmix hyperspectral data[J].IEEETransactions on Geoscience&Remote Sensing,2005,43(4):898-910.
[15]李宏俏.高光谱图像的光谱解混模型与算法研究[D].成都:电子科技大学,2017.Li Hongqiao.Study of Unmixing Models and Algorithms for Hyperspectral Images[D].Chengdu:University of Electronic Science and Technology of China,2017.(in Chinese with English abstract)
[16]金瑞,李小昱,颜伊芸,等.基于高光谱图像和光谱信息融合的马铃薯多指标检测方法[J].农业工程学报,2015,31(16):258-263.Jin Rui,Li Xiaoyu,Yan Yiyun,et al.Detection method of multi-target recognition of potato based on fusion of hyperspectral imaging and spectral information[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2015,31(16):258-263.(in Chinese with English abstract)
[17]Xu Mingming,Zhang Liangpei,Du Bo,et al.An image-based endmember bundle extraction algorithm using reconstruction error for hyperspectral imagery[J].Neurocomputing,2016,173(2):397-405.
[18]Zhang B,Sun X,Gao L,et al.Endmember extraction of hyperspectral remote sensing images based on the ant colony optimization(ACO)algorithm[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(11):4173-4176.
[19]Chen Y,Lin Z,Zhao X,et al.Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(6):2094-2107.
[20]Bengio Y,Lamblin P,Popovici D,et al.Greedy layer-wise training of deep networks[J].Advances in Neural Information Processing Systems,2007,19(1):153-160.
[21]Eusuff M M,Lansey K E.Optimization of water distribution network design using the shuffled frog leaping algorithm[J].Journal of Water Resources Planning and Management,2003,129(3):210-225.
[22]Daoden K,Thaiupthump T.A Modified Shuffled Frog Leaping Algorithm Using Truncated Gaussian Distribution in Frog’s Position Updating Process[J].Information Science and Applications(ICISA),2016,376(2):965-974
[23]崔广新,李殿奎.基于自编码算法的深度学习综述[J].计算机系统应用,2018,27(9):47-51.Cui Guangxin,Li Diankui.Overview on deep learning based on automatic encoder algorithms[J].Computer Systems&Applications,2018,27(9):47-51.(in Chinese with English abstract)
[24]Denisova A,Juravel Y,Myasnikov V.Linear spectral mixture analysis of hyperspectral images with atmospheric distortions[J].Computer Vision and Graphics.2016,9972(9):134-141
[25]Zhang B,Sun X,Gao L,et al.Endmember extraction of hyperspectral remote sensing images based on the discrete particle swarm optimization algorithm[J].IEEETransactions on Geoscience&Remote Sensing,2011,49(11):4173-4176.
[26]Filippi A M,Archibald R.Support vector machine-based endmember extraction[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(3):771-791.
[27]Miao L,Qi H.Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(3):765-777.
[28]Chan T H,Ambikapathi A M,Ma W K,et al.Robust affine set fitting and fast simplex volume max-min for hyperspectral endmember extraction[J].IEEE Transactions on Geoscience&Remote Sensing,2013,51(7):3982-3997.
[29]Rajabi R,Ghassemian H.Spectral unmixing of hyperspectral imagery using multilayer NMF[J].IEEE Geoscience and Remote Sensing Letters,2014,12(1):38-42.
[30]Chang C I,Xiong W,Liu W,et al.Linear spectral mixture analysis based approaches to estimation of virtual dimensionality in hyperspectral Imagery[J].IEEETransactions on Geoscience and Remote Sensing,2010,48(11):3960-3979.
[2]杨红卫,童小华.中高分辨率遥感影像在农业中的应用现状[J].农业工程学报,2012,28(24):138-149.Yang Hongwei,Tong Xiaohua.Application status of middle and high resolution remote sensing images in agriculture[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2012,28(24):138-149.(in Chinese with English abstract)
[3]蓝金辉,邹金霖,郝彦爽,等.高光谱遥感影像混合像元分解研究进展[J].遥感学报,2018,22(1):13-27.Lan Jinhui,Zou Jinlin,Hao Yanshuang,et al.Research progress on ummixing of hyperspectral remote sensing imagery[J].Journal of Remote Sensing,2018,22(1):13-27.(in Chinese with English abstract)
[4]张成业,秦其明,陈理,等.高光谱遥感岩矿识别的研究进展[J].光学精密工程,2015,23(8):2407-2418.Zhang Chengye,Qin Qiming,Chen Li,et al.Research and development of mineral identification utilizing hyperspectral remote sensing[J].Optics and Precision Engineering,2015,23(8):2407-2418.(in Chinese with English abstract)
[5]Graceline Jasmine S,Pattabiraman V.Performance analysis of statistical-based pixel purity index algorithms for endmember extraction in hyperspectral imagery[J].Advances in Intelligent Systems and Computing.2018(645):10-21.
[6]Peter D B H,Wang X.Spectral representation of proton nmr spectroscopy for the pattern recognition of complex materials[J].Journal of Analysis and Testing,2017,1(2):1-10.
[7]王红军,熊俊涛,黎邹邹,等.基于机器视觉图像特征参数的马铃薯质量和形状分级方法[J].农业工程学报,2016,32(8):272-277.Wang Hongjun,Xiong Juntao,Li Zouzou,et al.Potato grading method of weight and shape based on imaging characteristics parameters in machine vision system[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2016,32(8):272-277(in Chinese with English abstract).
[8]Zhang C,Qin Q,Zhang T,et al.Endmember extraction from hyperspectral image based on discrete firefly algorithm(EE-DFA)[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,126(4):108-119.
[9]Makeev V V.Dividing a convex figure by a system of rays and inscribed polygons[J].Mathematics,2015,48(3):366-375.
[10]Plaza A,Plaza J,Martin G.Spatial-spectral endmember extraction from hyperspectral imagery using multi-band morphology and volume optimization[C].IEEE International Conference on Image Processing,2009(1):3721-3724.
[11]Gruninger J H,Ratkowski A J,Hoke M L.The sequential maximum angle convex cone(SMACC)endmember model[J].Proceedings of Spie,2004,5425(8):1-14.
[12]Berman M,Kiiveri H,Lagerstrom R,et al.ICE:a statistical approach to identifying endmembers in hyperspectral images[J].IEEE Transactions on Geoscience&Remote Sensing,2008,42(10):2085-2095.
[13]Manuel A,Hernandez C,Gallego J.A single individual evolutionary strategy for endmember search in hyperspectral images[J].Information Sciences,2004,161(3-4):181-197.
[14]Nascimento J M P,Dias J M B.Vertex component analysis:A fast algorithm to unmix hyperspectral data[J].IEEETransactions on Geoscience&Remote Sensing,2005,43(4):898-910.
[15]李宏俏.高光谱图像的光谱解混模型与算法研究[D].成都:电子科技大学,2017.Li Hongqiao.Study of Unmixing Models and Algorithms for Hyperspectral Images[D].Chengdu:University of Electronic Science and Technology of China,2017.(in Chinese with English abstract)
[16]金瑞,李小昱,颜伊芸,等.基于高光谱图像和光谱信息融合的马铃薯多指标检测方法[J].农业工程学报,2015,31(16):258-263.Jin Rui,Li Xiaoyu,Yan Yiyun,et al.Detection method of multi-target recognition of potato based on fusion of hyperspectral imaging and spectral information[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2015,31(16):258-263.(in Chinese with English abstract)
[17]Xu Mingming,Zhang Liangpei,Du Bo,et al.An image-based endmember bundle extraction algorithm using reconstruction error for hyperspectral imagery[J].Neurocomputing,2016,173(2):397-405.
[18]Zhang B,Sun X,Gao L,et al.Endmember extraction of hyperspectral remote sensing images based on the ant colony optimization(ACO)algorithm[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(11):4173-4176.
[19]Chen Y,Lin Z,Zhao X,et al.Deep learning-based classification of hyperspectral data[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(6):2094-2107.
[20]Bengio Y,Lamblin P,Popovici D,et al.Greedy layer-wise training of deep networks[J].Advances in Neural Information Processing Systems,2007,19(1):153-160.
[21]Eusuff M M,Lansey K E.Optimization of water distribution network design using the shuffled frog leaping algorithm[J].Journal of Water Resources Planning and Management,2003,129(3):210-225.
[22]Daoden K,Thaiupthump T.A Modified Shuffled Frog Leaping Algorithm Using Truncated Gaussian Distribution in Frog’s Position Updating Process[J].Information Science and Applications(ICISA),2016,376(2):965-974
[23]崔广新,李殿奎.基于自编码算法的深度学习综述[J].计算机系统应用,2018,27(9):47-51.Cui Guangxin,Li Diankui.Overview on deep learning based on automatic encoder algorithms[J].Computer Systems&Applications,2018,27(9):47-51.(in Chinese with English abstract)
[24]Denisova A,Juravel Y,Myasnikov V.Linear spectral mixture analysis of hyperspectral images with atmospheric distortions[J].Computer Vision and Graphics.2016,9972(9):134-141
[25]Zhang B,Sun X,Gao L,et al.Endmember extraction of hyperspectral remote sensing images based on the discrete particle swarm optimization algorithm[J].IEEETransactions on Geoscience&Remote Sensing,2011,49(11):4173-4176.
[26]Filippi A M,Archibald R.Support vector machine-based endmember extraction[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(3):771-791.
[27]Miao L,Qi H.Endmember extraction from highly mixed data using minimum volume constrained nonnegative matrix factorization[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(3):765-777.
[28]Chan T H,Ambikapathi A M,Ma W K,et al.Robust affine set fitting and fast simplex volume max-min for hyperspectral endmember extraction[J].IEEE Transactions on Geoscience&Remote Sensing,2013,51(7):3982-3997.
[29]Rajabi R,Ghassemian H.Spectral unmixing of hyperspectral imagery using multilayer NMF[J].IEEE Geoscience and Remote Sensing Letters,2014,12(1):38-42.
[30]Chang C I,Xiong W,Liu W,et al.Linear spectral mixture analysis based approaches to estimation of virtual dimensionality in hyperspectral Imagery[J].IEEETransactions on Geoscience and Remote Sensing,2010,48(11):3960-3979.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |