联合空间信息的高光谱遥感协同表示动态集成分类算法
Dynamic selection algorithm for collaborative representation of hyperspectral remote sensing based on joint spatial information
- 2024年28卷第1期 页码：187-202
纸质出版日期： 2024-01-07
DOI： 10.11834/jrs.20221704
移动端阅览
浏览全部资源
扫码关注微信
摘要
近年来，集成学习成为高光谱遥感影像分类的研究热点，尤其是动态集成算法根据测试样本的特征自适应地选择最佳分类器，其分类性能显著提升。然而现有的动态集成方法仅考虑测试样本与验证样本的光谱信息，忽略了高度规则化的高光谱遥感影像包含的丰富空间信息。为进一步提升高光谱遥感影像动态集成算法分类的准确性和可靠性，提出了联合空间信息的可变K邻域动态集成算法VKS（Variable K-neighborhood and Spatial Information）和联合自适应邻域空间信息的可变K邻域动态集成算法VKSA（Variable K-neighborhood with Shape-Adaptive）。两种算法第一阶段综合考虑分类器精度与相似度自适应地改变测试样本的K邻域，第二阶段分别设计固定窗口和自适应窗口的嵌入方式增加地物的局部空间近邻关系，充分利用高光谱遥感影像地物复杂的空间形态结构信息。实验部分采用3组通用的高光谱遥感影像数据对所提出算法的性能进行综合评价。结果表明相比于传统的动态集成算法，本文提出的联合空间信息的动态集成模型能显著提升分类精度，其中基于自适应窗口方式的VKSA算法明显优于基于固定窗口的VKS算法。
Abstract
Ensemble learning has recently attracted considerable attention for hyperspectral image analysis. This model integrates multiple base classifiers for joint decision making
which is better than using a base classifier. Ensemble learning includes static and dynamic classifier ensembles. In the static ensemble method
the same classifier combination scheme is selected for testing sample. However
this method ignores the difference in classifier performance for each testing sample. Considering the features of testing sample
the best classifier is selected adaptively in dynamic ensemble methods. Therefore
this classifier can generally achieve better performance than static ensemble methods for hyperspectral image classification. However
numerous dynamic ensemble methods only consider the spectral information of the validation and training samples
ignoring the rich spatial information of hyperspectral images.
A Variable K-neighborhood and Spatial information algorithm (VKS) is proposed in this paper to further improve the accuracy and reliability of hyperspectral image classification. Firstly
the VKS algorithm comprehensively considers the accuracy and similarity of the classifier to adaptively adjust the K-neighborhood of the testing sample
increasing the reliability and flexibility of the region of competence setting. Thus
the testing samples with good spectral discrimination performance are preferentially classified. The label information of spatial neighborhood samples is used for predicting the testing samples with poor spectral discrimination performance. A fixed window is designed to provide local spatial information in hyperspectral images. However
fixed windows cannot reveal the complex and changeable morphological characteristics of ground objects. An adaptive window that can effectively reflect complex spatial information is proposed to capture the complex and changeable spatial structure in a hyperspectral image
and a variable K-neighborhood with a shape-adaptive (VKSA) algorithm is further designed.
The Purdue Campus
Indian Pines
and Salinas hyperspectral remote sensing data sets are used to design experiments and verify the performance of the proposed VKS and VKSA algorithms. Four state-of-the-art methods
namely
majority voting
overall local accuracy
modified local accuracy
and multiple classifier behavior
are used to quantify the classification accuracy. Experimental results demonstrate that the VKS and VKSA algorithms outperform static ensemble methods and three classic dynamic ensemble methods in overall classification accuracy. Moreover
the VKSA algorithm with an adaptive window perform better than the VKS algorithm with a fixed window.
关键词
高光谱遥感动态集成自适应邻域协同表示影像分类
Keywords
hyperspectral remote sensingdynamic selectionshape-adaptive neighborhoodcollaborative representationimage classification
references
Benediktsson J A, Chanussot J and Fauvel M. 2007. Multiple classifier systems in remote sensing: from basics to recent developments//7th International Workshop on Multiple Classifier Systems. Prague: Springer: 501-512 [DOI: 10.1007/978-3-540-72523-7_50http://dx.doi.org/10.1007/978-3-540-72523-7_50]
Bioucas-Dias J M, Plaza A, Camps-Valls G, Scheunders P, Nasrabadi N and Chanussot J. 2013. Hyperspectral remote sensing data analysis and future challenges. IEEE Geoscience and Remote Sensing Magazine, 1(2): 6-36 [DOI: 10.1109/mgrs.2013.2244672http://dx.doi.org/10.1109/mgrs.2013.2244672]
Chang C I. 2003. Hyperspectral Imaging: Techniques for Spectral Detection and Classification. New York: Plenum Publishing Co
Cruz R M O, Sabourin R and Cavalcanti G D C. 2015. META-DES. H: a dynamic ensemble selection technique using meta-learning and a dynamic weighting approach//Proceeding of 2015 International Joint Conference on Neural Networks (IJCNN). Killarney: IEEE, 2015: 1-8 [DOI: 10.1109/IJCNN.2015.7280594http://dx.doi.org/10.1109/IJCNN.2015.7280594]
Cruz R M O, Sabourin R and Cavalcanti G D C. 2018. Dynamic classifier selection: recent advances and perspectives. Information Fusion, 41: 195-216 [DOI: 10.1016/j.inffus.2017.09.010http://dx.doi.org/10.1016/j.inffus.2017.09.010]
Damodaran B B and Nidamanuri R R. 2014. Dynamic linear classifier system for hyperspectral image classification for land cover mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2080-2093 [DOI: 10.1109/JSTARS.2013.2294857http://dx.doi.org/10.1109/JSTARS.2013.2294857]
Damodaran B B, Nidamanuri R R and Tarabalka Y. 2015. Dynamic ensemble selection approach for hyperspectral image classification with joint spectral and spatial information. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2405-2417 [DOI: 10.1109/JSTARS.2015.2407493http://dx.doi.org/10.1109/JSTARS.2015.2407493]
Didaci L and Giacinto G. 2004. Dynamic classifier selection by adaptive k-nearest-neighbourhood rule//5th International Workshop on Multiple Classifier Systems. Cagliari: Springer: 174-183 [DOI: 10.1007/978-3-540-25966-4_17http://dx.doi.org/10.1007/978-3-540-25966-4_17]
Dos Santos E M, Sabourin R and Maupin P. 2008. A dynamic overproduce-and-choose strategy for the selection of classifier ensembles. Pattern recognition, 41(10): 2993-3009 [DOI: 10.1016/j.patcog.2008.03.027http://dx.doi.org/10.1016/j.patcog.2008.03.027]
Du P J, Xia J S, Xue Z H, Tan K, Su H J and Bao R. 2016. Review of Hyperspectral remote sensing image classification. Journal of Remote Sensing, 20(2): 236-256
杜培军, 夏俊士, 薛朝辉, 谭琨, 苏红军, 鲍蕊. 2016. 高光谱遥感影像分类研究进展. 遥感学报, 20(2): 236-256 [DOI: 10.11834/jrs.20165022http://dx.doi.org/10.11834/jrs.20165022]
Foi A, Katkovnik V and Egiazarian K. 2007. Pointwise shape-adaptive DCT for high-quality denoising and deblocking of grayscale and color images. IEEE Transactions on Image Processing, 16(5): 1395-1411 [DOI: 10.1109/TIP.2007.891788http://dx.doi.org/10.1109/TIP.2007.891788]
Fu W, Li S T, Fang L Y, Kang X D and Benediktsson J A. 2016. Hyperspectral image classification via shape-adaptive joint sparse representation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(2): 556-567 [DOI: 10.1109/JSTARS.2015.2477364http://dx.doi.org/10.1109/JSTARS.2015.2477364]
García S, Zhang Z L, Altalhi A, Alshomrani S and Herrera F. 2018. Dynamic ensemble selection for multi-class imbalanced datasets. Information Sciences, 445-446: 22-37 [DOI: 10.1016/j.ins.2018.03.002http://dx.doi.org/10.1016/j.ins.2018.03.002]
Giacinto G and Roli F. 2001. Dynamic classifier selection based on multiple classifier behaviour. Pattern Recognition, 34(9): 1879-1881 [DOI: 10.1016/S0031-3203(00)00150-3http://dx.doi.org/10.1016/S0031-3203(00)00150-3]
He L, Li J, Liu C Y and Li S T. 2018. Recent advances on spectral-spatial hyperspectral image classification: an overview and new guidelines. IEEE Transactions on Geoscience and Remote Sensing, 56(3): 1579-1597 [DOI: 10.1109/TGRS.2017.2765364http://dx.doi.org/10.1109/TGRS.2017.2765364]
Hou C Q, Xia Y J, Xu Z R and Sun J. 2016. Learning classifier competence based on graph for dynamic classifier selection//Proceeding of the 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). Changsha: IEEE, 2016: 1164-1168 [DOI: 10.1109/FSKD.2016.7603343http://dx.doi.org/10.1109/FSKD.2016.7603343]
Ko A H R, Sabourin R and Britto A S. 2008. From dynamic classifier selection to dynamic ensemble selection. Pattern Recognition, 41(5): 1718-1731 [DOI: 10.1016/j.patcog.2007.10.015http://dx.doi.org/10.1016/j.patcog.2007.10.015]
Kumar S, Ghosh J and Crawford M M. 2002. Hierarchical fusion of multiple classifiers for hyperspectral data analysis. Pattern Analysis and Applications, 5(2): 210-220 [DOI: 10.1007/s100440200019http://dx.doi.org/10.1007/s100440200019]
Kuncheva L I. 2000. Clustering-and-selection model for classifier combination//KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings (Cat. No.00TH8516). Brighton: IEEE: 185-188 [DOI: 10.1109/KES.2000.885788http://dx.doi.org/10.1109/KES.2000.885788]
Li D Y, Wen G H, Li X and Cai X F. 2019. Graph-based dynamic ensemble pruning for facial expression recognition. Applied Intelligence, 49(9): 3188-3206 [DOI: 10.1007/s10489-019-01435-2http://dx.doi.org/10.1007/s10489-019-01435-2]
Li W and Du Q. 2014. Joint within-class collaborative representation for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2200-2208 [DOI: 10.1109/JSTARS.2014.2306956http://dx.doi.org/10.1109/JSTARS.2014.2306956]
Peng J T, Sun W W and Du Q. 2019. Self-paced joint sparse representation for the classification of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 57(2): 1183-1194 [DOI: 10.1109/TGRS.2018.2865102http://dx.doi.org/10.1109/TGRS.2018.2865102]
Peng J T, Zhou Y C, Sun W W, Du Q and Xia L K. 2021. Self-paced nonnegative matrix factorization for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 59(2): 1501-1515 [DOI: 10.1109/TGRS.2020.2996688http://dx.doi.org/10.1109/TGRS.2020.2996688]
Smits P C. 2002. Multiple classifier systems for supervised remote sensing image classification based on dynamic classifier selection. IEEE Transactions on Geoscience and Remote Sensing, 40(4): 801-813 [DOI: 10.1109/TGRS.2002.1006354http://dx.doi.org/10.1109/TGRS.2002.1006354]
Su H J. 2022. Dimensionality reduction for hyperspectral remote sensing： Advances， challenges， and prospects. National Remote Sensing Bulletin， 26（8）：1504-1529
苏红军.2022.高光谱遥感影像降维：进展、挑战与展望.遥感学报，26（8）： 1504-1529 [DOI：10.11834/jrs.20210354http://dx.doi.org/10.11834/jrs.20210354]
Su H J and Liu H. 2017. A novel dynamic classifier selection algorithm using spatial-spectral information for hyperspectral classification. Remote Sensing for Land and Resources, 29(2): 15-21
苏红军, 刘浩. 2017. 一种利用空间和光谱信息的高光谱遥感多分类器动态集成算法. 国土资源遥感, 29(2): 15-21 [DOI: 10.6046/gtzyyg.2017.02.03http://dx.doi.org/10.6046/gtzyyg.2017.02.03]
Su H J, Yu Y, Du Q and Du P J. 2020. Ensemble learning for hyperspectral image classification using tangent collaborative representation. IEEE Transactions on Geoscience and Remote Sensing, 58(6): 3778-3790 [DOI: 10.1109/TGRS.2019.2957135http://dx.doi.org/10.1109/TGRS.2019.2957135]
Su H J, Zhao B, Du Q and Sheng Y H. 2016. Tangent distance-based collaborative representation for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 13(9): 1236-1240 [DOI: 10.1109/LGRS.2016.2578038http://dx.doi.org/10.1109/LGRS.2016.2578038]
Tang X, Meng F B, Zhang X R, Cheung Y M, Ma J J, Liu F and Jiao L C. 2021. Hyperspectral image classification based on 3-D octave convolution with spatial–spectral attention network. IEEE Transactions on Geoscience and Remote Sensing, 59(3): 2430-2447 [DOI: 10.1109/TGRS.2020.3005431http://dx.doi.org/10.1109/TGRS.2020.3005431]
Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
童庆禧, 张兵, 张立福. 2016. 中国高光谱遥感的前沿进展. 遥感学报, 20(5): 689-707 [DOI: 10.11834/jrs.20166264http://dx.doi.org/10.11834/jrs.20166264]
Woloszynski T and Kurzynski M A. 2011. Probabilistic model of classifier competence for dynamic ensemble selection. Pattern Recognition, 44(10-11): 2656-2668 [DOI: 10.1016/j.patcog.2011.03.020http://dx.doi.org/10.1016/j.patcog.2011.03.020]
Woods K, Kegelmeyer W P and Bowyer K. 1997. Combination of multiple classifiers using local accuracy estimates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(4): 405-410 [DOI: 10.1109/34.588027http://dx.doi.org/10.1109/34.588027]
Zhang L P and Zhang L F. 2005. Hyperspectral Remote Sensing. Wuhan: Wuhan University Press
张良培, 张立福. 2005. 高光谱遥感. 武汉: 武汉大学出版社
文章被引用时，请邮件提醒。
提交
相关作者
虞瑶 江苏省基础地理信息中心
苏红军 河海大学地球科学与工程学院
陶旸 江苏省基础地理信息中心
苏红军 河海大学 地球科学与工程学院
姚文静 河海大学 地球科学与工程学院
吴曌月 河海大学 地球科学与工程学院
岑奕 中国科学院空天信息创新研究院 遥感科学国家重点实验室
王跃明 中国科学院上海技术物理研究所 中国科学院空间主动光电技术重点实验室
相关机构
河海大学 地球科学与工程学院
中国科学院空天信息创新研究院 遥感科学国家重点实验室
中国科学院上海技术物理研究所 中国科学院空间主动光电技术重点实验室
中国科学院西安光学精密机械研究所 光谱成像技术实验室
中国科学院大学
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部