Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (2): 431-440    DOI: 10.11873/j.issn.1004-0323.2021.2.0431
数据与图像处理     
高光谱遥感影像纹理特征提取的对比分析
邵文静(),孙伟伟(),杨刚
宁波大学地理与空间信息技术系,浙江 宁波 315211
Comparison of Texture Feature Extraction Methods for Hyperspectral Imagery Classification
Wenjing Shao(),Weiwei Sun(),Gang Yang
Department of Geography and Spatial Information Techniques,Ningbo University,Zhejiang 315211,China
 全文: PDF(11336 KB)   HTML
摘要:

地物的“同物异谱”或“异物同谱”问题,使得仅仅依据高光谱影像的光谱信息较难得到理想的分类精度。纹理特征是地物空间分布的重要结构信息,能够一定程度上弥补光谱特征在高光谱遥感影像分类中的不足。纹理特征提取在高光谱遥感影像分类中得到了诸多发展,然而当前的纹理特征方法缺乏较为全面的对比分析。因此,选取旋转不变局部二值模式、简单线性迭代、扩展形态剖面、差分形态剖面、属性剖面、3D-Gabor、联合双边滤波和导向滤波共8种典型的纹理特征方法,利用印第安纳、帕维亚大学和雄安3个高光谱数据集设计分类实验,采用分类精度、计算时间、总体分类精度的标准差来进行定量评价。实验结果表明:扩展形态剖面的总体分类精度和计算速度整体上优于其他7种方法。

关键词: 高光谱遥感纹理分类特征提取    
Abstract:

The problem of “same object with different spectrum” and “different objects with same spectrum” makes that it difficult to obtain high classification accuracy for hyperspectral images using the single spectral information. Texture feature is the important structural information of spatial distribution of ground objects, which can compensate for the deficiency of spectral features in the classification to some extent. Many texture feature extraction methods have been developed in hyperspectral image classification, but they are lacking of a comprehensive comparative analysis. Therefore, this paper aim to explore the classification performance of different texture feature extraction methods. The 8 selected methods include rotational invariant local binary mode (riLBP), Simple Linear Iteration (SLIC), Extended Morphological Profile (EMP), Differential Morphological Profile (DMP), Attribute Profile (AP), 3D-Gabor, Joint Bilateral Filtering (JBF) and Guided Filtering (GF) design classification experiments. Experimental results on Indiana Pines, Pavia University and Xiong'an datasets show that EMP behaves better than other methods both in overall classification accuracy and computational speeds.

Key words: Hyperspectral remote sensing    Texture    Classification    Feature extraction
收稿日期: 2019-12-12 出版日期: 2021-05-24
ZTFLH:  TP75  
基金资助: 国家自然科学基金项目(41971296);浙江省自然科学基金项目(LR1901D0001);武汉大学测绘遥感信息工程国家重点实验室开放基金(18R05)
通讯作者: 孙伟伟     E-mail: 1811073014@nbu.edu.cn;sunweiwei@nbu.edu.cn
作者简介: 邵文静(1996-),女,湖北江陵人,硕士研究生,主要从事高光谱分类研究。E?mail:1811073014@nbu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
邵文静
孙伟伟
杨刚

引用本文:

邵文静,孙伟伟,杨刚. 高光谱遥感影像纹理特征提取的对比分析[J]. 遥感技术与应用, 2021, 36(2): 431-440.

Wenjing Shao,Weiwei Sun,Gang Yang. Comparison of Texture Feature Extraction Methods for Hyperspectral Imagery Classification. Remote Sensing Technology and Application, 2021, 36(2): 431-440.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.2.0431        http://www.rsta.ac.cn/CN/Y2021/V36/I2/431

图1  印第安纳数据
图2  帕维亚大学数据
图3  雄安数据
地物类别纹理特征提取方法/%
riLBPSLICEMPDMPAP3D-GaborJBFGFSVM
苜蓿95.1284.8897.5698.5494.0229.0262.4429.7628.78
玉米未耕地98.3991.4697.3296.7695.9862.3782.1179.8155.83
玉米疏耕地98.8492.6498.5398.2697.0760.1364.3163.2747.20
玉米98.7582.8296.9099.0694.3849.3084.8463.9931.46
牧草地98.0193.6898.2197.2096.7787.3893.5694.1683.52
草树混合地99.3497.6399.8899.4899.0898.22100.00100.0090.91
修剪的牧草93.3395.2799.2097.6096.5374.0094.0096.0056.80
干牧草99.8498.51100.00100.0099.5997.56100.00100.0093.93
燕麦98.1577.22100.00100.0093.8426.678.331.1126.67
大豆未耕地98.7492.9497.9297.5396.7862.8286.1376.4658.49
大豆疏耕地99.3795.4599.6199.3398.4478.3795.2795.5078.79
大豆已耕地98.0084.1098.1397.4594.4247.7572.9068.1640.37
小麦100.0093.4899.1399.4698.0296.52100.0099.8993.04
树木99.8598.32100.0099.9899.5495.4099.8999.9394.39
林间小道99.1491.87100.0099.8397.7155.8860.7268.2732.02
钢铁塔94.8489.1796.43100.0095.1186.5593.8199.6480.12
OA98.9894.0298.8898.6494.2374.8488.0386.2369.66
AA98.1191.5498.6898.7896.7069.2581.1477.2562.02
KC98.8393.1798.7298.4593.4271.1269.7065.2665.08
表1  印第安纳数据的分类精度 (%)
地物类别纹理特征提取方法/%
riLBPSLICEMPDMPAP3D-GaborJBFGFSVM
柏油路91.4595.2496.6392.1897.9691.1897.8296.7388.69
草地99.2599.5199.8599.4599.6895.9299.8110096.05
沙砾94.6377.3198.4488.4794.5264.9973.6365.4247.16
树木60.1690.5197.3095.3093.8190.3589.8483.6875.35
金属板93.1898.3599.8696.5398.6398.6510010099.78
裸地98.6999.1699.9398.4398.4974.8579.1571.6753.72
沥青屋顶87.5690.8795.0894.7699.7171.1675.6377.7159.18
地砖95.4188.3795.0692.7698.0183.2697.7898.4479.34
阴影45.1890.3089.9182.0396.6595.4898.6299.7780.91
OA92.8795.6098.3396.2098.3689.0192.8893.0483.30
AA85.0692.1896.9093.3297.5085.0990.2588.1675.76
KC90.4994.1697.7894.9497.8285.3181.5580.7777.45
表2  帕维亚大学分类精度 (%)
地物类别纹理特征提取方法
riLBPSLICEMPDMPAP3D-GaborJBFGFSVM
复叶槭97.7698.5999.5496.8697.7991.7295.3396.1989.34
柳树93.7897.4699.9095.2798.8379.6563.4961.1175.31
房屋97.4398.8098.4796.7496.6595.1996.5997.0892.93
桃树94.1795.3197.1386.7888.8172.9784.2484.5868.11
国槐95.6897.1698.9293.8495.6687.1790.9892.2985.33
白腊梅98.8698.7599.5398.6399.1795.6699.3899.8493.98
草地89.8282.2492.7981.8476.3964.6156.5153.1755.55
水域99.0898.5299.3197.3997.9695.3699.1999.9294.71
稀疏林92.0081.3169.9347.8327.1714.230.000.0017.10
菜地92.9783.8793.9586.9181.0536.375.283.1534.02
杨树97.4496.4896.7890.2295.0486.6895.3896.5782.87
玉米96.2094.4998.6494.9794.2379.0393.2294.0873.82
梨树97.7996.8299.0196.1894.0685.2486.2686.6482.99
大豆66.3885.2593.4680.5980.7471.5098.3998.1260.38
OA97.8496.7298.5394.7294.7286.4189.9089.7783.76
AA93.5293.2295.5388.8687.4075.3876.0275.9171.89
KC94.2196.1898.2993.8393.8584.1676.3276.2581.07
表3  雄安分类精度 (%)
riLBPSLICEMPDMPAP3D-GaborJBFGF
印第安纳364.20225.3366.3266.66357.48149.3200.210.15
帕维亚大学5 351.0267.22100.18103.212 039.11 366.002.080.48
雄安14 798.63 020.59321.98328.467 913.02595.024.243.25
表4  不同方法的计算时间对比 (s)
图4  印第安纳数据分类图
图5  帕维亚大学数据分类图
图6  雄安分类图
1 Tong Qingxi, Zhang Bing, Zhang Lifu. Current Progress of Hyperspectral Remote Sensing in China[J]. Journal of Remote Sensing,2016,20(5):689-707.
1 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 Chen Weimin, Zhang Ling, Song Dongmei, et al. Research on Hyprespectral Imagery Land Cover Classification Method based on AdaBoost Improved Random Forest [J]. Remote Sensing Technology and Application, 2018, 33(4): 612-620.
2 陈伟民, 张凌, 宋冬梅,等. 基于AdaBoost改进随机森林的高光谱图像地物分类方法研究[J].遥感技术与应用,2018,33(4):612-620.
3 Sun W, Du Q. Hyperspectral Band Selection: A Review[J]. IEEE Geoscience and Remote Sensing Magazine, 2019, 7(2): 118-139. doi: 10.1109/MGRS.2019.2911100.
doi: 10.1109/MGRS.2019.2911100
4 Sun W, Yang G, Peng J, et al. Hyperspectral Band Selection Using Weighted Kernel Regularization[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2019,12(9):3665-3676. doi:10.1109/JSTARS.2019. 2922201.
doi: 10.1109/JSTARS.2019. 2922201
5 Peng J, Sun W, Du Q. Self-paced Joint Sparse Representation for the Classification of Hyperspectral Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(2): 1183-1194. doi: 10.1109/TGRS.2018.2865102.
doi: 10.1109/TGRS.2018.2865102
6 Qian Jin, Luo Ding. Feature Extraction from Hyperspectral Remote Sensing Imagery based on Semisupervised Dimensionality Reduction with Pairwise Constraint[J]. Remote Sensing Technology and Application, 2016, 29(4): 681-688.
6 钱进, 罗鼎. 基于成对约束半监督降维的高光谱遥感影像特征提取[J]. 遥感技术与应用,2016,29(4):681-688.
7 Zhou Zhuang,Li Shengyang,Zhang Kang,et al. Crop Mapping Using Remotely Sensed Spectral and Context Features based on CNN[J]. Remote Sensing Technology and Application, 2019, 34(4): 694-703.
7 周壮,李胜阳,张康,等.基于CNN和农作物光谱纹理特征进行作物分布制图[J]. 遥感技术与应用, 2019, 34(4): 694-703.
8 Su Hongjun, Spectral-Texture Feature Extraction and Classifier Ensemble for Hyperspectral Imagery[D]. Nanjing: Nanjing Normal University, 2011. [苏红军. 高光谱影像光谱一纹理特征提取与多分类器集成技术研究[D]. 南京: 南京师范大学, 2011.]
9 Bau T C, Sarkar S, Healey G. Using three-dimensional Spectral/spatial Gabor Filters for Hyperspectral Region Classification[C]∥Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIV. International Society for Optics and Photonics,2008,6966:69660E. doi: org/10.1117/12.777737.
doi: org/10.1117/12.777737
10 Kang X, Li S, Benediktsson J A. Spectral-spatial Hyperspectral Image Classification with Edge-preserving Filtering[J]. IEEE Transactions on Geoscience and Remote Sensing,2013, 52(5):2666-2677. doi: 10.1109/TGRS.2013.2264508.
doi: 10.1109/TGRS.2013.2264508
11 Li Z, Zhu Q, Wang Y, et al. Feature Extraction Method based on Spectral Dimensional Edge Preservation Filtering for Hyperspectral Image Classification[J]. International Journal of Remote Sensing, 2020, 41(1): 90-113. doi: org/10.1080/01431161.2019.1635723.
doi: org/10.1080/01431161.2019.1635723
12 Solberg A H S, Taxt T, Jain A K. A Markov Random Field Model for Classification of Multisource Satellite Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34(1):100-113. doi: 10.1109/36.481897.
doi: 10.1109/36.481897
13 Ghamisi P, Maggiori E, Li S, et al. New Frontiers in Spectral-spatial Hyperspectral Image Classification: The Latest Advances based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning[J]. IEEE Geoscience and Remote Sensing Magazine,2018,6(3):10-43. doi:10.1109/MGRS.2018.2854840.
doi: 10.1109/MGRS.2018.2854840
14 Gewali U B, Monteiro S T. A Tutorial on Modelling and Inference in Undirected Graphical Models for Hyperspectral Image Analysis[J]. International Journal of Remote Sensing, 2018,39(20):7104-7143. doi:org/10.1080/01431161.2018. 1465614.
doi: org/10.1080/01431161.2018. 1465614
15 Zhong P, Wang R. Learning Conditional Random Fields for Classification of Hyperspectral Images[J]. IEEE Transactions on Image Processing,2010,19(7):1890-1907. doi:10.1109/TIP. 2010.2045034.
doi: 10.1109/TIP. 2010.2045034
16 Zhang X, Chew S E, Xu Z, et al. SLIC Superpixels for Efficient Graph-based Dimensionality Reduction of Hyperspectral Imagery[C]∥Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXI. International Society for Optics and Photonics,2015,9472:947209. doi:org/10.1117/12.2176911.
doi: org/10.1117/12.2176911
17 Benediktsson J A, Palmason J A, Sveinsson J R. Classification of Hyperspectral Data from Urban Areas based on Extended Morphological Profiles[J]. IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):480-491. doi:10.1109/TGRS.2004.842478.
doi: 10.1109/TGRS.2004.842478
18 Dalla Mura M, Benediktsson J A, Waske B, et al. Morphological Attribute Profiles for the Analysis of Very High Resolution Images[J]. IEEE Transactions on Geoscience and Remote Sensing,2010,48(10):3747-3762. doi:10.1109/TGRS.2010. 2048116]
doi: 10.1109/TGRS.2010. 2048116
19 Ghamisi P, Souza R, Benediktsson J A, et al. Extinction Profiles for the Classification of Remote Sensing Data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(10): 5631-5645. doi: 10.1109/TGRS.2016.2561842.
doi: 10.1109/TGRS.2016.2561842
20 Hong D, Wu X, Ghamisi P, et al. Invariant Attribute Profiles: A Spatial-frequency Joint Feature Extractor for Hyperspectral Image Classification[J]. IEEE Transactions on Geoscience and Remote Sensing,2020,58(6):3791-3808. doi: 10.1109/TGRS.2019.2957251.
doi: 10.1109/TGRS.2019.2957251
21 Imani M, Ghassemian H. An Overview on Spectral and Spatial Information Fusion for Hyperspectral Image Classification: Current Trends and Challenges[J]. Information Fusion, 2020, 59: 59-83. doi:org/10.1016/j.inffus.2020.01.007.
doi: org/10.1016/j.inffus.2020.01.007
22 Pan L, He C, Xiang Y, et al. Multiscale Adjacent Superpixel-Based Extended Multi-Attribute Profiles Embedded Multiple Kernel Learning Method for Hyperspectral Classification[J]. Remote Sensing, 2021, 13(1): 50. doi: org/10.3390/rs 13010050]
doi: org/10.3390/rs 13010050
23 Cao X, Yao J, Xu Z, et al. Hyperspectral Image Classification with Convolutional Neural Network and Active Learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020,58(7):4604-4616.doi: 10.1109/TGRS.2020.2964627.
doi: 10.1109/TGRS.2020.2964627
24 Wang Fang, Yang Wunian, Wang Jian, al et, Selection and Evaluation of the Optimal Scale in Multi-scale Segmentation of Remote Sensing Images[J]. Remote Sensing Technology and application, 2020, 35(3): 623-633.
24 王芳,杨武年,王建,等.遥感影像多尺度分割中最优尺度的选取及评价[J].遥感技术与应用,2020,35(3):623-633.
25 Fauvel M, Tarabalka Y, Benediktsson J A, et al. Advances in Spectral-spatial Classification of Hyperspectral Images[J]. Proceedings of the IEEE,2012,101(3): 652-675. doi:10.1109/ JPROC.2012.2197589.
doi: 10.1109/ JPROC.2012.2197589
26 Song C, Yang F, Li P. Rotation Invariant Texture Measured by Local Binary Pattern for Remote Sensing Image Classification[C]∥2010 Second International Workshop on Education Technology and Computer Science. IEEE, 2010, 3: 3-6. doi: 10.1109/ETCS.2010.37.
doi: 10.1109/ETCS.2010.37
27 Duan W, Li S, Fang L. Spectral-spatial Hyperspectral Image Classification Using Superpixel and Extreme Learning Machines[C]∥Chinese Conference on Pattern Recognition. Springer, Berlin, Heidelberg, 2014: 159-167. doi:org/10.1007/978-3-662-45646-0_17.
doi: org/10.1007/978-3-662-45646-0_17
28 Huang X, Zhang L. An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-resolution Remotely Sensed Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing,2012,51(1):257-272.
29 Bao Rui, Xia Junshi, Xue Zhaohui, et al. Ensemble Classification for Hyperspectral Imagery based on Morphological Attribute Profiles[J]. Remote Sensing Technology and Application, 2016, 31(4):731-738.
29 鲍 蕊,夏俊士,薛朝辉,等. 基于形态学属性剖面的高光谱影像集成分类[J]. 遥感技术与应用, 2016, 31(4):731–730.
30 Dalla Mura M, Atli Benediktsson J, Waske B, et al. Extended Profiles with Morphological Attribute Filters for the Analysis of Hyperspectral Data[J]. International Journal of Remote Sensing,2010,31(22):5975-5991. doi:org/10.1080/01431161.2010. 512425.
doi: org/10.1080/01431161.2010. 512425
31 Bau T C, Sarkar S, Healey G. Hyperspectral Region Classification Using a Three-dimensional Gabor Filterbank[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(9): 3457-3464. doi:10.1109/TGRS.2010.2046494.
doi: 10.1109/TGRS.2010.2046494
32 Qiao T, Yang Z, Ren J, et al. Joint Bilateral Filtering and Spectral Similarity-based Sparse Representation: A Generic Framework for Effective Feature Extraction and Data Classification in Hyperspectral Imaging[J]. Pattern Recognition, 2018, 77: 316-328. doi: org/10.1016/j.patcog.2017.10.008.
doi: org/10.1016/j.patcog.2017.10.008
33 He K, Sun J, Tang X. Guided Image Filtering[C]∥European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2010: 1-14. doi: org/10.1007/978-3-642-15549-9_1.
doi: org/10.1007/978-3-642-15549-9_1
34 Li W,Chen C,Su H,et al. Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015,53(7):3681-3693. doi:10.1109/TGRS.2014. 2381602.
doi: 10.1109/TGRS.2014. 2381602
[1] 陈敏,潘佳威,李江杰,徐璐,刘加敏,韩健,陈奕云. 结合VGGNet与Mask R-CNN的高分辨率遥感影像建设用地检测[J]. 遥感技术与应用, 2021, 36(2): 256-264.
[2] 陈妮,应丰,王静,李健. 基于U-Net的高分辨率遥感图像土地利用信息提取[J]. 遥感技术与应用, 2021, 36(2): 285-292.
[3] 屈炀,袁占良,赵文智,陈学泓,陈家阁. 基于多时序特征和卷积神经网络的农作物分类[J]. 遥感技术与应用, 2021, 36(2): 304-313.
[4] 王晨丞,王永前,王利花. 基于SAR纹理信息的农作物识别研究——以农安县为例[J]. 遥感技术与应用, 2021, 36(2): 372-380.
[5] 尹燕旻,贾立. 基于Sentinel-2的闪电河流域农作物分类研究[J]. 遥感技术与应用, 2021, 36(2): 400-410.
[6] 郑琪,邸苏闯,潘兴瑶,刘洪禄,朱永华,张岑,周星. 基于Rapid Eye数据的北京生态涵养区土地利用分类及变化研究[J]. 遥感技术与应用, 2020, 35(5): 1118-1126.
[7] 牟昱璇,邬明权,牛铮,黄文江,杨尽. 南方地区复杂条件下的耕地面积遥感提取方法[J]. 遥感技术与应用, 2020, 35(5): 1127-1135.
[8] 程雨婷,刘昭华,鹿琳琳,刘士彪,李庆亭. 一带一路沿海超大城市热岛时空特征遥感分析[J]. 遥感技术与应用, 2020, 35(5): 1197-1205.
[9] 李宏达,高小红,汤敏. 基于CNN的不同空间分辨率影像土地覆被分类研究[J]. 遥感技术与应用, 2020, 35(4): 749-758.
[10] 杨瑞,祁元,苏阳. 深度学习U-Net方法及其在高分辨卫星影像分类中的应用[J]. 遥感技术与应用, 2020, 35(4): 767-774.
[11] 虞瑶,苏红军,姚文静. 基于Boosting的高光谱遥感切空间协同表示集成学习方法[J]. 遥感技术与应用, 2020, 35(3): 634-644.
[12] 谷祥辉,张英,桑会勇,翟亮,李少军. 基于哨兵2时间序列组合植被指数的作物分类研究[J]. 遥感技术与应用, 2020, 35(3): 702-711.
[13] 程娟,肖青,闻建光,唐勇,游冬琴,卞尊健,吴胜标,郝大磊,钟守熠. 地物波谱数据库应用方法及遥感应用现状[J]. 遥感技术与应用, 2020, 35(2): 267-286.
[14] 柴旭荣,李明,周义,王金风,田庆春. 影像的土地覆被快速分类[J]. 遥感技术与应用, 2020, 35(2): 315-325.
[15] 李强,冯德俊,瑚敏君,伍燚垚,杨历辉. 集成特征分量的高分二号影像阴影检测[J]. 遥感技术与应用, 2019, 34(6): 1252-1260.