光谱-频域属性模式融合的高光谱遥感图像变化检测
Spectral-Frequency Domain Attribute Pattern Fusion for Hyperspectral Image Change Detection
- 2023年 页码：1-16
DOI： 10.11834/jrs.20232600
扫 描 看 全 文
摘要
高光谱作为“图谱合一”的遥感技术，具有精细光谱和空间影像的地面覆盖观测与识别优势。然而，高光谱遥感数据的光谱信息表征以及空间信息的利用给双时相高光谱遥感图像变化检测任务带了巨大的挑战。为此，本文探讨了一种光谱-频域属性模式融合的高光谱遥感图像变化检测方法（Spectral-Frequency Domain Attribute Pattern Fusion， SFDAPF）。首先，本文设计了一种基于梯度相关性的光谱绝对距离，使双时相高光谱遥感图像像元对的属性模式从光谱信息表征方面得到了逐级量化。其次，本文基于傅里叶变换理论提出了一种变化像元属性模式显著性增强策略，从全局空间信息利用方面改善了变化与非变化属性像元对的可分性。然后，将全图属性模式显著性水平与梯度相关性的光谱绝对距离进行融合，得到变化检测的综合界定值。最后，依据虚警阈值确定双时相高光谱遥感图像变化检测的二值化结果。本文方法在开源的双时相高光谱遥感图像河流和农场数据集上进行了变化检测性能验证，结果表明：本文SFDAPF方法能够优于传统的和最新的变化检测方法，变化检测的总体精度在河流和农场数据集上分别达到了0.96508和0.97287（最高精度为1.00000），证明了本文方法的有效性。
Abstract
(Objective),2,Hyperspectral imagery (HSI) is a three-dimensional cube data that combines spatial imagery and spectral information, which brings many conveniences to the accurate interpretation of observation information of ground coverings. However, there are also challenges in high-dimensional nonlinear data processing for the HSI change detection (HSI-CD) task. Therefore, a HSI change detection method based on spectral-frequency domain attribute pattern fusion (SFDAPF) is introduced to quantify the spectral representation of pixel attribute patterns step by step. Specifically, a saliency enhancement (SE) strategy for pixel attribute patterns based on Fourier transform theory is developed to improve the separability between pixel attribute patterns in our work. The proposed SFDAPF method consists of four components as follows.,(Method),2,First, a gradient correlation-based spectral absolute distance (GCASD) is designed in this paper, so that the attribute patterns of pixel pairs in bitemporal HSI can be quantified step by step from the aspect of spectral information representation. Then, according to Fourier transform theory, this paper proposed a SE strategy of attribute patterns of pixel pairs, which improves the separability of attribute patterns of changing and non-changing pixel pairs in terms of global spatial information utilization. Next, the saliency level and GCASD per pixel are fused to obtain the comprehensive discrimination value of change detection. Finally, according to the false alarm threshold, the binarization results of the bitemporal HSI-CD are obtained.,(Result),2,The proposed SFDAPF method is applied to two open-source bitemporal HSI datasets, i.e., River and Farmland datasets. Experimental results show that the proposed SFDAPF method can outperform the traditional and state-of-the-art HSI-CD methods. For the River dataset, compared with the traditional methods, the SFDAPF method in this paper introduces the local context information of the pixel in the calculation stage of the GCASD and adopts the global SE strategy, which is effective in reducing false alarms. Compared with the state-of-the-art methods, the SFDAPF method in this paper achieves the highest accuracy for most of the performance evaluation indicators. For the Farmland dataset, the AA, Kappa, F1, IoU, and OA indicators of the SFDAPF method in this paper have reached the highest accuracy, which is 0.01985, 0.05653, 0.01474, 0.02798, and 0.02187 higher than the second highest accuracy. In addition, the OAu (0.97500) and OAc (0.96766) indicators of the SFDAPF method did not achieve the highest accuracy, but they were only 0.00673 and 0.01237 lower than the highest accuracy, which can be called slightly lower than the highest accuracy. Therefore, the experiments verified the effectiveness of the proposed SFDAPF method in the HSI-CD task.,(Conclusion),2,In general, the proposed SFDAPF method fully considers the representation of spectral information and the utilization of neighborhood spatial information, and thus promoting overall accuracy of HSI-CD. However, the proposed SFDAPF method only considers the single-window eight-connected neighborhood in the spectral characterization stage as well as the magnitude features represented in the frequency domain. Therefore, in future research work, we will further explore the contribution of dual-window spectral information representation and phase information of frequency domain representation to HSI-CD task.
关键词
高光谱图像变化检测图像融合特征提取显著性分析傅里叶变换
Keywords
Hyperspectral image change detectionimage fusionfeature extractionsaliency analysisFourier transform
references
Baisantry M, Negi DS, and Manocha OP. 2012. Change vector analysis using enhanced PCA and inverse triangular function-based thresholding. Defence Science Journal. 62(4):236-42 [DOI: 10.14429/dsj.62.1072http://dx.doi.org/10.14429/dsj.62.1072]
Bovolo F, Bruzzone L, and Marconcini M. 2008. A novel approach to unsupervised change detection based on a semisupervised SVM and a similarity measure. IEEE Transactions on Geoscience and Remote Sensing. 46(7):2070-82 [DOI: 10.1109/TGRS.2008.916643http://dx.doi.org/10.1109/TGRS.2008.916643]
Carvalho J O A, Guimarães R F, Gillespie A R, Silva N C, Gomes R A. 2011. A new approach to change vector analysis using distance and similarity measures. Remote Sensing. 3(11):2473-93. [DOI: 10.3390/rs3112473http://dx.doi.org/10.3390/rs3112473]
Cong R, Lei J, Fu H, Cheng MM, Lin W, Huang Q. 2019. Review of visual saliency detection with comprehensive information. IEEE Transactions on circuits and Systems for Video Technology. 29(10):2941-59 [DOI: 10.1109/TCSVT.2018.2870832http://dx.doi.org/10.1109/TCSVT.2018.2870832]
Du P, Liu S, Gamba P, Tan K, and Xia J. 2012. Fusion of difference images for change detection over urban areas. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 5(4): 1076-86 [DOI: 10.1109/JSTARS.2012.2200879http://dx.doi.org/10.1109/JSTARS.2012.2200879]
Demir B, Bovolo F, and Bruzzone L. 2011. Detection of land-cover transitions in multitemporal remote sensing images with active-learning-based compound classification. IEEE Transactions on Geoscience and Remote Sensing. 50(5):1930-41 [DOI: 10.1109/TGRS.2011.2168534http://dx.doi.org/10.1109/TGRS.2011.2168534]
Du B, Ru L, Wu C, and Zhang L. 2019. Unsupervised deep slow feature analysis for change detection in multi-temporal remote sensing images. IEEE Transactions on Geoscience and Remote Sensing. 57(12):9976-92 [DOI: 10.1109/TGRS.2019.2930682http://dx.doi.org/10.1109/TGRS.2019.2930682]
Feng G, Xiao W, Dong J, and Wang S. SAR Image Change Detection Based on Frequency Domain Analysis and Random Multi-Graphs[J]. Journal of Applied Remote Sensing, 2017, 12(1)1:17 [DOI: 10.1117/1.JRS.12.016010].
Hemati M, Hasanlou M, Mahdianpari M, and Mohammadimanesh F. 2021. A systematic review of landsat data for change detection applications: 50 years of monitoring the earth. Remote Sensings. 13(15) [DOI: 10.3390/rs13152869]
Hou X, and Zhang L. 2007. Saliency detection: A spectral residual approach//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE:1-8 [DOI: 10.1109/CVPR.2007.383267http://dx.doi.org/10.1109/CVPR.2007.383267]
Hou Z, Li W, Li L, Tao R, and Du Q. 2021. Hyperspectral change detection based on multiple morphological profiles. IEEE Transactions on Geoscience and Remote Sensing. 60(5507312):1-12 [DOI: 10.1109/TGRS.2021.3090802http://dx.doi.org/10.1109/TGRS.2021.3090802]
Hou Z, Li W, and Du Q. 2021. A patch tensor-based change detection method for hyperspectral images// Proceedings of 2021 IEEE International Geoscience and Remote Sensing Symposium. Belgium: IEEE:4328-4331 [DOI: 10.1109/IGARSS47720.2021.9554630http://dx.doi.org/10.1109/IGARSS47720.2021.9554630]
Hu M, Wu C, Du B, and Zhang L. 2023. Binary change guided hyperspectral multiclass change detection. IEEE Transactions on Image Processing. 32:791-806 [DOI: 10.1109/TIP.2022.3233187http://dx.doi.org/10.1109/TIP.2022.3233187]
Jenjira Jaemsiri, Titijaroonroj T, and Rungrattanaubol J. 2019. Modified scale-space analysis in frequency domain based on adaptive multiscale Gaussian filter for saliency detection// Proceedings of 2019 16th International Joint Conference on Computer Science and Software Engineering. Chonburi: IEEE:218-223 [DOI: 10.1109/JCSSE.2019.8864211http://dx.doi.org/10.1109/JCSSE.2019.8864211]
Koch C and Poggio T. 1999. Predicting the visual world: silence is golden. Nature Neuroscience. 2(1):9-10 [DOI: 10.1038/4511http://dx.doi.org/10.1038/4511]
Kwan C. 2019. Methods and challenges using multispectral and hyperspectral images for practical change detection applications. Information. 10(11):353 [DOI: 10.3390/info10110353http://dx.doi.org/10.3390/info10110353]
Li Jian, Levine M. D, An X, Xu X, and He H. 2013. Visual saliency based on scale-space analysis in the frequency domain. IEEE Transactions on Pattern Analysis and Machine Intelligence. 35(4): 996-1010 [doi: 10.1109/TPAMI.2012.147http://dx.doi.org/10.1109/TPAMI.2012.147]
Li M, Li M, Zhang P, Wu Y, Song W, and An L. 2019. SAR image change detection using PCANet guided by saliency detection. IEEE Geoscience and Remote Sensing Letters. 16(3):402-406 [DOI: 10.1109/LGRS.2018.2876616http://dx.doi.org/10.1109/LGRS.2018.2876616]
Liu S, Marinelli D, Bruzzone L, and Bovolo F. 2019. A review of change detection in multitemporal hyperspectral images: Current techniques, applications, and challenges. IEEE Geoscience and Remote Sensing Magazine, 7(2): 140-158 [DOI: 10.1109/MGRS.2019.2898520http://dx.doi.org/10.1109/MGRS.2019.2898520]
Luo F, Du B, Zhan G L, Zhang L F, Tao D C. 2019. Feature learning using spatial-spectral hypergraph discriminant analysis for hyperspectral image[J]. IEEE Transactions on Cybernetics. 49(7):2406-2419.
Marchesi S and Bruzzone L. 2009. ICA and kernel ICA for change detection in multispectral remote sensing images//Proceedings of 2009 IEEE International Geoscience and Remote Sensing Symposium. South Africa: IEEE: (2)II-980 [DOI: 10.1109/IGARSS.2009.5418265http://dx.doi.org/10.1109/IGARSS.2009.5418265]
Nielsen A. A. 2007. The regularized iteratively reweighted MAD method for change detection in multi-and hyperspectral data. IEEE Transactions on Image Processing. 16(2):463-78 [DOI: 10.1109/TIP.2006.888195http://dx.doi.org/10.1109/TIP.2006.888195]
Ortiz R V, Vélez R M, and Roysam B. 2006. Change detection in hyperspectral imagery using temporal principal components. Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII. 6233: 368-377 [DOI: 10.1117/12.667961http://dx.doi.org/10.1117/12.667961]
Ou X, Liu L, Tu B, Zhang G, and Xu Z. 2022. A CNN framework with slow-fast band selection and feature fusion grouping for hyperspectral image change detection. IEEE Transactions on Geoscience and Remote Sensing, 60(5524716): 1-16 [DOI: 10.1109/TGRS.2022.3156041http://dx.doi.org/10.1109/TGRS.2022.3156041]
Prasad S, and Bruce LM. 2008. Limitations of principal components analysis for hyperspectral target recognition. IEEE Geoscience and Remote Sensing Letters. 5(4):625-9 [DOI: 10.1109/LGRS.2008.2001282http://dx.doi.org/10.1109/LGRS.2008.2001282]
Srivastava A, Lee AB, Simoncelli EP, and Zhu SC. 2003. On advances in statistical modeling of natural images. Journal of Mathematical Imaging and Vision. 18(1):17-33 [DOI: 10.1023/A:1021889010444http://dx.doi.org/10.1023/A:1021889010444]
Shang X D, Song M P, Wang Y L, Yu C Y, Yu H Y, Li F, Chang, C I. 2021. Target-constrained interference-minimized band selection for hyperspectral target detection. IEEE Transactions on Geoscience and Remote Sensing, 59(7): 6044-6064 [DOI: 10.1109/TGRS.2020.3010826http://dx.doi.org/10.1109/TGRS.2020.3010826]
Song A, Choi J, Han Y, Kim Y. 2018. Change detection in hyperspectral images using recurrent 3D fully convolutional networks. Remote Sensing. 10(11):1827 [DOI: 10.3390/rs10111827http://dx.doi.org/10.3390/rs10111827]
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, Wu Z Y, Zhang H H, Du Q. 2022. Hyperspectral anomaly detection: a survey. IEEE Geoscience and Remote Sensing Magazine, 10(1): 64-90 [DOI: 10.1109/MGRS.2021.3105440http://dx.doi.org/10.1109/MGRS.2021.3105440]
Tu B, Zhou C, Peng J, Zhang G, Peng Y. 2021. Feature extraction via joint adaptive structure density for hyperspectral imagery classification. IEEE Transactions on Instrumentation and Measurement. 70(5006916): 1-16 [DOI: 10.1109/TIM.2020.3038557http://dx.doi.org/10.1109/TIM.2020.3038557]
Wang L, Wang L, Wang Q, and Bruzzone L. 2022. RSCNet: A Residual Self-Calibrated Network for Hyperspectral Image Change Detection. IEEE Transactions on Geoscience and Remote Sensing. 60:1-17,5529917 [DOI: 10.1109/TGRS.2022.3177478http://dx.doi.org/10.1109/TGRS.2022.3177478]
Wang Q, Yuan Z, Du Q, and Li X. 2018. GETNET: A general end-to-end 2-D CNN framework for hyperspectral image change detection. IEEE Transactions on Geoscience and Remote Sensing. 57(1):3-13 [DOI: 10.1109/TGRS.2018.2849692http://dx.doi.org/10.1109/TGRS.2018.2849692]
Yousif O, and Ban Y. 2014. Improving SAR-based urban change detection by combining MAP-MRF classifier and nonlocal means similarity weights. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(10): 4288-4300 [DOI: 10.1109/JSTARS.2014.2347171http://dx.doi.org/10.1109/JSTARS.2014.2347171]
Zhang B, Yang W, Gao L, and Chen D. 2012. Real-time target detection in hyperspectral images based on spatial-spectral information extraction. EURASIP Journal on Advances in Signal Processing. (142):1-5 [DOI: 10.1186/1687-6180-2012-142http://dx.doi.org/10.1186/1687-6180-2012-142]
Zhao C, Cheng H, and Feng S. 2021. A spectral–spatial change detection method based on simplified 3-D convolutional autoencoder for multitemporal hyperspectral images. IEEE Geoscience and Remote Sensing Letters. 19:1-5 [DOI: 10.1109/LGRS.2021.3096526http://dx.doi.org/10.1109/LGRS.2021.3096526]
Zhou C, Tu B., Ren Q. and Chen S. 2022. Spatial peak-aware collaborative representation for hyperspectral imagery classification. IEEE Geoscience and Remote Sensing Letters, 19:1-5, noArt. 5506805 [DOI: 10.1109/LGRS.2021.3083416http://dx.doi.org/10.1109/LGRS.2021.3083416]
Zhou C, Tu B, Li N, He W, and Plaza A. 2021. Structure-Aware Multikernel Learning for Hyperspectral Image Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 14:9837-9854 [DOI: 10.1109/JSTARS.2021.3111740http://dx.doi.org/10.1109/JSTARS.2021.3111740]
Zhang J F, Xie L L, and Tao X X. 2003. Change detection of earthquake-damaged buildings on remote sensing image and its application in seismic disaster assessment//Proceedings of 2003 IEEE International Geoscience and Remote Sensing Symposium. Toulouse: IEEE: 2436-2438 [DOI: 10.1109/IGARSS.2003.1294467http://dx.doi.org/10.1109/IGARSS.2003.1294467]
Zheng K, Gao L, Liao W, Hong D, Zhang B, Cui X, and Chanussot J. 2020. Coupled convolutional neural network with adaptive response function learning for unsupervised hyperspectral super resolution. IEEE Transactions on Geoscience and Remote Sensing. 59(3):2487-502 [DOI: 10.1109/TGRS.2020.3006534http://dx.doi.org/10.1109/TGRS.2020.3006534]
Zhan T, Song B, Sun L, Jia X, Wan M, Yang G, and Wu Z. 2020. TDSSC: A three-directions spectral–spatial convolution neural network for hyperspectral image change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 14:377-388 [DOI: 10.1109/JSTARS.2020.3037070http://dx.doi.org/10.1109/JSTARS.2020.3037070]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
中山大学 地球科学与工程学院
中国科学院空天信息创新研究院
中国科学院大学 电子电气与通信工程学院
中国矿业大学 人工智能研究院
济南市勘察测绘研究院
- 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